Fix fastapi version compat

TTS_TYPE = "EDGE_TTS"需要的依赖

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -34,7 +34,7 @@ body:
         - Others | 非最新版
     validations:
       required: true
-      
+
   - type: dropdown
     id: os
     attributes:
@@ -47,7 +47,7 @@ body:
         - Docker
     validations:
       required: true
-      
+
   - type: textarea
     id: describe
     attributes:
@@ -55,7 +55,7 @@ body:
       description: Describe the bug | 简述
     validations:
       required: true
-      
+
   - type: textarea
     id: screenshot
     attributes:
@@ -63,15 +63,9 @@ body:
       description: Screen Shot | 有帮助的截图
     validations:
       required: true
-      
+
   - type: textarea
     id: traceback
     attributes:
       label: Terminal Traceback & Material to Help Reproduce Bugs | 终端traceback（如有） + 帮助我们复现的测试材料样本（如有）
       description: Terminal Traceback & Material to Help Reproduce Bugs | 终端traceback（如有） + 帮助我们复现的测试材料样本（如有）
-
-
-
-
-
-

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -21,8 +21,3 @@ body:
     attributes:
       label: Feature Request | 功能请求
       description: Feature Request | 功能请求
-
-
-
-
-

.github/workflows/build-with-all-capacity-beta.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: build-with-all-capacity-beta
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_with_all_capacity_beta
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v2
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          push: true
+          file: docs/GithubAction+AllCapacityBeta
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/stale.yml

@@ -15,7 +15,7 @@ jobs:
     permissions:
       issues: write
       pull-requests: read
-    
+
     steps:
       - uses: actions/stale@v8
         with:

.gitignore

@@ -146,9 +146,11 @@ debug*
 private*
 crazy_functions/test_project/pdf_and_word
 crazy_functions/test_samples
-request_llm/jittorllms
+request_llms/jittorllms
 multi-language
-request_llm/moss
+request_llms/moss
 media
 flagged
-request_llm/ChatGLM-6b-onnx-u8s8
+request_llms/ChatGLM-6b-onnx-u8s8
+.pre-commit-config.yaml
+themes/common.js.min.*.js

Dockerfile

@@ -1,34 +1,34 @@
-# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型或者latex运行依赖，请参考 docker-compose.yml
-# 如何构建: 先修改 `config.py`， 然后 `docker build -t gpt-academic . `
-# 如何运行(Linux下): `docker run --rm -it --net=host gpt-academic `
-# 如何运行(其他操作系统，选择任意一个固定端口50923): `docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic `
+# 此Dockerfile适用于“无本地模型”的迷你运行环境构建
+# 如果需要使用chatglm等本地模型或者latex运行依赖，请参考 docker-compose.yml
+# - 如何构建: 先修改 `config.py`， 然后 `docker build -t gpt-academic . `
+# - 如何运行(Linux下): `docker run --rm -it --net=host gpt-academic `
+# - 如何运行(其他操作系统，选择任意一个固定端口50923): `docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic `
 FROM python:3.11
 
 
-# 非必要步骤，更换pip源
+# 非必要步骤，更换pip源 （以下三行，可以删除）
 RUN echo '[global]' > /etc/pip.conf && \
     echo 'index-url = https://mirrors.aliyun.com/pypi/simple/' >> /etc/pip.conf && \
     echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
 
 
-# 进入工作路径
+# 进入工作路径（必要）
 WORKDIR /gpt
 
 
-# 安装大部分依赖，利用Docker缓存加速以后的构建
+# 安装大部分依赖，利用Docker缓存加速以后的构建 （以下三行，可以删除）
 COPY requirements.txt ./
-COPY ./docs/gradio-3.32.2-py3-none-any.whl ./docs/gradio-3.32.2-py3-none-any.whl
 RUN pip3 install -r requirements.txt
 
 
-# 装载项目文件，安装剩余依赖
+# 装载项目文件，安装剩余依赖（必要）
 COPY . .
 RUN pip3 install -r requirements.txt
 
 
-# 非必要步骤，用于预热模块
+# 非必要步骤，用于预热模块（可以删除）
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 
 
-# 启动
+# 启动（必要）
 CMD ["python3", "-u", "main.py"]

README.md

@@ -1,71 +1,98 @@
-> **Note**
+> [!IMPORTANT]
+> 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)  
+> 2024.4.30: 3.75版本引入Edge-TTS和SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)  
+> 2024.3.11: 恭迎Claude3和Moonshot，全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！  
+> 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。
+
+<br>
+
+<div align=center>
+<h1 aligh="center">
+<img src="docs/logo.png" width="40"> GPT 学术优化 (GPT Academic)
+</h1>
+
+[![Github][Github-image]][Github-url]
+[![License][License-image]][License-url]
+[![Releases][Releases-image]][Releases-url]
+[![Installation][Installation-image]][Installation-url]
+[![Wiki][Wiki-image]][Wiki-url]
+[![PR][PRs-image]][PRs-url]
+
+[Github-image]: https://img.shields.io/badge/github-12100E.svg?style=flat-square
+[License-image]: https://img.shields.io/github/license/binary-husky/gpt_academic?label=License&style=flat-square&color=orange
+[Releases-image]: https://img.shields.io/github/release/binary-husky/gpt_academic?label=Release&style=flat-square&color=blue
+[Installation-image]: https://img.shields.io/badge/dynamic/json?color=blue&url=https://raw.githubusercontent.com/binary-husky/gpt_academic/master/version&query=$.version&label=Installation&style=flat-square
+[Wiki-image]: https://img.shields.io/badge/wiki-项目文档-black?style=flat-square
+[PRs-image]: https://img.shields.io/badge/PRs-welcome-pink?style=flat-square
+
+[Github-url]: https://github.com/binary-husky/gpt_academic
+[License-url]: https://github.com/binary-husky/gpt_academic/blob/master/LICENSE
+[Releases-url]: https://github.com/binary-husky/gpt_academic/releases
+[Installation-url]: https://github.com/binary-husky/gpt_academic#installation
+[Wiki-url]: https://github.com/binary-husky/gpt_academic/wiki
+[PRs-url]: https://github.com/binary-husky/gpt_academic/pulls
+
+
+</div>
+<br>
+
+**如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或插件，欢迎发pull requests！**
+
+If you like this project, please give it a Star.
+Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanese.md) | [한국어](docs/README.Korean.md) | [Русский](docs/README.Russian.md) | [Français](docs/README.French.md). All translations have been provided by the project itself. To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
+<br>
+
+> [!NOTE]
+> 1.本项目中每个文件的功能都在[自译解报告](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告)`self_analysis.md`详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题请查阅wiki。
+>    [![常规安装方法](https://img.shields.io/static/v1?label=&message=常规安装方法&color=gray)](#installation)  [![一键安装脚本](https://img.shields.io/static/v1?label=&message=一键安装脚本&color=gray)](https://github.com/binary-husky/gpt_academic/releases)  [![配置说明](https://img.shields.io/static/v1?label=&message=配置说明&color=gray)](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明) [![wiki](https://img.shields.io/static/v1?label=&message=wiki&color=gray)]([https://github.com/binary-husky/gpt_academic/wiki/项目配置说明](https://github.com/binary-husky/gpt_academic/wiki))
 >
-> 2023.7.8: Gradio, Pydantic依赖调整，已修改 `requirements.txt`。请及时**更新代码**，安装依赖时，请严格选择`requirements.txt`中**指定的版本**
->
-> `pip install -r requirements.txt`
+> 2.本项目兼容并鼓励尝试国内中文大语言基座模型如通义千问，智谱GLM等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交即可生效。
 
-
-# <div align=center><img src="docs/logo.png" width="40"> GPT 学术优化 (GPT Academic)</div>
-
-**如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或函数插件，欢迎发pull requests！**
-
-If you like this project, please give it a Star. If you've come up with more useful academic shortcuts or functional plugins, feel free to open an issue or pull request. We also have a README in [English|](docs/README_EN.md)[日本語|](docs/README_JP.md)[한국어|](https://github.com/mldljyh/ko_gpt_academic)[Русский|](docs/README_RS.md)[Français](docs/README_FR.md) translated by this project itself.
-To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
-
-> **Note**
->
-> 1.请注意只有 **高亮** 标识的函数插件（按钮）才支持读取文件，部分插件位于插件区的**下拉菜单**中。另外我们以**最高优先级**欢迎和处理任何新插件的PR。
->
-> 2.本项目中每个文件的功能都在[自译解报告`self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告)详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题[`wiki`](https://github.com/binary-husky/gpt_academic/wiki)。[安装方法](#installation) | [配置说明](https://github.com/binary-husky/gpt_academic/wiki/%E9%A1%B9%E7%9B%AE%E9%85%8D%E7%BD%AE%E8%AF%B4%E6%98%8E)。
-> 
-> 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM和Moss等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。
-
-
- 
+<br><br>
 
 <div align="center">
 
 功能（⭐= 近期新增功能） | 描述
 --- | ---
-⭐[接入新模型](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)！ | 百度[千帆](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu)与文心一言, [通义千问](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)，上海AI-Lab[书生](https://github.com/InternLM/InternLM)，讯飞[星火](https://xinghuo.xfyun.cn/)，[LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
-一键润色 | 支持一键润色、一键查找论文语法错误
-一键中英互译 | 一键中英互译
-一键代码解释 | 显示代码、解释代码、生成代码、给代码加注释
+⭐[接入新模型](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B) | 百度[千帆](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu)与文心一言, 通义千问[Qwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)，上海AI-Lab[书生](https://github.com/InternLM/InternLM)，讯飞[星火](https://xinghuo.xfyun.cn/)，[LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)，[智谱GLM4](https://open.bigmodel.cn/)，DALLE3, [DeepseekCoder](https://coder.deepseek.com/)
+⭐支持mermaid图像渲染 | 支持让GPT生成[流程图](https://www.bilibili.com/video/BV18c41147H9/)、状态转移图、甘特图、饼状图、GitGraph等等（3.7版本）
+⭐Arxiv论文精细翻译 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
+⭐[实时语音对话输入](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [插件] 异步[监听音频](https://www.bilibili.com/video/BV1AV4y187Uy/)，自动断句，自动寻找回答时机
+⭐AutoGen多智能体插件 | [插件] 借助微软AutoGen，探索多Agent的智能涌现可能！
+⭐虚空终端插件 | [插件] 能够使用自然语言直接调度本项目其他插件
+润色、翻译、代码解释 | 一键润色、翻译、查找论文语法错误、解释代码
 [自定义快捷键](https://www.bilibili.com/video/BV14s4y1E7jN) | 支持自定义快捷键
-模块化设计 | 支持自定义强大的[函数插件](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
-[自我程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] [一键读懂](https://github.com/binary-husky/gpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)本项目的源代码
-[程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] 一键可以剖析其他Python/C/C++/Java/Lua/...项目树
-读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [函数插件] 一键解读latex/pdf论文全文并生成摘要
-Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [函数插件] 一键翻译或润色latex论文
-批量注释生成 | [函数插件] 一键批量生成函数注释
-Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？
-chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
-[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [函数插件] PDF论文提取题目&摘要+翻译全文（多线程）
-[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
-Latex论文一键校对 | [函数插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
-[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
-互联网信息聚合+GPT | [函数插件] 一键[让GPT从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)回答问题，让信息永不过时
-⭐Arxiv论文精细翻译 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
-⭐[实时语音对话输入](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [函数插件] 异步[监听音频](https://www.bilibili.com/video/BV1AV4y187Uy/)，自动断句，自动寻找回答时机
+模块化设计 | 支持自定义强大的[插件](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [插件] 一键剖析Python/C/C++/Java/Lua/...项目树 或 [自我剖析](https://www.bilibili.com/video/BV1cj411A7VW)
+读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [插件] 一键解读latex/pdf论文全文并生成摘要
+Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [插件] 一键翻译或润色latex论文
+批量注释生成 | [插件] 一键批量生成函数注释
+Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？就是出自他的手笔
+[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [插件] PDF论文提取题目&摘要+翻译全文（多线程）
+[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
+Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
+[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
+互联网信息聚合+GPT | [插件] 一键[让GPT从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)回答问题，让信息永不过时
 公式/图片/表格显示 | 可以同时显示公式的[tex形式和渲染形式](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)，支持公式、代码高亮
-多线程函数插件支持 | 支持多线调用chatgpt，一键处理[海量文本](https://www.bilibili.com/video/BV1FT411H7c5/)或程序
 启动暗色[主题](https://github.com/binary-husky/gpt_academic/issues/173) | 在浏览器url后面添加```/?__theme=dark```可以切换dark主题
-[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？
-⭐ChatGLM2微调模型 | 支持加载ChatGLM2微调模型，提供ChatGLM2微调辅助插件
+[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)伺候的感觉一定会很不错吧？
 更多LLM模型接入，支持[huggingface部署](https://huggingface.co/spaces/qingxu98/gpt-academic) | 加入Newbing接口(新必应)，引入清华[Jittorllms](https://github.com/Jittor/JittorLLMs)支持[LLaMA](https://github.com/facebookresearch/llama)和[盘古α](https://openi.org.cn/pangu/)
 ⭐[void-terminal](https://github.com/binary-husky/void-terminal) pip包 | 脱离GUI，在Python中直接调用本项目的所有函数插件（开发中）
-⭐虚空终端插件 | [函数插件] 用自然语言，直接调度本项目其他插件
 更多新功能展示 (图像生成等) …… | 见本文档结尾处 ……
 </div>
 
 
 - 新界面（修改`config.py`中的LAYOUT选项即可实现“左右布局”和“上下布局”的切换）
 <div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/230361456-61078362-a966-4eb5-b49e-3c62ef18b860.gif" width="700" >
+<img src="https://user-images.githubusercontent.com/96192199/279702205-d81137c3-affd-4cd1-bb5e-b15610389762.gif" width="700" >
+</div>
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/70ff1ec5-e589-4561-a29e-b831079b37fb.gif" width="700" >
 </div>
 
 
-- 所有按钮都通过读取functional.py动态生成，可随意加自定义功能，解放粘贴板
+- 所有按钮都通过读取functional.py动态生成，可随意加自定义功能，解放剪贴板
 <div align="center">
 <img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
 </div>
@@ -75,68 +102,99 @@ Latex论文一键校对 | [函数插件] 仿Grammarly对Latex文章进行语法
 <img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
 </div>
 
-- 如果输出包含公式，会同时以tex形式和渲染形式显示，方便复制和阅读
+- 如果输出包含公式，会以tex形式和渲染形式同时显示，方便复制和阅读
 <div align="center">
 <img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
 </div>
 
-- 懒得看项目代码？整个工程直接给chatgpt炫嘴里
+- 懒得看项目代码？直接把整个工程炫ChatGPT嘴里
 <div align="center">
 <img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
 </div>
 
-- 多种大语言模型混合调用（ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4）
+- 多种大语言模型混合调用（ChatGLM + OpenAI-GPT3.5 + GPT4）
 <div align="center">
 <img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
 </div>
 
-# Installation
-### 安装方法I：直接运行 (Windows, Linux or MacOS) 
+<br><br>
 
-1. 下载项目
-```sh
-git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
-cd gpt_academic
+# Installation
+
+```mermaid
+flowchart TD
+    A{"安装方法"} --> W1("I. 🔑直接运行 (Windows, Linux or MacOS)")
+    W1 --> W11["1. Python pip包管理依赖"]
+    W1 --> W12["2. Anaconda包管理依赖（推荐⭐）"]
+
+    A --> W2["II. 🐳使用Docker (Windows, Linux or MacOS)"]
+
+    W2 --> k1["1. 部署项目全部能力的大镜像（推荐⭐）"]
+    W2 --> k2["2. 仅在线模型（GPT, GLM4等）镜像"]
+    W2 --> k3["3. 在线模型 + Latex的大镜像"]
+
+    A --> W4["IV. 🚀其他部署方法"]
+    W4 --> C1["1. Windows/MacOS 一键安装运行脚本（推荐⭐）"]
+    W4 --> C2["2. Huggingface, Sealos远程部署"]
+    W4 --> C4["3. ... 其他 ..."]
 ```
 
-2. 配置API_KEY
+### 安装方法I：直接运行 (Windows, Linux or MacOS)
 
-在`config.py`中，配置API KEY等设置，[点击查看特殊网络环境设置方法](https://github.com/binary-husky/gpt_academic/issues/1) 。[Wiki页面](https://github.com/binary-husky/gpt_academic/wiki/%E9%A1%B9%E7%9B%AE%E9%85%8D%E7%BD%AE%E8%AF%B4%E6%98%8E)。
+1. 下载项目
 
-「 程序会优先检查是否存在名为`config_private.py`的私密配置文件，并用其中的配置覆盖`config.py`的同名配置。如您能理解该读取逻辑，我们强烈建议您在`config.py`旁边创建一个名为`config_private.py`的新配置文件，并把`config.py`中的配置转移（复制）到`config_private.py`中（仅复制您修改过的配置条目即可）。 」
+    ```sh
+    git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+    cd gpt_academic
+    ```
 
-「 支持通过`环境变量`配置项目，环境变量的书写格式参考`docker-compose.yml`文件或者我们的[Wiki页面](https://github.com/binary-husky/gpt_academic/wiki/%E9%A1%B9%E7%9B%AE%E9%85%8D%E7%BD%AE%E8%AF%B4%E6%98%8E)。配置读取优先级: `环境变量` > `config_private.py` > `config.py`。 」
+2. 配置API_KEY等变量
+
+    在`config.py`中，配置API KEY等变量。[特殊网络环境设置方法](https://github.com/binary-husky/gpt_academic/issues/1)、[Wiki-项目配置说明](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。
+
+    「 程序会优先检查是否存在名为`config_private.py`的私密配置文件，并用其中的配置覆盖`config.py`的同名配置。如您能理解以上读取逻辑，我们强烈建议您在`config.py`同路径下创建一个名为`config_private.py`的新配置文件，并使用`config_private.py`配置项目，从而确保自动更新时不会丢失配置 」。
+
+    「 支持通过`环境变量`配置项目，环境变量的书写格式参考`docker-compose.yml`文件或者我们的[Wiki页面](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。配置读取优先级: `环境变量` > `config_private.py` > `config.py` 」。
 
 
 3. 安装依赖
-```sh
-# （选择I: 如熟悉python）（python版本3.9以上，越新越好），备注：使用官方pip源或者阿里pip源,临时换源方法：python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
-python -m pip install -r requirements.txt
+    ```sh
+    # （选择I: 如熟悉python, python推荐版本 3.9 ~ 3.11）备注：使用官方pip源或者阿里pip源, 临时换源方法：python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+    python -m pip install -r requirements.txt
 
-# （选择II: 使用Anaconda）步骤也是类似的 (https://www.bilibili.com/video/BV1rc411W7Dr)：
-conda create -n gptac_venv python=3.11    # 创建anaconda环境
-conda activate gptac_venv                 # 激活anaconda环境
-python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤
-```
+    # （选择II: 使用Anaconda）步骤也是类似的 (https://www.bilibili.com/video/BV1rc411W7Dr)：
+    conda create -n gptac_venv python=3.11    # 创建anaconda环境
+    conda activate gptac_venv                 # 激活anaconda环境
+    python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤
+    ```
 
 
 <details><summary>如果需要支持清华ChatGLM2/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
 <p>
 
-【可选步骤】如果需要支持清华ChatGLM2/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
+【可选步骤】如果需要支持清华ChatGLM3/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
+
 ```sh
-# 【可选步骤I】支持清华ChatGLM2。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
-python -m pip install -r request_llm/requirements_chatglm.txt  
+# 【可选步骤I】支持清华ChatGLM3。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+python -m pip install -r request_llms/requirements_chatglm.txt
 
 # 【可选步骤II】支持复旦MOSS
-python -m pip install -r request_llm/requirements_moss.txt
-git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 注意执行此行代码时，必须处于项目根路径
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # 注意执行此行代码时，必须处于项目根路径
 
 # 【可选步骤III】支持RWKV Runner
 参考wiki：https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
 
 # 【可选步骤IV】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+
+# 【可选步骤V】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
+pip install bitsandbyte
+# windows用户安装bitsandbytes需要使用下面bitsandbytes-windows-webui
+python -m pip install bitsandbytes --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui
+pip install -U git+https://github.com/huggingface/transformers.git
+pip install -U git+https://github.com/huggingface/accelerate.git
+pip install peft
 ```
 
 </p>
@@ -145,101 +203,85 @@ AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-
 
 
 4. 运行
-```sh
-python main.py
-```
+    ```sh
+    python main.py
+    ```
 
 ### 安装方法II：使用Docker
 
-0. 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个，建议使用方案1）（需要熟悉[Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian)运行时）
-[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+0. 部署项目的全部能力（这个是包含cuda和latex的大型镜像。但如果您网速慢、硬盘小，则不推荐该方法部署完整项目）
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
 
-``` sh
-# 修改docker-compose.yml，保留方案0并删除其他方案。修改docker-compose.yml中方案0的配置，参考其中注释即可
-docker-compose up
-```
+    ``` sh
+    # 修改docker-compose.yml，保留方案0并删除其他方案。然后运行：
+    docker-compose up
+    ```
 
-1. 仅ChatGPT+文心一言+spark等在线模型（推荐大多数人选择）
+1. 仅ChatGPT + GLM4 + 文心一言+spark等在线模型（推荐大多数人选择）
 [![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
 [![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
 [![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
 
-``` sh
-# 修改docker-compose.yml，保留方案1并删除其他方案。修改docker-compose.yml中方案1的配置，参考其中注释即可
-docker-compose up
-```
+    ``` sh
+    # 修改docker-compose.yml，保留方案1并删除其他方案。然后运行：
+    docker-compose up
+    ```
 
 P.S. 如果需要依赖Latex的插件功能，请见Wiki。另外，您也可以直接使用方案4或者方案0获取Latex功能。
 
-2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + 通义千问（需要熟悉[Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian)运行时）
+2. ChatGPT + GLM3 + MOSS + LLAMA2 + 通义千问（需要熟悉[Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian)运行时）
 [![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
 
-``` sh
-# 修改docker-compose.yml，保留方案2并删除其他方案。修改docker-compose.yml中方案2的配置，参考其中注释即可
-docker-compose up
-```
-
-3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉[Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian)运行时）
-[![jittorllms](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-jittorllms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-jittorllms.yml)
-
-``` sh
-# 修改docker-compose.yml，保留方案3并删除其他方案。修改docker-compose.yml中方案3的配置，参考其中注释即可
-docker-compose up
-```
+    ``` sh
+    # 修改docker-compose.yml，保留方案2并删除其他方案。然后运行：
+    docker-compose up
+    ```
 
 
-### 安装方法III：其他部署姿势
-1. 一键运行脚本。
-完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。
-脚本的贡献来源是[oobabooga](https://github.com/oobabooga/one-click-installers)。
+### 安装方法III：其他部署方法
+1. **Windows一键运行脚本**。
+完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。脚本贡献来源：[oobabooga](https://github.com/oobabooga/one-click-installers)。
 
-2. 使用docker-compose运行。
-请阅读docker-compose.yml后，按照其中的提示操作即可
+2. 使用第三方API、Azure等、文心一言、星火等，见[Wiki页面](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)
 
-3. 如何使用反代URL
-按照`config.py`中的说明配置API_URL_REDIRECT即可。
+3. 云服务器远程部署避坑指南。
+请访问[云服务器远程部署wiki](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
 
-4. 微软云AzureAPI
-按照`config.py`中的说明配置即可（AZURE_ENDPOINT等四个配置）
-
-5. 远程云服务器部署（需要云服务器知识与经验）。
-请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
-
-6. 使用Sealos[一键部署](https://github.com/binary-husky/gpt_academic/issues/993)。
-
-7. 使用WSL2（Windows Subsystem for Linux 子系统）。
-请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
-
-8. 如何在二级网址（如`http://localhost/subpath`）下运行。
-请访问[FastAPI运行说明](docs/WithFastapi.md)
+4. 在其他平台部署&二级网址部署
+    - 使用Sealos[一键部署](https://github.com/binary-husky/gpt_academic/issues/993)。
+    - 使用WSL2（Windows Subsystem for Linux 子系统）。请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
+    - 如何在二级网址（如`http://localhost/subpath`）下运行。请访问[FastAPI运行说明](docs/WithFastapi.md)
 
+<br><br>
 
 # Advanced Usage
 ### I：自定义新的便捷按钮（学术快捷键）
-任意文本编辑器打开`core_functional.py`，添加条目如下，然后重启程序即可。（如果按钮已经添加成功并可见，那么前缀、后缀都支持热修改，无需重启程序即可生效。）
-例如
-```
+
+现在已可以通过UI中的`界面外观`菜单中的`自定义菜单`添加新的便捷按钮。如果需要在代码中定义，请使用任意文本编辑器打开`core_functional.py`，添加如下条目即可：
+
+```python
 "超级英译中": {
     # 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
-    "Prefix": "请翻译把下面一段内容成中文，然后用一个markdown表格逐一解释文中出现的专有名词：\n\n", 
-    
+    "Prefix": "请翻译把下面一段内容成中文，然后用一个markdown表格逐一解释文中出现的专有名词：\n\n",
+
     # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来。
     "Suffix": "",
 },
 ```
+
 <div align="center">
 <img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
 </div>
 
 ### II：自定义函数插件
-
 编写强大的函数插件来执行任何你想得到的和想不到的任务。
 本项目的插件编写、调试难度很低，只要您具备一定的python基础知识，就可以仿照我们提供的模板实现自己的插件功能。
 详情请参考[函数插件指南](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)。
 
+<br><br>
 
-# Latest Update
-### I：新功能动态
+# Updates
+### I：动态
 
 1. 对话保存功能。在函数插件区调用 `保存当前的对话` 即可将当前对话保存为可读+可复原的html文件，
 另外在函数插件区（下拉菜单）调用 `载入对话历史存档` ，即可还原之前的会话。
@@ -280,28 +322,23 @@ Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史h
 <img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
 </div>
 
-7. 新增MOSS大语言模型支持
-<div align="center">
-<img src="https://user-images.githubusercontent.com/96192199/236639178-92836f37-13af-4fdd-984d-b4450fe30336.png" width="500" >
-</div>
-
-8. OpenAI图像生成
+7. OpenAI图像生成
 <div align="center">
 <img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
 </div>
 
-9. OpenAI音频解析与总结
+8. 基于mermaid的流图、脑图绘制
 <div align="center">
-<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/c518b82f-bd53-46e2-baf5-ad1b081c1da4" width="500" >
 </div>
 
-10. Latex全文校对纠错
+9. Latex全文校对纠错
 <div align="center">
 <img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
 <img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
 </div>
 
-11. 语言、主题切换
+10. 语言、主题切换
 <div align="center">
 <img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
 </div>
@@ -309,7 +346,13 @@ Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史h
 
 
 ### II：版本:
-- version 3.60（todo）: 优化虚空终端，引入code interpreter和更多插件
+- version 3.80(TODO): 优化AutoGen插件主题并设计一系列衍生插件
+- version 3.70: 引入Mermaid绘图，实现GPT画脑图等功能   
+- version 3.60: 引入AutoGen作为新一代插件的基石
+- version 3.57: 支持GLM3，星火v3，文心一言v4，修复本地模型的并发BUG
+- version 3.56: 支持动态追加基础功能按钮，新汇报PDF汇总页面
+- version 3.55: 重构前端界面，引入悬浮窗口与菜单栏
+- version 3.54: 新增动态代码解释器（Code Interpreter）（待完善）
 - version 3.53: 支持动态选择不同界面主题，提高稳定性&解决多用户冲突问题
 - version 3.50: 使用自然语言调用本项目的所有函数插件（虚空终端），支持插件分类，改进UI，设计新主题
 - version 3.49: 支持百度千帆平台和文心一言
@@ -324,25 +367,58 @@ Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史h
 - version 3.0: 对chatglm和其他小型llm的支持
 - version 2.6: 重构了插件结构，提高了交互性，加入更多插件
 - version 2.5: 自更新，解决总结大工程源代码时文本过长、token溢出的问题
-- version 2.4: (1)新增PDF全文翻译功能; (2)新增输入区切换位置的功能; (3)新增垂直布局选项; (4)多线程函数插件优化。
+- version 2.4: 新增PDF全文翻译功能; 新增输入区切换位置的功能
 - version 2.3: 增强多线程交互性
 - version 2.2: 函数插件支持热重载
 - version 2.1: 可折叠式布局
 - version 2.0: 引入模块化函数插件
 - version 1.0: 基础功能
 
-gpt_academic开发者QQ群-2：610599535
+GPT Academic开发者QQ群：`610599535`
 
 - 已知问题
     - 某些浏览器翻译插件干扰此软件前端的运行
-    - 官方Gradio目前有很多兼容性Bug，请务必使用`requirement.txt`安装Gradio
+    - 官方Gradio目前有很多兼容性问题，请**务必使用`requirement.txt`安装Gradio**
+
+```mermaid
+timeline LR
+    title GPT-Academic项目发展历程
+    section 2.x
+        1.0~2.2: 基础功能: 引入模块化函数插件: 可折叠式布局: 函数插件支持热重载
+        2.3~2.5: 增强多线程交互性: 新增PDF全文翻译功能: 新增输入区切换位置的功能: 自更新
+        2.6: 重构了插件结构: 提高了交互性: 加入更多插件
+    section 3.x
+        3.0~3.1: 对chatglm支持: 对其他小型llm支持: 支持同时问询多个gpt模型: 支持多个apikey负载均衡
+        3.2~3.3: 函数插件支持更多参数接口: 保存对话功能: 解读任意语言代码: 同时询问任意的LLM组合: 互联网信息综合功能
+        3.4: 加入arxiv论文翻译: 加入latex论文批改功能
+        3.44: 正式支持Azure: 优化界面易用性
+        3.46: 自定义ChatGLM2微调模型: 实时语音对话
+        3.49: 支持阿里达摩院通义千问: 上海AI-Lab书生: 讯飞星火: 支持百度千帆平台 & 文心一言
+        3.50: 虚空终端: 支持插件分类: 改进UI: 设计新主题
+        3.53: 动态选择不同界面主题: 提高稳定性: 解决多用户冲突问题
+        3.55: 动态代码解释器: 重构前端界面: 引入悬浮窗口与菜单栏
+        3.56: 动态追加基础功能按钮: 新汇报PDF汇总页面
+        3.57: GLM3, 星火v3: 支持文心一言v4: 修复本地模型的并发BUG
+        3.60: 引入AutoGen
+        3.70: 引入Mermaid绘图: 实现GPT画脑图等功能
+        3.80(TODO): 优化AutoGen插件主题: 设计衍生插件
+
+```
+
 
 ### III：主题
 可以通过修改`THEME`选项（config.py）变更主题
 1. `Chuanhu-Small-and-Beautiful` [网址](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
 
 
-### IV：参考与学习
+### IV：本项目的开发分支
+
+1. `master` 分支: 主分支，稳定版
+2. `frontier` 分支: 开发分支，测试版
+3. 如何[接入其他大模型](request_llms/README.md)
+4. 访问GPT-Academic的[在线服务并支持我们](https://github.com/binary-husky/gpt_academic/wiki/online)
+
+### V：参考与学习
 
 ```
 代码中参考了很多其他优秀项目中的设计，顺序不分先后：

check_proxy.py

@@ -5,7 +5,6 @@ def check_proxy(proxies):
     try:
         response = requests.get("https://ipapi.co/json/", proxies=proxies, timeout=4)
         data = response.json()
-        # print(f'查询代理的地理位置，返回的结果是{data}')
         if 'country_name' in data:
             country = data['country_name']
             result = f"代理配置 {proxies_https}, 代理所在地：{country}"
@@ -46,9 +45,9 @@ def backup_and_download(current_version, remote_version):
         return new_version_dir
     os.makedirs(new_version_dir)
     shutil.copytree('./', backup_dir, ignore=lambda x, y: ['history'])
-    proxies, = get_conf('proxies')
-    r = requests.get(
-        'https://github.com/binary-husky/chatgpt_academic/archive/refs/heads/master.zip', proxies=proxies, stream=True)
+    proxies = get_conf('proxies')
+    try:    r = requests.get('https://github.com/binary-husky/chatgpt_academic/archive/refs/heads/master.zip', proxies=proxies, stream=True)
+    except: r = requests.get('https://public.agent-matrix.com/publish/master.zip', proxies=proxies, stream=True)
     zip_file_path = backup_dir+'/master.zip'
     with open(zip_file_path, 'wb+') as f:
         f.write(r.content)
@@ -82,7 +81,7 @@ def patch_and_restart(path):
     dir_util.copy_tree(path_new_version, './')
     print亮绿('代码已经更新，即将更新pip包依赖……')
     for i in reversed(range(5)): time.sleep(1); print(i)
-    try: 
+    try:
         import subprocess
         subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
     except:
@@ -111,11 +110,10 @@ def auto_update(raise_error=False):
     try:
         from toolbox import get_conf
         import requests
-        import time
         import json
-        proxies, = get_conf('proxies')
-        response = requests.get(
-            "https://raw.githubusercontent.com/binary-husky/chatgpt_academic/master/version", proxies=proxies, timeout=5)
+        proxies = get_conf('proxies')
+        try:    response = requests.get("https://raw.githubusercontent.com/binary-husky/chatgpt_academic/master/version", proxies=proxies, timeout=5)
+        except: response = requests.get("https://public.agent-matrix.com/publish/version", proxies=proxies, timeout=5)
         remote_json_data = json.loads(response.text)
         remote_version = remote_json_data['version']
         if remote_json_data["show_feature"]:
@@ -127,8 +125,7 @@ def auto_update(raise_error=False):
             current_version = json.loads(current_version)['version']
         if (remote_version - current_version) >= 0.01-1e-5:
             from colorful import print亮黄
-            print亮黄(
-                f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
+            print亮黄(f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
             print('（1）Github更新地址:\nhttps://github.com/binary-husky/chatgpt_academic\n')
             user_instruction = input('（2）是否一键更新代码（Y+回车=确认，输入其他/无输入+回车=不更新）？')
             if user_instruction in ['Y', 'y']:
@@ -154,16 +151,26 @@ def auto_update(raise_error=False):
         print(msg)
 
 def warm_up_modules():
-    print('正在执行一些模块的预热...')
-    from request_llm.bridge_all import model_info
-    enc = model_info["gpt-3.5-turbo"]['tokenizer']
-    enc.encode("模块预热", disallowed_special=())
-    enc = model_info["gpt-4"]['tokenizer']
-    enc.encode("模块预热", disallowed_special=())
+    print('正在执行一些模块的预热 ...')
+    from toolbox import ProxyNetworkActivate
+    from request_llms.bridge_all import model_info
+    with ProxyNetworkActivate("Warmup_Modules"):
+        enc = model_info["gpt-3.5-turbo"]['tokenizer']
+        enc.encode("模块预热", disallowed_special=())
+        enc = model_info["gpt-4"]['tokenizer']
+        enc.encode("模块预热", disallowed_special=())
+
+def warm_up_vectordb():
+    print('正在执行一些模块的预热 ...')
+    from toolbox import ProxyNetworkActivate
+    with ProxyNetworkActivate("Warmup_Modules"):
+        import nltk
+        with ProxyNetworkActivate("Warmup_Modules"): nltk.download("punkt")
+
 
 if __name__ == '__main__':
     import os
     os.environ['no_proxy'] = '*'  # 避免代理网络产生意外污染
     from toolbox import get_conf
-    proxies, = get_conf('proxies')
+    proxies = get_conf('proxies')
     check_proxy(proxies)

colorful.py

@@ -3,7 +3,7 @@ from sys import stdout
 
 if platform.system()=="Linux":
     pass
-else: 
+else:
     from colorama import init
     init()
 

config.py

@@ -2,8 +2,8 @@
     以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
     读取优先级：环境变量 > config_private.py > config.py
     --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
-    All the following configurations also support using environment variables to override, 
-    and the environment variable configuration format can be seen in docker-compose.yml. 
+    All the following configurations also support using environment variables to override,
+    and the environment variable configuration format can be seen in docker-compose.yml.
     Configuration reading priority: environment variable > config_private.py > config.py
 """
 
@@ -15,13 +15,13 @@ API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗
 USE_PROXY = False
 if USE_PROXY:
     """
+    代理网络的地址，打开你的代理软件查看代理协议(socks5h / http)、地址(localhost)和端口(11284)
     填写格式是 [协议]://  [地址] :[端口]，填写之前不要忘记把USE_PROXY改成True，如果直接在海外服务器部署，此处不修改
             <配置教程&视频教程> https://github.com/binary-husky/gpt_academic/issues/1>
     [协议] 常见协议无非socks5h/http; 例如 v2**y 和 ss* 的默认本地协议是socks5h; 而cl**h 的默认本地协议是http
-    [地址] 懂的都懂，不懂就填localhost或者127.0.0.1肯定错不了（localhost意思是代理软件安装在本机上）
+    [地址] 填localhost或者127.0.0.1（localhost意思是代理软件安装在本机上）
     [端口] 在代理软件的设置里找。虽然不同的代理软件界面不一样，但端口号都应该在最显眼的位置上
     """
-    # 代理网络的地址，打开你的*学*网软件查看代理的协议(socks5h / http)、地址(localhost)和端口(11284)
     proxies = {
         #          [协议]://  [地址]  :[端口]
         "http":  "socks5h://localhost:11284",  # 再例如  "http":  "http://127.0.0.1:7890",
@@ -30,11 +30,37 @@ if USE_PROXY:
 else:
     proxies = None
 
-# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
+# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
+LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
+AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
+                    "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
+                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
+                    "gemini-pro", "chatglm3"
+                    ]
+# --- --- --- ---
+# P.S. 其他可用的模型还包括
+# AVAIL_LLM_MODELS = [
+#   "qianfan", "deepseekcoder",
+#   "spark", "sparkv2", "sparkv3", "sparkv3.5",
+#   "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
+#   "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
+#   "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125"
+#   "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
+#   "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
+#   "yi-34b-chat-0205", "yi-34b-chat-200k"
+# ]
+# --- --- --- ---
+# 此外，您还可以在接入one-api/vllm/ollama时，
+# 使用"one-api-*","vllm-*","ollama-*"前缀直接使用非标准方式接入的模型，例如
+# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)"]
+# --- --- --- ---
+
+
+# --------------- 以下配置可以优化体验 ---------------
 
 # 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
-# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"} 
-# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
+# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
+# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
 API_URL_REDIRECT = {}
 
 
@@ -48,6 +74,11 @@ DEFAULT_WORKER_NUM = 3
 THEME = "Default"
 AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
 
+
+# 默认的系统提示词（system prompt）
+INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
+
+
 # 对话窗的高度 （仅在LAYOUT="TOP-DOWN"时生效）
 CHATBOT_HEIGHT = 1115
 
@@ -58,7 +89,10 @@ CODE_HIGHLIGHT = True
 
 # 窗口布局
 LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
-DARK_MODE = True        # 暗色模式 / 亮色模式
+
+
+# 暗色模式 / 亮色模式
+DARK_MODE = True
 
 
 # 发送请求到OpenAI后，等待多久判定为超时
@@ -77,18 +111,24 @@ MAX_RETRY = 2
 DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
 
 
-# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
-LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "api2d-gpt-3.5-turbo", 
-                    "gpt-4", "gpt-4-32k", "azure-gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "stack-claude"]
-# P.S. 其他可用的模型还包括 ["qianfan", "llama2", "qwen", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", 
-# "spark", "sparkv2", "chatglm_onnx", "claude-1-100k", "claude-2", "internlm", "jittorllms_pangualpha", "jittorllms_llama"]
+# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
+MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
+
+
+# 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
+# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
+# 也可以是具体的模型路径
+QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
+
+
+# 接入通义千问在线大模型 https://dashscope.console.aliyun.com/
+DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
 
 
 # 百度千帆（LLM_MODEL="qianfan"）
 BAIDU_CLOUD_API_KEY = ''
 BAIDU_CLOUD_SECRET_KEY = ''
-BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat"
+BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot'    # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat"
 
 
 # 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
@@ -117,33 +157,37 @@ ADD_WAIFU = False
 AUTHENTICATION = []
 
 
-# 如果需要在二级路径下运行（常规情况下，不要修改!!）（需要配合修改main.py才能生效!）
+# 如果需要在二级路径下运行（常规情况下，不要修改!!）
+# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
 CUSTOM_PATH = "/"
 
 
+# HTTPS 秘钥和证书（不需要修改）
+SSL_KEYFILE = ""
+SSL_CERTFILE = ""
+
+
 # 极少数情况下，openai的官方KEY需要伴随组织编码（格式如org-xxxxxxxxxxxxxxxxxxxxxxxx）使用
 API_ORG = ""
 
 
-# 如果需要使用Slack Claude，使用教程详情见 request_llm/README.md
-SLACK_CLAUDE_BOT_ID = ''   
+# 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
+SLACK_CLAUDE_BOT_ID = ''
 SLACK_CLAUDE_USER_TOKEN = ''
 
 
-# 如果需要使用AZURE 详情请见额外文档 docs\use_azure.md
+# 如果需要使用AZURE（方法一：单个azure模型部署）详情请见额外文档 docs\use_azure.md
 AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/"
 AZURE_API_KEY = "填入azure openai api的密钥"    # 建议直接在API_KEY处填写，该选项即将被弃用
 AZURE_ENGINE = "填入你亲手写的部署名"            # 读 docs\use_azure.md
 
 
-# 使用Newbing
-NEWBING_STYLE = "creative"  # ["creative", "balanced", "precise"]
-NEWBING_COOKIES = """
-put your new bing cookies here
-"""
+# 如果需要使用AZURE（方法二：多个azure模型部署+动态切换）详情请见额外文档 docs\use_azure.md
+AZURE_CFG_ARRAY = {}
 
 
-# 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
+# 阿里云实时语音识别 配置难度较高
+# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
 ENABLE_AUDIO = False
 ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
 ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
@@ -151,20 +195,52 @@ ALIYUN_ACCESSKEY="" # （无需填写）
 ALIYUN_SECRET=""    # （无需填写）
 
 
+# GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
+TTS_TYPE = "DISABLE" # LOCAL / LOCAL_SOVITS_API / DISABLE
+GPT_SOVITS_URL = ""
+EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
+
+
 # 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
 XFYUN_APPID = "00000000"
 XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
 XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
 
 
+# 接入智谱大模型
+ZHIPUAI_API_KEY = ""
+ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
+
+
 # Claude API KEY
 ANTHROPIC_API_KEY = ""
 
 
+# 月之暗面 API KEY
+MOONSHOT_API_KEY = ""
+
+
+# 零一万物(Yi Model) API KEY
+YIMODEL_API_KEY = ""
+
+
+# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
+MATHPIX_APPID = ""
+MATHPIX_APPKEY = ""
+
+
+# DOC2X的PDF解析服务，注册账号并获取API KEY: https://doc2x.noedgeai.com/login
+DOC2X_API_KEY = ""
+
+
 # 自定义API KEY格式
 CUSTOM_API_KEY_PATTERN = ""
 
 
+# Google Gemini API-Key
+GEMINI_API_KEY = ''
+
+
 # HUGGINGFACE的TOKEN，下载LLAMA时起作用 https://huggingface.co/docs/hub/security-tokens
 HUGGINGFACE_ACCESS_TOKEN = "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"
 
@@ -173,21 +249,48 @@ HUGGINGFACE_ACCESS_TOKEN = "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"
 # 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
 GROBID_URLS = [
     "https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
-    "https://shaocongma-grobid.hf.space","https://FBR123-grobid.hf.space", "https://yeku-grobid.hf.space", 
+    "https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
+    "https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
 ]
 
 
 # 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
 ALLOW_RESET_CONFIG = False
+
+
+# 在使用AutoGen插件时，是否使用Docker容器运行代码
+AUTOGEN_USE_DOCKER = False
+
+
 # 临时的上传文件夹位置，请勿修改
 PATH_PRIVATE_UPLOAD = "private_upload"
+
+
 # 日志文件夹的位置，请勿修改
 PATH_LOGGING = "gpt_log"
+
+
 # 除了连接OpenAI之外，还有哪些场合允许使用代理，请勿修改
-WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid"]
+WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
+                     "Warmup_Modules", "Nougat_Download", "AutoGen"]
+
+
+# *实验性功能*: 自动检测并屏蔽失效的KEY，请勿使用
+BLOCK_INVALID_APIKEY = False
+
+
+# 启用插件热加载
+PLUGIN_HOT_RELOAD = False
+
+
+# 自定义按钮的最大数量限制
+NUM_CUSTOM_BASIC_BTN = 4
+
 
 
 """
+--------------- 配置关联关系说明 ---------------
+
 在线大模型配置关联关系示意图
 │
 ├── "gpt-3.5-turbo" 等openai模型
@@ -196,19 +299,22 @@ WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid"]
 │   ├── API_ORG（不常用）
 │   └── API_URL_REDIRECT（不常用）
 │
-├── "azure-gpt-3.5" 等azure模型
+├── "azure-gpt-3.5" 等azure模型（单个azure模型，不需要动态切换）
 │   ├── API_KEY
 │   ├── AZURE_ENDPOINT
 │   ├── AZURE_API_KEY
 │   ├── AZURE_ENGINE
 │   └── API_URL_REDIRECT
 │
+├── "azure-gpt-3.5" 等azure模型（多个azure模型，需要动态切换，高优先级）
+│   └── AZURE_CFG_ARRAY
+│
 ├── "spark" 星火认知大模型 spark & sparkv2
 │   ├── XFYUN_APPID
 │   ├── XFYUN_API_SECRET
 │   └── XFYUN_API_KEY
 │
-├── "claude-1-100k" 等claude模型
+├── "claude-3-opus-20240229" 等claude模型
 │   └── ANTHROPIC_API_KEY
 │
 ├── "stack-claude"
@@ -220,11 +326,40 @@ WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid"]
 │   ├── BAIDU_CLOUD_API_KEY
 │   └── BAIDU_CLOUD_SECRET_KEY
 │
-├── "newbing" Newbing接口不再稳定，不推荐使用
-    ├── NEWBING_STYLE
-    └── NEWBING_COOKIES
+├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
+│   └── ZHIPUAI_API_KEY
+│
+├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
+│   └── YIMODEL_API_KEY
+│
+├── "qwen-turbo" 等通义千问大模型
+│   └──  DASHSCOPE_API_KEY
+│
+├── "Gemini"
+│   └──  GEMINI_API_KEY
+│
+└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
+    ├── AVAIL_LLM_MODELS
+    ├── API_KEY
+    └── API_URL_REDIRECT
+
+
+本地大模型示意图
+│
+├── "chatglm3"
+├── "chatglm"
+├── "chatglm_onnx"
+├── "chatglmft"
+├── "internlm"
+├── "moss"
+├── "jittorllms_pangualpha"
+├── "jittorllms_llama"
+├── "deepseekcoder"
+├── "qwen-local"
+├──  RWKV的支持见Wiki
+└── "llama2"
+
 
-    
 用户图形界面布局依赖关系示意图
 │
 ├── CHATBOT_HEIGHT 对话窗的高度
@@ -235,7 +370,7 @@ WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid"]
 ├── THEME 色彩主题
 ├── AUTO_CLEAR_TXT 是否在提交时自动清空输入框
 ├── ADD_WAIFU 加一个live2d装饰
-├── ALLOW_RESET_CONFIG 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性
+└── ALLOW_RESET_CONFIG 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性
 
 
 插件在线服务配置依赖关系示意图
@@ -247,7 +382,10 @@ WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid"]
 │   ├── ALIYUN_ACCESSKEY
 │   └── ALIYUN_SECRET
 │
-├── PDF文档精准解析
-│   └── GROBID_URLS
+└── PDF文档精准解析
+    ├── GROBID_URLS
+    ├── MATHPIX_APPID
+    └── MATHPIX_APPKEY
+
 
 """

core_functional.py

@@ -3,30 +3,69 @@
 # 'stop' 颜色对应 theme.py 中的 color_er
 import importlib
 from toolbox import clear_line_break
-
+from toolbox import apply_gpt_academic_string_mask_langbased
+from toolbox import build_gpt_academic_masked_string_langbased
+from textwrap import dedent
 
 def get_core_functions():
     return {
-        "英语学术润色": {
-            # 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
-            "Prefix":   r"Below is a paragraph from an academic paper. Polish the writing to meet the academic style, " +
-                        r"improve the spelling, grammar, clarity, concision and overall readability. When necessary, rewrite the whole sentence. " +
-                        r"Firstly, you should provide the polished paragraph. "
-                        r"Secondly, you should list all your modification and explain the reasons to do so in markdown table." + "\n\n",
-            # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
+
+        "学术语料润色": {
+            # [1*] 前缀字符串，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等。
+            #      这里填一个提示词字符串就行了，这里为了区分中英文情景搞复杂了一点
+            "Prefix":   build_gpt_academic_masked_string_langbased(
+                            text_show_english=
+                                r"Below is a paragraph from an academic paper. Polish the writing to meet the academic style, "
+                                r"improve the spelling, grammar, clarity, concision and overall readability. When necessary, rewrite the whole sentence. "
+                                r"Firstly, you should provide the polished paragraph. "
+                                r"Secondly, you should list all your modification and explain the reasons to do so in markdown table.",
+                            text_show_chinese=
+                                r"作为一名中文学术论文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，"
+                                r"同时分解长句，减少重复，并提供改进建议。请先提供文本的更正版本，然后在markdown表格中列出修改的内容，并给出修改的理由:"
+                        ) + "\n\n",
+            # [2*] 后缀字符串，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
             "Suffix":   r"",
-            # 按钮颜色 (默认 secondary)
+            # [3] 按钮颜色 (可选参数，默认 secondary)
             "Color":    r"secondary",
-            # 按钮是否可见 (默认 True，即可见)
+            # [4] 按钮是否可见 (可选参数，默认 True，即可见)
             "Visible": True,
-            # 是否在触发时清除历史 (默认 False，即不处理之前的对话历史)
-            "AutoClearHistory": False
+            # [5] 是否在触发时清除历史 (可选参数，默认 False，即不处理之前的对话历史)
+            "AutoClearHistory": False,
+            # [6] 文本预处理 （可选参数，默认 None，举例：写个函数移除所有的换行符）
+            "PreProcess": None,
         },
-        "中文学术润色": {
-            "Prefix":   r"作为一名中文学术论文写作改进助理，你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性，" +
-                        r"同时分解长句，减少重复，并提供改进建议。请只提供文本的更正版本，避免包括解释。请编辑以下文本" + "\n\n",
-            "Suffix":   r"",
+
+
+        "总结绘制脑图": {
+            # 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
+            "Prefix":   '''"""\n\n''',
+            # 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来
+            "Suffix":
+                # dedent() 函数用于去除多行字符串的缩进
+                dedent("\n\n"+r'''
+                    """
+
+                    使用mermaid flowchart对以上文本进行总结，概括上述段落的内容以及内在逻辑关系，例如：
+
+                    以下是对以上文本的总结，以mermaid flowchart的形式展示：
+                    ```mermaid
+                    flowchart LR
+                        A["节点名1"] --> B("节点名2")
+                        B --> C{"节点名3"}
+                        C --> D["节点名4"]
+                        C --> |"箭头名1"| E["节点名5"]
+                        C --> |"箭头名2"| F["节点名6"]
+                    ```
+
+                    注意：
+                    （1）使用中文
+                    （2）节点名字使用引号包裹，如["Laptop"]
+                    （3）`|` 和 `"`之间不要存在空格
+                    （4）根据情况选择flowchart LR（从左到右）或者flowchart TD（从上到下）
+                '''),
         },
+
+
         "查找语法错误": {
             "Prefix":   r"Help me ensure that the grammar and the spelling is correct. "
                         r"Do not try to polish the text, if no mistake is found, tell me that this paragraph is good. "
@@ -46,42 +85,61 @@ def get_core_functions():
             "Suffix":   r"",
             "PreProcess": clear_line_break,    # 预处理：清除换行符
         },
+
+
         "中译英": {
             "Prefix":   r"Please translate following sentence to English:" + "\n\n",
             "Suffix":   r"",
         },
-        "学术中英互译": {
-            "Prefix":   r"I want you to act as a scientific English-Chinese translator, " +
-                        r"I will provide you with some paragraphs in one language " +
-                        r"and your task is to accurately and academically translate the paragraphs only into the other language. " +
-                        r"Do not repeat the original provided paragraphs after translation. " +
-                        r"You should use artificial intelligence tools, " +
-                        r"such as natural language processing, and rhetorical knowledge " +
-                        r"and experience about effective writing techniques to reply. " +
-                        r"I'll give you my paragraphs as follows, tell me what language it is written in, and then translate:" + "\n\n",
-            "Suffix": "",
-            "Color": "secondary",
+
+
+        "学术英中互译": {
+            "Prefix":   build_gpt_academic_masked_string_langbased(
+                            text_show_chinese=
+                                r"I want you to act as a scientific English-Chinese translator, "
+                                r"I will provide you with some paragraphs in one language "
+                                r"and your task is to accurately and academically translate the paragraphs only into the other language. "
+                                r"Do not repeat the original provided paragraphs after translation. "
+                                r"You should use artificial intelligence tools, "
+                                r"such as natural language processing, and rhetorical knowledge "
+                                r"and experience about effective writing techniques to reply. "
+                                r"I'll give you my paragraphs as follows, tell me what language it is written in, and then translate:",
+                            text_show_english=
+                                r"你是经验丰富的翻译，请把以下学术文章段落翻译成中文，"
+                                r"并同时充分考虑中文的语法、清晰、简洁和整体可读性，"
+                                r"必要时，你可以修改整个句子的顺序以确保翻译后的段落符合中文的语言习惯。"
+                                r"你需要翻译的文本如下："
+                        ) + "\n\n",
+            "Suffix":   r"",
         },
+
+
         "英译中": {
             "Prefix":   r"翻译成地道的中文：" + "\n\n",
             "Suffix":   r"",
-            "Visible": False,
+            "Visible":  False,
         },
+
+
         "找图片": {
-            "Prefix":   r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，" +
+            "Prefix":   r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，"
                         r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
             "Suffix":   r"",
-            "Visible": False,
+            "Visible":  False,
         },
+
+
         "解释代码": {
             "Prefix":   r"请解释以下代码：" + "\n```\n",
             "Suffix":   "\n```\n",
         },
+
+
         "参考文献转Bib": {
-            "Prefix":   r"Here are some bibliography items, please transform them into bibtex style." +
-                        r"Note that, reference styles maybe more than one kind, you should transform each item correctly." +
-                        r"Items need to be transformed:",
-            "Visible": False,
+            "Prefix":   r"Here are some bibliography items, please transform them into bibtex style."
+                        r"Note that, reference styles maybe more than one kind, you should transform each item correctly."
+                        r"Items need to be transformed:" + "\n\n",
+            "Visible":  False,
             "Suffix":   r"",
         }
     }
@@ -91,8 +149,25 @@ def handle_core_functionality(additional_fn, inputs, history, chatbot):
     import core_functional
     importlib.reload(core_functional)    # 热更新prompt
     core_functional = core_functional.get_core_functions()
-    if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
-    inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
-    if core_functional[additional_fn].get("AutoClearHistory", False):
-        history = []
-    return inputs, history
+    addition = chatbot._cookies['customize_fn_overwrite']
+    if additional_fn in addition:
+        # 自定义功能
+        inputs = addition[additional_fn]["Prefix"] + inputs + addition[additional_fn]["Suffix"]
+        return inputs, history
+    else:
+        # 预制功能
+        if "PreProcess" in core_functional[additional_fn]:
+            if core_functional[additional_fn]["PreProcess"] is not None:
+                inputs = core_functional[additional_fn]["PreProcess"](inputs)  # 获取预处理函数（如果有的话）
+        # 为字符串加上上面定义的前缀和后缀。
+        inputs = apply_gpt_academic_string_mask_langbased(
+            string = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"],
+            lang_reference = inputs,
+        )
+        if core_functional[additional_fn].get("AutoClearHistory", False):
+            history = []
+        return inputs, history
+
+if __name__ == "__main__":
+    t = get_core_functions()["总结绘制脑图"]
+    print(t["Prefix"] + t["Suffix"])

crazy_functional.py

@@ -1,4 +1,5 @@
 from toolbox import HotReload  # HotReload 的意思是热更新，修改函数插件后，不需要重启程序，代码直接生效
+from toolbox import trimmed_format_exc
 
 
 def get_crazy_functions():
@@ -26,120 +27,127 @@ def get_crazy_functions():
     from crazy_functions.辅助功能 import 清除缓存
     from crazy_functions.批量Markdown翻译 import Markdown英译中
     from crazy_functions.批量总结PDF文档 import 批量总结PDF文档
-    from crazy_functions.批量翻译PDF文档_多线程 import 批量翻译PDF文档
+    from crazy_functions.PDF批量翻译 import 批量翻译PDF文档
     from crazy_functions.谷歌检索小助手 import 谷歌检索小助手
     from crazy_functions.理解PDF文档内容 import 理解PDF文档内容标准文件输入
     from crazy_functions.Latex全文润色 import Latex中文润色
     from crazy_functions.Latex全文润色 import Latex英文纠错
-    from crazy_functions.Latex全文翻译 import Latex中译英
-    from crazy_functions.Latex全文翻译 import Latex英译中
     from crazy_functions.批量Markdown翻译 import Markdown中译英
     from crazy_functions.虚空终端 import 虚空终端
-
+    from crazy_functions.生成多种Mermaid图表 import 生成多种Mermaid图表
 
     function_plugins = {
         "虚空终端": {
             "Group": "对话|编程|学术|智能体",
             "Color": "stop",
             "AsButton": True,
-            "Function": HotReload(虚空终端)
+            "Function": HotReload(虚空终端),
         },
         "解析整个Python项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": True,
             "Info": "解析一个Python项目的所有源文件(.py) | 输入参数为路径",
-            "Function": HotReload(解析一个Python项目)
+            "Function": HotReload(解析一个Python项目),
         },
         "载入对话历史存档（先上传存档或输入路径）": {
             "Group": "对话",
             "Color": "stop",
             "AsButton": False,
             "Info": "载入对话历史存档 | 输入参数为路径",
-            "Function": HotReload(载入对话历史存档)
+            "Function": HotReload(载入对话历史存档),
         },
         "删除所有本地对话历史记录（谨慎操作）": {
             "Group": "对话",
             "AsButton": False,
             "Info": "删除所有本地对话历史记录，谨慎操作 | 不需要输入参数",
-            "Function": HotReload(删除所有本地对话历史记录)
+            "Function": HotReload(删除所有本地对话历史记录),
         },
         "清除所有缓存文件（谨慎操作）": {
             "Group": "对话",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "清除所有缓存文件，谨慎操作 | 不需要输入参数",
-            "Function": HotReload(清除缓存)
+            "Function": HotReload(清除缓存),
+        },
+        "生成多种Mermaid图表(从当前对话或路径(.pdf/.md/.docx)中生产图表）": {
+            "Group": "对话",
+            "Color": "stop",
+            "AsButton": False,
+            "Info" : "基于当前对话或文件生成多种Mermaid图表,图表类型由模型判断",
+            "Function": HotReload(生成多种Mermaid图表),
+            "AdvancedArgs": True,
+            "ArgsReminder": "请输入图类型对应的数字,不输入则为模型自行判断:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图,9-思维导图",
         },
         "批量总结Word文档": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": True,
             "Info": "批量总结word文档 | 输入参数为路径",
-            "Function": HotReload(总结word文档)
+            "Function": HotReload(总结word文档),
         },
         "解析整个Matlab项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,
             "Info": "解析一个Matlab项目的所有源文件(.m) | 输入参数为路径",
-            "Function": HotReload(解析一个Matlab项目)
+            "Function": HotReload(解析一个Matlab项目),
         },
         "解析整个C++项目头文件": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个C++项目的所有头文件(.h/.hpp) | 输入参数为路径",
-            "Function": HotReload(解析一个C项目的头文件)
+            "Function": HotReload(解析一个C项目的头文件),
         },
         "解析整个C++项目（.cpp/.hpp/.c/.h）": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个C++项目的所有源文件（.cpp/.hpp/.c/.h）| 输入参数为路径",
-            "Function": HotReload(解析一个C项目)
+            "Function": HotReload(解析一个C项目),
         },
         "解析整个Go项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个Go项目的所有源文件 | 输入参数为路径",
-            "Function": HotReload(解析一个Golang项目)
+            "Function": HotReload(解析一个Golang项目),
         },
         "解析整个Rust项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个Rust项目的所有源文件 | 输入参数为路径",
-            "Function": HotReload(解析一个Rust项目)
+            "Function": HotReload(解析一个Rust项目),
         },
         "解析整个Java项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个Java项目的所有源文件 | 输入参数为路径",
-            "Function": HotReload(解析一个Java项目)
+            "Function": HotReload(解析一个Java项目),
         },
         "解析整个前端项目（js,ts,css等）": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个前端项目的所有源文件（js,ts,css等） | 输入参数为路径",
-            "Function": HotReload(解析一个前端项目)
+            "Function": HotReload(解析一个前端项目),
         },
         "解析整个Lua项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个Lua项目的所有源文件 | 输入参数为路径",
-            "Function": HotReload(解析一个Lua项目)
+            "Function": HotReload(解析一个Lua项目),
         },
         "解析整个CSharp项目": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "解析一个CSharp项目的所有源文件 | 输入参数为路径",
-            "Function": HotReload(解析一个CSharp项目)
+            "Function": HotReload(解析一个CSharp项目),
         },
         "解析Jupyter Notebook文件": {
             "Group": "编程",
@@ -155,396 +163,530 @@ def get_crazy_functions():
             "Color": "stop",
             "AsButton": False,
             "Info": "读取Tex论文并写摘要 | 输入参数为路径",
-            "Function": HotReload(读文章写摘要)
+            "Function": HotReload(读文章写摘要),
         },
         "翻译README或MD": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": True,
             "Info": "将Markdown翻译为中文 | 输入参数为路径或URL",
-            "Function": HotReload(Markdown英译中)
+            "Function": HotReload(Markdown英译中),
         },
         "翻译Markdown或README（支持Github链接）": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,
             "Info": "将Markdown或README翻译为中文 | 输入参数为路径或URL",
-            "Function": HotReload(Markdown英译中)
+            "Function": HotReload(Markdown英译中),
         },
         "批量生成函数注释": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "批量生成函数的注释 | 输入参数为路径",
-            "Function": HotReload(批量生成函数注释)
+            "Function": HotReload(批量生成函数注释),
         },
         "保存当前的对话": {
             "Group": "对话",
             "AsButton": True,
             "Info": "保存当前的对话 | 不需要输入参数",
-            "Function": HotReload(对话历史存档)
+            "Function": HotReload(对话历史存档),
         },
         "[多线程Demo]解析此项目本身（源码自译解）": {
             "Group": "对话|编程",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "多线程解析并翻译此项目的源码 | 不需要输入参数",
-            "Function": HotReload(解析项目本身)
+            "Function": HotReload(解析项目本身),
         },
-        "[插件demo]历史上的今天": {
+        "历史上的今天": {
             "Group": "对话",
             "AsButton": True,
-            "Info": "查看历史上的今天事件 | 不需要输入参数",
-            "Function": HotReload(高阶功能模板函数)
+            "Info": "查看历史上的今天事件 (这是一个面向开发者的插件Demo) | 不需要输入参数",
+            "Function": HotReload(高阶功能模板函数),
         },
         "精准翻译PDF论文": {
             "Group": "学术",
             "Color": "stop",
-            "AsButton": True,  
+            "AsButton": True,
             "Info": "精准翻译PDF论文为中文 | 输入参数为路径",
-            "Function": HotReload(批量翻译PDF文档)
+            "Function": HotReload(批量翻译PDF文档),
         },
         "询问多个GPT模型": {
             "Group": "对话",
             "Color": "stop",
             "AsButton": True,
-            "Function": HotReload(同时问询)
+            "Function": HotReload(同时问询),
         },
         "批量总结PDF文档": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "批量总结PDF文档的内容 | 输入参数为路径",
-            "Function": HotReload(批量总结PDF文档)
+            "Function": HotReload(批量总结PDF文档),
         },
         "谷歌学术检索助手（输入谷歌学术搜索页url）": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "使用谷歌学术检索助手搜索指定URL的结果 | 输入参数为谷歌学术搜索页的URL",
-            "Function": HotReload(谷歌检索小助手)
+            "Function": HotReload(谷歌检索小助手),
         },
         "理解PDF文档内容 （模仿ChatPDF）": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "理解PDF文档的内容并进行回答 | 输入参数为路径",
-            "Function": HotReload(理解PDF文档内容标准文件输入)
+            "Function": HotReload(理解PDF文档内容标准文件输入),
         },
         "英文Latex项目全文润色（输入路径或上传压缩包）": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "对英文Latex项目全文进行润色处理 | 输入参数为路径或上传压缩包",
-            "Function": HotReload(Latex英文润色)
-        },
-        "英文Latex项目全文纠错（输入路径或上传压缩包）": {
-            "Group": "学术",
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Info": "对英文Latex项目全文进行纠错处理 | 输入参数为路径或上传压缩包",
-            "Function": HotReload(Latex英文纠错)
+            "Function": HotReload(Latex英文润色),
         },
+
         "中文Latex项目全文润色（输入路径或上传压缩包）": {
             "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "对中文Latex项目全文进行润色处理 | 输入参数为路径或上传压缩包",
-            "Function": HotReload(Latex中文润色)
-        },
-        "Latex项目全文中译英（输入路径或上传压缩包）": {
-            "Group": "学术",
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Info": "对Latex项目全文进行中译英处理 | 输入参数为路径或上传压缩包",
-            "Function": HotReload(Latex中译英)
-        },
-        "Latex项目全文英译中（输入路径或上传压缩包）": {
-            "Group": "学术",
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Info": "对Latex项目全文进行英译中处理 | 输入参数为路径或上传压缩包",
-            "Function": HotReload(Latex英译中)
+            "Function": HotReload(Latex中文润色),
         },
+        # 已经被新插件取代
+        # "英文Latex项目全文纠错（输入路径或上传压缩包）": {
+        #     "Group": "学术",
+        #     "Color": "stop",
+        #     "AsButton": False,  # 加入下拉菜单中
+        #     "Info": "对英文Latex项目全文进行纠错处理 | 输入参数为路径或上传压缩包",
+        #     "Function": HotReload(Latex英文纠错),
+        # },
+        # 已经被新插件取代
+        # "Latex项目全文中译英（输入路径或上传压缩包）": {
+        #     "Group": "学术",
+        #     "Color": "stop",
+        #     "AsButton": False,  # 加入下拉菜单中
+        #     "Info": "对Latex项目全文进行中译英处理 | 输入参数为路径或上传压缩包",
+        #     "Function": HotReload(Latex中译英)
+        # },
+        # 已经被新插件取代
+        # "Latex项目全文英译中（输入路径或上传压缩包）": {
+        #     "Group": "学术",
+        #     "Color": "stop",
+        #     "AsButton": False,  # 加入下拉菜单中
+        #     "Info": "对Latex项目全文进行英译中处理 | 输入参数为路径或上传压缩包",
+        #     "Function": HotReload(Latex英译中)
+        # },
         "批量Markdown中译英（输入路径或上传压缩包）": {
             "Group": "编程",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Info": "批量将Markdown文件中文翻译为英文 | 输入参数为路径或上传压缩包",
-            "Function": HotReload(Markdown中译英)
+            "Function": HotReload(Markdown中译英),
         },
     }
 
     # -=--=- 尚未充分测试的实验性插件 & 需要额外依赖的插件 -=--=-
     try:
         from crazy_functions.下载arxiv论文翻译摘要 import 下载arxiv论文并翻译摘要
-        function_plugins.update({
-            "一键下载arxiv论文并翻译摘要（先在input输入编号，如1812.10695）": {
-                "Group": "学术",
-                "Color": "stop",
-                "AsButton": False,  # 加入下拉菜单中
-                # "Info": "下载arxiv论文并翻译摘要 | 输入参数为arxiv编号如1812.10695",
-                "Function": HotReload(下载arxiv论文并翻译摘要)
+
+        function_plugins.update(
+            {
+                "一键下载arxiv论文并翻译摘要（先在input输入编号，如1812.10695）": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,  # 加入下拉菜单中
+                    # "Info": "下载arxiv论文并翻译摘要 | 输入参数为arxiv编号如1812.10695",
+                    "Function": HotReload(下载arxiv论文并翻译摘要),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.联网的ChatGPT import 连接网络回答问题
-        function_plugins.update({
-            "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,  # 加入下拉菜单中
-                # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
-                "Function": HotReload(连接网络回答问题)
+
+        function_plugins.update(
+            {
+                "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,  # 加入下拉菜单中
+                    # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
+                    "Function": HotReload(连接网络回答问题),
+                }
             }
-        })
+        )
         from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
-        function_plugins.update({
-            "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,  # 加入下拉菜单中
-                "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
-                "Function": HotReload(连接bing搜索回答问题)
+
+        function_plugins.update(
+            {
+                "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,  # 加入下拉菜单中
+                    "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
+                    "Function": HotReload(连接bing搜索回答问题),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.解析项目源代码 import 解析任意code项目
-        function_plugins.update({
-            "解析项目源代码（手动指定和筛选源代码文件类型）": {
-                "Group": "编程",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"",  # 高级参数输入区的显示提示
-                "Function": HotReload(解析任意code项目)
-            },
-        })
+
+        function_plugins.update(
+            {
+                "解析项目源代码（手动指定和筛选源代码文件类型）": {
+                    "Group": "编程",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+                    "ArgsReminder": '输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: "*.c, ^*.cpp, config.toml, ^*.toml"',  # 高级参数输入区的显示提示
+                    "Function": HotReload(解析任意code项目),
+                },
+            }
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
-        function_plugins.update({
-            "询问多个GPT模型（手动指定询问哪些模型）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4",  # 高级参数输入区的显示提示
-                "Function": HotReload(同时问询_指定模型)
-            },
-        })
+
+        function_plugins.update(
+            {
+                "询问多个GPT模型（手动指定询问哪些模型）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+                    "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&gpt-4",  # 高级参数输入区的显示提示
+                    "Function": HotReload(同时问询_指定模型),
+                },
+            }
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
-        from crazy_functions.图片生成 import 图片生成
-        function_plugins.update({
-            "图片生成（先切换模型到openai或api2d）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
-                "ArgsReminder": "在这里输入分辨率, 如256x256（默认）",  # 高级参数输入区的显示提示
-                "Info": "图片生成 | 输入参数字符串，提供图像的内容",
-                "Function": HotReload(图片生成)
-            },
-        })
+        from crazy_functions.图片生成 import 图片生成_DALLE2, 图片生成_DALLE3, 图片修改_DALLE2
+
+        function_plugins.update(
+            {
+                "图片生成_DALLE2 （先切换模型到gpt-*）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+                    "ArgsReminder": "在这里输入分辨率, 如1024x1024（默认），支持 256x256, 512x512, 1024x1024",  # 高级参数输入区的显示提示
+                    "Info": "使用DALLE2生成图片 | 输入参数字符串，提供图像的内容",
+                    "Function": HotReload(图片生成_DALLE2),
+                },
+            }
+        )
+        function_plugins.update(
+            {
+                "图片生成_DALLE3 （先切换模型到gpt-*）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+                    "ArgsReminder": "在这里输入自定义参数「分辨率-质量(可选)-风格(可选)」, 参数示例「1024x1024-hd-vivid」 || 分辨率支持 「1024x1024」(默认) /「1792x1024」/「1024x1792」 || 质量支持 「-standard」(默认) /「-hd」 || 风格支持 「-vivid」(默认) /「-natural」",  # 高级参数输入区的显示提示
+                    "Info": "使用DALLE3生成图片 | 输入参数字符串，提供图像的内容",
+                    "Function": HotReload(图片生成_DALLE3),
+                },
+            }
+        )
+        function_plugins.update(
+            {
+                "图片修改_DALLE2 （先切换模型到gpt-*）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": False,  # 调用时，唤起高级参数输入区（默认False）
+                    # "Info": "使用DALLE2修改图片 | 输入参数字符串，提供图像的内容",
+                    "Function": HotReload(图片修改_DALLE2),
+                },
+            }
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.总结音视频 import 总结音视频
-        function_plugins.update({
-            "批量总结音视频（输入路径或上传压缩包）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder": "调用openai api 使用whisper-1模型, 目前支持的格式:mp4, m4a, wav, mpga, mpeg, mp3。此处可以输入解析提示，例如：解析为简体中文（默认）。",
-                "Info": "批量总结音频或视频 | 输入参数为路径",
-                "Function": HotReload(总结音视频)
+
+        function_plugins.update(
+            {
+                "批量总结音视频（输入路径或上传压缩包）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "调用openai api 使用whisper-1模型, 目前支持的格式:mp4, m4a, wav, mpga, mpeg, mp3。此处可以输入解析提示，例如：解析为简体中文（默认）。",
+                    "Info": "批量总结音频或视频 | 输入参数为路径",
+                    "Function": HotReload(总结音视频),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.数学动画生成manim import 动画生成
-        function_plugins.update({
-            "数学动画生成（Manim）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "Info": "按照自然语言描述生成一个动画 | 输入参数是一段话",
-                "Function": HotReload(动画生成)
+
+        function_plugins.update(
+            {
+                "数学动画生成（Manim）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Info": "按照自然语言描述生成一个动画 | 输入参数是一段话",
+                    "Function": HotReload(动画生成),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
-        function_plugins.update({
-            "Markdown翻译（手动指定语言）": {
-                "Group": "编程",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder": "请输入要翻译成哪种语言，默认为Chinese。",
-                "Function": HotReload(Markdown翻译指定语言)
+
+        function_plugins.update(
+            {
+                "Markdown翻译（指定翻译成何种语言）": {
+                    "Group": "编程",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "请输入要翻译成哪种语言，默认为Chinese。",
+                    "Function": HotReload(Markdown翻译指定语言),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
-        from crazy_functions.Langchain知识库 import 知识库问答
-        function_plugins.update({
-            "构建知识库（先上传文件素材,再运行此插件）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder": "此处待注入的知识库名称id, 默认为default。文件进入知识库后可长期保存。可以通过再次调用本插件的方式，向知识库追加更多文档。",
-                "Function": HotReload(知识库问答)
+        from crazy_functions.知识库问答 import 知识库文件注入
+
+        function_plugins.update(
+            {
+                "构建知识库（先上传文件素材,再运行此插件）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "此处待注入的知识库名称id, 默认为default。文件进入知识库后可长期保存。可以通过再次调用本插件的方式，向知识库追加更多文档。",
+                    "Function": HotReload(知识库文件注入),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
-        from crazy_functions.Langchain知识库 import 读取知识库作答
-        function_plugins.update({
-            "知识库问答（构建知识库后,再运行此插件）": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder": "待提取的知识库名称id, 默认为default, 您需要构建知识库后再运行此插件。",
-                "Function": HotReload(读取知识库作答)
+        from crazy_functions.知识库问答 import 读取知识库作答
+
+        function_plugins.update(
+            {
+                "知识库文件注入（构建知识库后,再运行此插件）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "待提取的知识库名称id, 默认为default, 您需要构建知识库后再运行此插件。",
+                    "Function": HotReload(读取知识库作答),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.交互功能函数模板 import 交互功能模板函数
-        function_plugins.update({
-            "交互功能模板函数": {
-                "Group": "对话",
-                "Color": "stop",
-                "AsButton": False,
-                "Function": HotReload(交互功能模板函数)
+
+        function_plugins.update(
+            {
+                "交互功能模板Demo函数（查找wallhaven.cc的壁纸）": {
+                    "Group": "对话",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Function": HotReload(交互功能模板函数),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
-        from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
-        function_plugins.update({
-            "Latex英文纠错+高亮修正位置 [需Latex]": {
-                "Group": "学术",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
-                "Function": HotReload(Latex英文纠错加PDF对比)
+        from crazy_functions.Latex输出PDF import Latex英文纠错加PDF对比
+        from crazy_functions.Latex输出PDF import Latex翻译中文并重新编译PDF
+        from crazy_functions.Latex输出PDF import PDF翻译中文并重新编译PDF
+
+        function_plugins.update(
+            {
+                "Latex英文纠错+高亮修正位置 [需Latex]": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
+                    "Function": HotReload(Latex英文纠错加PDF对比),
+                },
+                "Arxiv论文精细翻译（输入arxivID）[需Latex]": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                                    r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                    r'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                    "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
+                    "Function": HotReload(Latex翻译中文并重新编译PDF),
+                },
+                "本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                                    r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                    r'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                    "Info": "本地Latex论文精细翻译 | 输入参数是路径",
+                    "Function": HotReload(Latex翻译中文并重新编译PDF),
+                },
+                "PDF翻译中文并重新编译PDF（上传PDF）[需Latex]": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "AdvancedArgs": True,
+                    "ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
+                                    r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
+                                    r'If the term "agent" is used in this section, it should be translated to "智能体". ',
+                    "Info": "PDF翻译中文，并重新编译PDF | 输入参数为路径",
+                    "Function": HotReload(PDF翻译中文并重新编译PDF)
+                }
             }
-        })
-        from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
-        function_plugins.update({
-            "Arixv论文精细翻译（输入arxivID）[需Latex]": {
-                "Group": "学术",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder":
-                    "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 " +
-                    "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " +
-                    'If the term "agent" is used in this section, it should be translated to "智能体". ',
-                "Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
-                "Function": HotReload(Latex翻译中文并重新编译PDF)
-            }
-        })
-        function_plugins.update({
-            "本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
-                "Group": "学术",
-                "Color": "stop",
-                "AsButton": False,
-                "AdvancedArgs": True,
-                "ArgsReminder":
-                    "如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 " +
-                    "例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " +
-                    'If the term "agent" is used in this section, it should be translated to "智能体". ',
-                "Info": "本地Latex论文精细翻译 | 输入参数是路径",
-                "Function": HotReload(Latex翻译中文并重新编译PDF)
-            }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from toolbox import get_conf
-        ENABLE_AUDIO, = get_conf('ENABLE_AUDIO')
+
+        ENABLE_AUDIO = get_conf("ENABLE_AUDIO")
         if ENABLE_AUDIO:
             from crazy_functions.语音助手 import 语音助手
-            function_plugins.update({
-                "实时音频采集": {
-                    "Group": "对话",
-                    "Color": "stop",
-                    "AsButton": True,
-                    "Info": "开始语言对话 | 没有输入参数",
-                    "Function": HotReload(语音助手)
+
+            function_plugins.update(
+                {
+                    "实时语音对话": {
+                        "Group": "对话",
+                        "Color": "stop",
+                        "AsButton": True,
+                        "Info": "这是一个时刻聆听着的语音对话助手 | 没有输入参数",
+                        "Function": HotReload(语音助手),
+                    }
                 }
-            })
+            )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.批量翻译PDF文档_NOUGAT import 批量翻译PDF文档
-        function_plugins.update({
-            "精准翻译PDF文档（NOUGAT）": {
-                "Group": "学术",
-                "Color": "stop",
-                "AsButton": False,
-                "Function": HotReload(批量翻译PDF文档)
+
+        function_plugins.update(
+            {
+                "精准翻译PDF文档（NOUGAT）": {
+                    "Group": "学术",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Function": HotReload(批量翻译PDF文档),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     try:
         from crazy_functions.函数动态生成 import 函数动态生成
-        function_plugins.update({
-            "动态代码解释器（CodeInterpreter）": {
-                "Group": "智能体",
-                "Color": "stop",
-                "AsButton": False,
-                "Function": HotReload(函数动态生成)
+
+        function_plugins.update(
+            {
+                "动态代码解释器（CodeInterpreter）": {
+                    "Group": "智能体",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Function": HotReload(函数动态生成),
+                }
             }
-        })
+        )
     except:
-        print('Load function plugin failed')
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        from crazy_functions.多智能体 import 多智能体终端
+
+        function_plugins.update(
+            {
+                "AutoGen多智能体终端（仅供测试）": {
+                    "Group": "智能体",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Function": HotReload(多智能体终端),
+                }
+            }
+        )
+    except:
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        from crazy_functions.互动小游戏 import 随机小游戏
+
+        function_plugins.update(
+            {
+                "随机互动小游戏（仅供测试）": {
+                    "Group": "智能体",
+                    "Color": "stop",
+                    "AsButton": False,
+                    "Function": HotReload(随机小游戏),
+                }
+            }
+        )
+    except:
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
 
     # try:
-    #     from crazy_functions.CodeInterpreter import 虚空终端CodeInterpreter
+    #     from crazy_functions.高级功能函数模板 import 测试图表渲染
     #     function_plugins.update({
-    #         "CodeInterpreter（开发中，仅供测试）": {
-    #             "Group": "编程|对话",
+    #         "绘制逻辑关系（测试图表渲染）": {
+    #             "Group": "智能体",
     #             "Color": "stop",
-    #             "AsButton": False,
-    #             "Function": HotReload(虚空终端CodeInterpreter)
+    #             "AsButton": True,
+    #             "Function": HotReload(测试图表渲染)
     #         }
     #     })
     # except:
+    #     print(trimmed_format_exc())
     #     print('Load function plugin failed')
 
     # try:
@@ -561,8 +703,6 @@ def get_crazy_functions():
     # except:
     #     print('Load function plugin failed')
 
-
-
     """
     设置默认值:
     - 默认 Group = 对话
@@ -572,12 +712,12 @@ def get_crazy_functions():
     """
     for name, function_meta in function_plugins.items():
         if "Group" not in function_meta:
-            function_plugins[name]["Group"] = '对话'
+            function_plugins[name]["Group"] = "对话"
         if "AsButton" not in function_meta:
             function_plugins[name]["AsButton"] = True
         if "AdvancedArgs" not in function_meta:
             function_plugins[name]["AdvancedArgs"] = False
         if "Color" not in function_meta:
-            function_plugins[name]["Color"] = 'secondary'
+            function_plugins[name]["Color"] = "secondary"
 
     return function_plugins

crazy_functions/CodeInterpreter.py

@@ -1,232 +0,0 @@
-from collections.abc import Callable, Iterable, Mapping
-from typing import Any
-from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc
-from toolbox import promote_file_to_downloadzone, get_log_folder
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import input_clipping, try_install_deps
-from multiprocessing import Process, Pipe
-import os
-import time
-
-templete = """
-```python
-import ...  # Put dependencies here, e.g. import numpy as np
-
-class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
-
-    def run(self, path):    # The name of the function must be `run`, it takes only a positional argument.
-        # rewrite the function you have just written here 
-        ...
-        return generated_file_path
-```
-"""
-
-def inspect_dependency(chatbot, history):
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    return True
-
-def get_code_block(reply):
-    import re
-    pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
-    matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) == 1: 
-        return matches[0].strip('python') #  code block
-    for match in matches:
-        if 'class TerminalFunction' in match:
-            return match.strip('python') #  code block
-    raise RuntimeError("GPT is not generating proper code.")
-
-def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
-    # 输入
-    prompt_compose = [
-        f'Your job:\n'
-        f'1. write a single Python function, which takes a path of a `{file_type}` file as the only argument and returns a `string` containing the result of analysis or the path of generated files. \n',
-        f"2. You should write this function to perform following task: " + txt + "\n",
-        f"3. Wrap the output python function with markdown codeblock."
-    ]
-    i_say = "".join(prompt_compose)
-    demo = []
-
-    # 第一步
-    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=i_say, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo, 
-        sys_prompt= r"You are a programmer."
-    )
-    history.extend([i_say, gpt_say])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-
-    # 第二步
-    prompt_compose = [
-        "If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
-        templete
-    ]
-    i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
-    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=inputs_show_user, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-        sys_prompt= r"You are a programmer."
-    )
-    code_to_return = gpt_say
-    history.extend([i_say, gpt_say])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
-    # # 第三步
-    # i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
-    # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
-    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=inputs_show_user, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-    #     sys_prompt= r"You are a programmer."
-    # )
-    # # # 第三步  
-    # i_say = "Show me how to use `pip` to install packages to run the code above. "
-    # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
-    # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=i_say, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
-    #     sys_prompt= r"You are a programmer."
-    # )
-    installation_advance = ""
-    
-    return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
-
-def make_module(code):
-    module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
-    with open(f'{get_log_folder()}/{module_file}.py', 'w', encoding='utf8') as f:
-        f.write(code)
-
-    def get_class_name(class_string):
-        import re
-        # Use regex to extract the class name
-        class_name = re.search(r'class (\w+)\(', class_string).group(1)
-        return class_name
-
-    class_name = get_class_name(code)
-    return f"{get_log_folder().replace('/', '.')}.{module_file}->{class_name}"
-
-def init_module_instance(module):
-    import importlib
-    module_, class_ = module.split('->')
-    init_f = getattr(importlib.import_module(module_), class_)
-    return init_f()
-
-def for_immediate_show_off_when_possible(file_type, fp, chatbot):
-    if file_type in ['png', 'jpg']:
-        image_path = os.path.abspath(fp)
-        chatbot.append(['这是一张图片, 展示如下:',  
-            f'本地文件地址: <br/>`{image_path}`<br/>'+
-            f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
-        ])
-    return chatbot
-
-def subprocess_worker(instance, file_path, return_dict):
-    return_dict['result'] = instance.run(file_path)
-
-def have_any_recent_upload_files(chatbot):
-    _5min = 5 * 60
-    if not chatbot: return False    # chatbot is None
-    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
-    if not most_recent_uploaded: return False   # most_recent_uploaded is None
-    if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
-    else: return False  # most_recent_uploaded is too old
-
-def get_recent_file_prompt_support(chatbot):
-    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
-    path = most_recent_uploaded['path']
-    return path
-
-@CatchException
-def 虚空终端CodeInterpreter(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
-    """
-    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
-    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数，暂时没有用武之地
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
-    system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
-    """
-    raise NotImplementedError
-
-    # 清空历史，以免输入溢出
-    history = []; clear_file_downloadzone(chatbot)
-
-    # 基本信息：功能、贡献者
-    chatbot.append([
-        "函数插件功能？",
-        "CodeInterpreter开源版, 此插件处于开发阶段, 建议暂时不要使用, 插件初始化中 ..."
-    ])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    if have_any_recent_upload_files(chatbot):
-        file_path = get_recent_file_prompt_support(chatbot)
-    else:
-        chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 读取文件
-    if ("recently_uploaded_files" in plugin_kwargs) and (plugin_kwargs["recently_uploaded_files"] == ""): plugin_kwargs.pop("recently_uploaded_files")
-    recently_uploaded_files = plugin_kwargs.get("recently_uploaded_files", None)
-    file_path = recently_uploaded_files[-1]
-    file_type = file_path.split('.')[-1]
-
-    # 粗心检查
-    if is_the_upload_folder(txt):
-        chatbot.append([
-            "...",
-            f"请在输入框内填写需求，然后再次点击该插件（文件路径 {file_path} 已经被记忆）"
-        ])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-    # 开始干正事
-    for j in range(5):  # 最多重试5次
-        try:
-            code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
-                yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
-            code = get_code_block(code)
-            res = make_module(code)
-            instance = init_module_instance(res)
-            break
-        except Exception as e:
-            chatbot.append([f"第{j}次代码生成尝试，失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 代码生成结束, 开始执行
-    try:
-        import multiprocessing
-        manager = multiprocessing.Manager()
-        return_dict = manager.dict()
-
-        p = multiprocessing.Process(target=subprocess_worker, args=(instance, file_path, return_dict))
-        # only has 10 seconds to run
-        p.start(); p.join(timeout=10)
-        if p.is_alive(): p.terminate(); p.join()
-        p.close()
-        res = return_dict['result']
-        # res = instance.run(file_path)
-    except Exception as e:
-        chatbot.append(["执行失败了", f"错误追踪\n```\n{trimmed_format_exc()}\n```\n"])
-        # chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 顺利完成，收尾
-    res = str(res)
-    if os.path.exists(res):
-        chatbot.append(["执行成功了，结果是一个有效文件", "结果：" + res])
-        new_file_path = promote_file_to_downloadzone(res, chatbot=chatbot)
-        chatbot = for_immediate_show_off_when_possible(file_type, new_file_path, chatbot)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    else:
-        chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新   
-
-"""
-测试：
-    裁剪图像，保留下半部分
-    交换图像的蓝色通道和红色通道
-    将图像转为灰度图像
-    将csv文件转excel表格
-"""

crazy_functions/Latex全文润色.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui, trimmed_format_exc, promote_file_to_downloadzone, get_log_folder
-from toolbox import CatchException, report_execption, write_history_to_file, zip_folder
+from toolbox import CatchException, report_exception, write_history_to_file, zip_folder
 
 
 class PaperFileGroup():
@@ -11,7 +11,7 @@ class PaperFileGroup():
         self.sp_file_tag = []
 
         # count_token
-        from request_llm.bridge_all import model_info
+        from request_llms.bridge_all import model_info
         enc = model_info["gpt-3.5-turbo"]['tokenizer']
         def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
         self.get_token_num = get_token_num
@@ -26,8 +26,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
@@ -46,7 +46,7 @@ class PaperFileGroup():
                 manifest.append(path + '.polish.tex')
                 f.write(res)
         return manifest
-    
+
     def zip_result(self):
         import os, time
         folder = os.path.dirname(self.file_paths[0])
@@ -59,7 +59,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
 
-    #  <-------- 读取Latex文件，删除其中的所有注释 ----------> 
+    #  <-------- 读取Latex文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
 
     for index, fp in enumerate(file_manifest):
@@ -73,31 +73,31 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_paths.append(fp)
             pfg.file_contents.append(clean_tex_content)
 
-    #  <-------- 拆分过长的latex文件 ----------> 
+    #  <-------- 拆分过长的latex文件 ---------->
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
 
-    #  <-------- 多线程润色开始 ----------> 
+    #  <-------- 多线程润色开始 ---------->
     if language == 'en':
         if mode == 'polish':
-            inputs_array = ["Below is a section from an academic paper, polish this section to meet the academic standard, " + 
-                            "improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" + 
+            inputs_array = [r"Below is a section from an academic paper, polish this section to meet the academic standard, " +
+                            r"improve the grammar, clarity and overall readability, do not modify any latex command such as \section, \cite and equations:" +
                             f"\n\n{frag}" for frag in pfg.sp_file_contents]
         else:
-            inputs_array = [r"Below is a section from an academic paper, proofread this section." + 
-                            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
-                            r"Answer me only with the revised text:" + 
+            inputs_array = [r"Below is a section from an academic paper, proofread this section." +
+                            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
+                            r"Answer me only with the revised text:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"Polish {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
     elif language == 'zh':
         if mode == 'polish':
-            inputs_array = [f"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
+            inputs_array = [r"以下是一篇学术论文中的一段内容，请将此部分润色以满足学术标准，提高语法、清晰度和整体可读性，不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
                             f"\n\n{frag}" for frag in pfg.sp_file_contents]
         else:
-            inputs_array = [f"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" + 
-                            f"\n\n{frag}" for frag in pfg.sp_file_contents] 
+            inputs_array = [r"以下是一篇学术论文中的一段内容，请对这部分内容进行语法矫正。不要修改任何LaTeX命令，例如\section，\cite和方程式：" +
+                            f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"润色 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array=["你是一位专业的中文学术论文作家。" for _ in range(n_split)]
 
@@ -113,7 +113,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         scroller_max_len = 80
     )
 
-    #  <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ----------> 
+    #  <-------- 文本碎片重组为完整的tex文件，整理结果为压缩包 ---------->
     try:
         pfg.sp_file_result = []
         for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
@@ -124,7 +124,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     except:
         print(trimmed_format_exc())
 
-    #  <-------- 整理结果，退出 ----------> 
+    #  <-------- 整理结果，退出 ---------->
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
     res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
     promote_file_to_downloadzone(res, chatbot=chatbot)
@@ -135,18 +135,18 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
 
 
 @CatchException
-def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
-        "对整个Latex项目进行润色。函数插件贡献者: Binary-Husky。（注意，此插件不调用Latex，如果有Latex环境，请使用“Latex英文纠错+高亮”插件）"])
+        "对整个Latex项目进行润色。函数插件贡献者: Binary-Husky。（注意，此插件不调用Latex，如果有Latex环境，请使用「Latex英文纠错+高亮修正位置(需Latex)插件」"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -157,12 +157,12 @@ def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en')
@@ -173,7 +173,7 @@ def Latex英文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
 
 
 @CatchException
-def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
@@ -184,7 +184,7 @@ def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -195,12 +195,12 @@ def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh')
@@ -209,7 +209,7 @@ def Latex中文润色(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
 
 
 @CatchException
-def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
@@ -220,7 +220,7 @@ def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -231,12 +231,12 @@ def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en', mode='proofread')

crazy_functions/Latex全文翻译.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui, promote_file_to_downloadzone
-from toolbox import CatchException, report_execption, write_history_to_file
+from toolbox import CatchException, report_exception, write_history_to_file
 fast_debug = False
 
 class PaperFileGroup():
@@ -11,7 +11,7 @@ class PaperFileGroup():
         self.sp_file_tag = []
 
         # count_token
-        from request_llm.bridge_all import model_info
+        from request_llms.bridge_all import model_info
         enc = model_info["gpt-3.5-turbo"]['tokenizer']
         def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
         self.get_token_num = get_token_num
@@ -26,8 +26,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
@@ -39,7 +39,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     import time, os, re
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
-    #  <-------- 读取Latex文件，删除其中的所有注释 ----------> 
+    #  <-------- 读取Latex文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
 
     for index, fp in enumerate(file_manifest):
@@ -53,11 +53,11 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_paths.append(fp)
             pfg.file_contents.append(clean_tex_content)
 
-    #  <-------- 拆分过长的latex文件 ----------> 
+    #  <-------- 拆分过长的latex文件 ---------->
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 抽取摘要 ----------> 
+    #  <-------- 抽取摘要 ---------->
     # if language == 'en':
     #     abs_extract_inputs = f"Please write an abstract for this paper"
 
@@ -70,14 +70,14 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     #     sys_prompt="Your job is to collect information from materials。",
     # )
 
-    #  <-------- 多线程润色开始 ----------> 
+    #  <-------- 多线程润色开始 ---------->
     if language == 'en->zh':
-        inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" + 
+        inputs_array = ["Below is a section from an English academic paper, translate it into Chinese, do not modify any latex command such as \section, \cite and equations:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
     elif language == 'zh->en':
-        inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" + 
+        inputs_array = [f"Below is a section from a Chinese academic paper, translate it into English, do not modify any latex command such as \section, \cite and equations:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
@@ -93,7 +93,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         scroller_max_len = 80
     )
 
-    #  <-------- 整理结果，退出 ----------> 
+    #  <-------- 整理结果，退出 ---------->
     create_report_file_name = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + f"-chatgpt.polish.md"
     res = write_history_to_file(gpt_response_collection, create_report_file_name)
     promote_file_to_downloadzone(res, chatbot=chatbot)
@@ -106,7 +106,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
 
 
 @CatchException
-def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
@@ -117,7 +117,7 @@ def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -128,12 +128,12 @@ def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en->zh')
@@ -143,7 +143,7 @@ def Latex英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
 
 
 @CatchException
-def Latex中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Latex中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
@@ -154,7 +154,7 @@ def Latex中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -165,12 +165,12 @@ def Latex中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh->en')

crazy_functions/Latex输出PDF.py

@@ -0,0 +1,543 @@
+from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
+from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
+from functools import partial
+import glob, os, requests, time, json, tarfile
+
+pj = os.path.join
+ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 工具函数 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
+# 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
+def switch_prompt(pfg, mode, more_requirement):
+    """
+    Generate prompts and system prompts based on the mode for proofreading or translating.
+    Args:
+    - pfg: Proofreader or Translator instance.
+    - mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
+
+    Returns:
+    - inputs_array: A list of strings containing prompts for users to respond to.
+    - sys_prompt_array: A list of strings containing prompts for system prompts.
+    """
+    n_split = len(pfg.sp_file_contents)
+    if mode == 'proofread_en':
+        inputs_array = [r"Below is a section from an academic paper, proofread this section." +
+                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
+                        r"Answer me only with the revised text:" +
+                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
+    elif mode == 'translate_zh':
+        inputs_array = [
+            r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
+            r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
+            r"Answer me only with the translated text:" +
+            f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
+    else:
+        assert False, "未知指令"
+    return inputs_array, sys_prompt_array
+
+
+def desend_to_extracted_folder_if_exist(project_folder):
+    """
+    Descend into the extracted folder if it exists, otherwise return the original folder.
+
+    Args:
+    - project_folder: A string specifying the folder path.
+
+    Returns:
+    - A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
+    """
+    maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
+    if len(maybe_dir) == 0: return project_folder
+    if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
+    return project_folder
+
+
+def move_project(project_folder, arxiv_id=None):
+    """
+    Create a new work folder and copy the project folder to it.
+
+    Args:
+    - project_folder: A string specifying the folder path of the project.
+
+    Returns:
+    - A string specifying the path to the new work folder.
+    """
+    import shutil, time
+    time.sleep(2)  # avoid time string conflict
+    if arxiv_id is not None:
+        new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
+    else:
+        new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
+    try:
+        shutil.rmtree(new_workfolder)
+    except:
+        pass
+
+    # align subfolder if there is a folder wrapper
+    items = glob.glob(pj(project_folder, '*'))
+    items = [item for item in items if os.path.basename(item) != '__MACOSX']
+    if len(glob.glob(pj(project_folder, '*.tex'))) == 0 and len(items) == 1:
+        if os.path.isdir(items[0]): project_folder = items[0]
+
+    shutil.copytree(src=project_folder, dst=new_workfolder)
+    return new_workfolder
+
+
+def arxiv_download(chatbot, history, txt, allow_cache=True):
+    def check_cached_translation_pdf(arxiv_id):
+        translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
+        if not os.path.exists(translation_dir):
+            os.makedirs(translation_dir)
+        target_file = pj(translation_dir, 'translate_zh.pdf')
+        if os.path.exists(target_file):
+            promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
+            target_file_compare = pj(translation_dir, 'comparison.pdf')
+            if os.path.exists(target_file_compare):
+                promote_file_to_downloadzone(target_file_compare, rename_file=None, chatbot=chatbot)
+            return target_file
+        return False
+
+    def is_float(s):
+        try:
+            float(s)
+            return True
+        except ValueError:
+            return False
+
+    if txt.startswith('https://arxiv.org/pdf/'):
+        arxiv_id = txt.split('/')[-1]   # 2402.14207v2.pdf
+        txt = arxiv_id.split('v')[0]  # 2402.14207
+
+    if ('.' in txt) and ('/' not in txt) and is_float(txt):  # is arxiv ID
+        txt = 'https://arxiv.org/abs/' + txt.strip()
+    if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]):  # is arxiv ID
+        txt = 'https://arxiv.org/abs/' + txt[:10]
+
+    if not txt.startswith('https://arxiv.org'):
+        return txt, None    # 是本地文件，跳过下载
+
+    # <-------------- inspect format ------------->
+    chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
+    yield from update_ui(chatbot=chatbot, history=history)
+    time.sleep(1)  # 刷新界面
+
+    url_ = txt  # https://arxiv.org/abs/1707.06690
+
+    if not txt.startswith('https://arxiv.org/abs/'):
+        msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
+        yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history)  # 刷新界面
+        return msg, None
+    # <-------------- set format ------------->
+    arxiv_id = url_.split('/abs/')[-1]
+    if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
+    cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
+    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
+
+    url_tar = url_.replace('/abs/', '/e-print/')
+    translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
+    extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
+    os.makedirs(translation_dir, exist_ok=True)
+
+    # <-------------- download arxiv source file ------------->
+    dst = pj(translation_dir, arxiv_id + '.tar')
+    if os.path.exists(dst):
+        yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history)  # 刷新界面
+    else:
+        yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history)  # 刷新界面
+        proxies = get_conf('proxies')
+        r = requests.get(url_tar, proxies=proxies)
+        with open(dst, 'wb+') as f:
+            f.write(r.content)
+    # <-------------- extract file ------------->
+    yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history)  # 刷新界面
+    from toolbox import extract_archive
+    extract_archive(file_path=dst, dest_dir=extract_dst)
+    return extract_dst, arxiv_id
+
+
+def pdf2tex_project(pdf_file_path):
+    # Mathpix API credentials
+    app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
+    headers = {"app_id": app_id, "app_key": app_key}
+
+    # Step 1: Send PDF file for processing
+    options = {
+        "conversion_formats": {"tex.zip": True},
+        "math_inline_delimiters": ["$", "$"],
+        "rm_spaces": True
+    }
+
+    response = requests.post(url="https://api.mathpix.com/v3/pdf",
+                             headers=headers,
+                             data={"options_json": json.dumps(options)},
+                             files={"file": open(pdf_file_path, "rb")})
+
+    if response.ok:
+        pdf_id = response.json()["pdf_id"]
+        print(f"PDF processing initiated. PDF ID: {pdf_id}")
+
+        # Step 2: Check processing status
+        while True:
+            conversion_response = requests.get(f"https://api.mathpix.com/v3/pdf/{pdf_id}", headers=headers)
+            conversion_data = conversion_response.json()
+
+            if conversion_data["status"] == "completed":
+                print("PDF processing completed.")
+                break
+            elif conversion_data["status"] == "error":
+                print("Error occurred during processing.")
+            else:
+                print(f"Processing status: {conversion_data['status']}")
+                time.sleep(5)  # wait for a few seconds before checking again
+
+        # Step 3: Save results to local files
+        output_dir = os.path.join(os.path.dirname(pdf_file_path), 'mathpix_output')
+        if not os.path.exists(output_dir):
+            os.makedirs(output_dir)
+
+        url = f"https://api.mathpix.com/v3/pdf/{pdf_id}.tex"
+        response = requests.get(url, headers=headers)
+        file_name_wo_dot = '_'.join(os.path.basename(pdf_file_path).split('.')[:-1])
+        output_name = f"{file_name_wo_dot}.tex.zip"
+        output_path = os.path.join(output_dir, output_name)
+        with open(output_path, "wb") as output_file:
+            output_file.write(response.content)
+        print(f"tex.zip file saved at: {output_path}")
+
+        import zipfile
+        unzip_dir = os.path.join(output_dir, file_name_wo_dot)
+        with zipfile.ZipFile(output_path, 'r') as zip_ref:
+            zip_ref.extractall(unzip_dir)
+
+        return unzip_dir
+
+    else:
+        print(f"Error sending PDF for processing. Status code: {response.status_code}")
+        return None
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序1 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+
+@CatchException
+def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    # <-------------- information about this plugin ------------->
+    chatbot.append(["函数插件功能？",
+                    "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    history = []
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+    if len(file_manifest) == 0:
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- if is a zip/tar file ------------->
+    project_folder = desend_to_extracted_folder_if_exist(project_folder)
+
+    # <-------------- move latex project away from temp folder ------------->
+    project_folder = move_project(project_folder, arxiv_id=None)
+
+    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
+        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+                                       chatbot, history, system_prompt, mode='proofread_en',
+                                       switch_prompt=_switch_prompt_)
+
+    # <-------------- compile PDF ------------->
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                   main_file_modified='merge_proofread_en',
+                                   work_folder_original=project_folder, work_folder_modified=project_folder,
+                                   work_folder=project_folder)
+
+    # <-------------- zip PDF ------------->
+    zip_res = zip_result(project_folder)
+    if success:
+        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+    else:
+        chatbot.append((f"失败了",
+                        '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+    # <-------------- we are done ------------->
+    return success
+
+
+# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= 插件主程序2 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+@CatchException
+def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    # <-------------- information about this plugin ------------->
+    chatbot.append([
+        "函数插件功能？",
+        "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    history = []
+    try:
+        txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
+    except tarfile.ReadError as e:
+        yield from update_ui_lastest_msg(
+            "无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
+            chatbot=chatbot, history=history)
+        return
+
+    if txt.endswith('.pdf'):
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现已经存在翻译好的PDF文档")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+    if len(file_manifest) == 0:
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- if is a zip/tar file ------------->
+    project_folder = desend_to_extracted_folder_if_exist(project_folder)
+
+    # <-------------- move latex project away from temp folder ------------->
+    project_folder = move_project(project_folder, arxiv_id)
+
+    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+    if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
+        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+                                       chatbot, history, system_prompt, mode='translate_zh',
+                                       switch_prompt=_switch_prompt_)
+
+    # <-------------- compile PDF ------------->
+    success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                   main_file_modified='merge_translate_zh', mode='translate_zh',
+                                   work_folder_original=project_folder, work_folder_modified=project_folder,
+                                   work_folder=project_folder)
+
+    # <-------------- zip PDF ------------->
+    zip_res = zip_result(project_folder)
+    if success:
+        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+    else:
+        chatbot.append((f"失败了",
+                        '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
+        yield from update_ui(chatbot=chatbot, history=history);
+        time.sleep(1)  # 刷新界面
+        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+    # <-------------- we are done ------------->
+    return success
+
+
+#  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=- 插件主程序3  =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+
+@CatchException
+def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    # <-------------- information about this plugin ------------->
+    chatbot.append([
+        "函数插件功能？",
+        "将PDF转换为Latex项目，翻译为中文后重新编译为PDF。函数插件贡献者: Marroh。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # <-------------- more requirements ------------->
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    more_req = plugin_kwargs.get("advanced_arg", "")
+    no_cache = more_req.startswith("--no-cache")
+    if no_cache: more_req.lstrip("--no-cache")
+    allow_cache = not no_cache
+    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
+
+    # <-------------- check deps ------------->
+    try:
+        import glob, os, time, subprocess
+        subprocess.Popen(['pdflatex', '-version'])
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
+    except Exception as e:
+        chatbot.append([f"解析项目: {txt}",
+                        f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # <-------------- clear history and read input ------------->
+    if os.path.exists(txt):
+        project_folder = txt
+    else:
+        if txt == "": txt = '空空如也的输入栏'
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无法处理: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
+    if len(file_manifest) == 0:
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.pdf文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    if len(file_manifest) != 1:
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"不支持同时处理多个pdf文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+    app_id, app_key = get_conf('MATHPIX_APPID', 'MATHPIX_APPKEY')
+    if len(app_id) == 0 or len(app_key) == 0:
+        report_exception(chatbot, history, a="缺失 MATHPIX_APPID 和 MATHPIX_APPKEY。", b=f"请配置 MATHPIX_APPID 和 MATHPIX_APPKEY")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    hash_tag = map_file_to_sha256(file_manifest[0])
+
+    # <-------------- check repeated pdf ------------->
+    chatbot.append([f"检查PDF是否被重复上传", "正在检查..."])
+    yield from update_ui(chatbot=chatbot, history=history)
+    repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
+
+    except_flag = False
+
+    if repeat:
+        yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
+
+        try:
+            trans_html_file = [f for f in glob.glob(f'{project_folder}/**/*.trans.html', recursive=True)][0]
+            promote_file_to_downloadzone(trans_html_file, rename_file=None, chatbot=chatbot)
+
+            translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
+            promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
+
+            comparison_pdf = [f for f in glob.glob(f'{project_folder}/**/comparison.pdf', recursive=True)][0]
+            promote_file_to_downloadzone(comparison_pdf, rename_file=None, chatbot=chatbot)
+
+            zip_res = zip_result(project_folder)
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+            return True
+
+        except:
+            report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
+            yield from update_ui(chatbot=chatbot, history=history)
+
+            chatbot.append([f"没有相关文件", '尝试重新翻译PDF...'])
+            yield from update_ui(chatbot=chatbot, history=history)
+
+            except_flag = True
+
+
+    elif not repeat or except_flag:
+        yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
+
+        # <-------------- convert pdf into tex ------------->
+        chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
+        yield from update_ui(chatbot=chatbot, history=history)
+        project_folder = pdf2tex_project(file_manifest[0])
+        if project_folder is None:
+            report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"PDF转换为tex项目失败")
+            yield from update_ui(chatbot=chatbot, history=history)
+            return False
+
+        # <-------------- translate latex file into Chinese ------------->
+        yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
+        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
+        if len(file_manifest) == 0:
+            report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+            return
+
+        # <-------------- if is a zip/tar file ------------->
+        project_folder = desend_to_extracted_folder_if_exist(project_folder)
+
+        # <-------------- move latex project away from temp folder ------------->
+        project_folder = move_project(project_folder)
+
+        # <-------------- set a hash tag for repeat-checking ------------->
+        with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
+            f.write(hash_tag)
+            f.close()
+
+
+        # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
+        if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
+            yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
+                                        chatbot, history, system_prompt, mode='translate_zh',
+                                        switch_prompt=_switch_prompt_)
+
+        # <-------------- compile PDF ------------->
+        yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
+        success = yield from 编译Latex(chatbot, history, main_file_original='merge',
+                                    main_file_modified='merge_translate_zh', mode='translate_zh',
+                                    work_folder_original=project_folder, work_folder_modified=project_folder,
+                                    work_folder=project_folder)
+
+        # <-------------- zip PDF ------------->
+        zip_res = zip_result(project_folder)
+        if success:
+            chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
+            yield from update_ui(chatbot=chatbot, history=history);
+            time.sleep(1)  # 刷新界面
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+        else:
+            chatbot.append((f"失败了",
+                            '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
+            yield from update_ui(chatbot=chatbot, history=history);
+            time.sleep(1)  # 刷新界面
+            promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
+
+        # <-------------- we are done ------------->
+        return success

crazy_functions/Latex输出PDF结果.py

@@ -1,303 +0,0 @@
-from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
-from toolbox import CatchException, report_execption, update_ui_lastest_msg, zip_result, gen_time_str
-from functools import partial
-import glob, os, requests, time
-pj = os.path.join
-ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
-
-# =================================== 工具函数 ===============================================
-# 专业词汇声明  = 'If the term "agent" is used in this section, it should be translated to "智能体". '
-def switch_prompt(pfg, mode, more_requirement):
-    """
-    Generate prompts and system prompts based on the mode for proofreading or translating.
-    Args:
-    - pfg: Proofreader or Translator instance.
-    - mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
-
-    Returns:
-    - inputs_array: A list of strings containing prompts for users to respond to.
-    - sys_prompt_array: A list of strings containing prompts for system prompts.
-    """
-    n_split = len(pfg.sp_file_contents)
-    if mode == 'proofread_en':
-        inputs_array = [r"Below is a section from an academic paper, proofread this section." + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
-                        r"Answer me only with the revised text:" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
-        sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
-    elif mode == 'translate_zh':
-        inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement + 
-                        r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + 
-                        r"Answer me only with the translated text:" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
-        sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
-    else:
-        assert False, "未知指令"
-    return inputs_array, sys_prompt_array
-
-def desend_to_extracted_folder_if_exist(project_folder):
-    """ 
-    Descend into the extracted folder if it exists, otherwise return the original folder.
-
-    Args:
-    - project_folder: A string specifying the folder path.
-
-    Returns:
-    - A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
-    """
-    maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
-    if len(maybe_dir) == 0: return project_folder
-    if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
-    return project_folder
-
-def move_project(project_folder, arxiv_id=None):
-    """ 
-    Create a new work folder and copy the project folder to it.
-
-    Args:
-    - project_folder: A string specifying the folder path of the project.
-
-    Returns:
-    - A string specifying the path to the new work folder.
-    """
-    import shutil, time
-    time.sleep(2)   # avoid time string conflict
-    if arxiv_id is not None:
-        new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
-    else:
-        new_workfolder = f'{get_log_folder()}/{gen_time_str()}'
-    try:
-        shutil.rmtree(new_workfolder)
-    except:
-        pass
-
-    # align subfolder if there is a folder wrapper
-    items = glob.glob(pj(project_folder,'*'))
-    if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
-        if os.path.isdir(items[0]): project_folder = items[0]
-
-    shutil.copytree(src=project_folder, dst=new_workfolder)
-    return new_workfolder
-
-def arxiv_download(chatbot, history, txt, allow_cache=True):
-    def check_cached_translation_pdf(arxiv_id):
-        translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
-        if not os.path.exists(translation_dir):
-            os.makedirs(translation_dir)
-        target_file = pj(translation_dir, 'translate_zh.pdf')
-        if os.path.exists(target_file):
-            promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
-            return target_file
-        return False
-    def is_float(s):
-        try:
-            float(s)
-            return True
-        except ValueError:
-            return False
-    if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
-        txt = 'https://arxiv.org/abs/' + txt.strip()
-    if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
-        txt = 'https://arxiv.org/abs/' + txt[:10]
-    if not txt.startswith('https://arxiv.org'): 
-        return txt, None
-    
-    # <-------------- inspect format ------------->
-    chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...']) 
-    yield from update_ui(chatbot=chatbot, history=history)
-    time.sleep(1) # 刷新界面
-
-    url_ = txt   # https://arxiv.org/abs/1707.06690
-    if not txt.startswith('https://arxiv.org/abs/'): 
-        msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
-        yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
-        return msg, None
-    # <-------------- set format ------------->
-    arxiv_id = url_.split('/abs/')[-1]
-    if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
-    cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
-    if cached_translation_pdf and allow_cache: return cached_translation_pdf, arxiv_id
-
-    url_tar = url_.replace('/abs/', '/e-print/')
-    translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'e-print')
-    extract_dst = pj(ARXIV_CACHE_DIR, arxiv_id, 'extract')
-    os.makedirs(translation_dir, exist_ok=True)
-    
-    # <-------------- download arxiv source file ------------->
-    dst = pj(translation_dir, arxiv_id+'.tar')
-    if os.path.exists(dst):
-        yield from update_ui_lastest_msg("调用缓存", chatbot=chatbot, history=history)  # 刷新界面
-    else:
-        yield from update_ui_lastest_msg("开始下载", chatbot=chatbot, history=history)  # 刷新界面
-        proxies, = get_conf('proxies')
-        r = requests.get(url_tar, proxies=proxies)
-        with open(dst, 'wb+') as f:
-            f.write(r.content)
-    # <-------------- extract file ------------->
-    yield from update_ui_lastest_msg("下载完成", chatbot=chatbot, history=history)  # 刷新界面
-    from toolbox import extract_archive
-    extract_archive(file_path=dst, dest_dir=extract_dst)
-    return extract_dst, arxiv_id
-# ========================================= 插件主程序1 =====================================================    
-
-
-@CatchException
-def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
-    # <-------------- information about this plugin ------------->
-    chatbot.append([ "函数插件功能？",
-        "对整个Latex项目进行纠错, 用latex编译为PDF对修正处做高亮。函数插件贡献者: Binary-Husky。注意事项: 目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。仅在Windows系统进行了测试，其他操作系统表现未知。"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    
-    # <-------------- more requirements ------------->
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    more_req = plugin_kwargs.get("advanced_arg", "")
-    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
-
-    # <-------------- check deps ------------->
-    try:
-        import glob, os, time, subprocess
-        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
-    except Exception as e:
-        chatbot.append([ f"解析项目: {txt}",
-            f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- clear history and read input ------------->
-    history = []
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
-    if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- if is a zip/tar file ------------->
-    project_folder = desend_to_extracted_folder_if_exist(project_folder)
-
-
-    # <-------------- move latex project away from temp folder ------------->
-    project_folder = move_project(project_folder, arxiv_id=None)
-
-
-    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
-        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, 
-                                chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
-
-
-    # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en', 
-                             work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
-    
-
-    # <-------------- zip PDF ------------->
-    zip_res = zip_result(project_folder)
-    if success:
-        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-    else:
-        chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-
-    # <-------------- we are done ------------->
-    return success
-
-
-# ========================================= 插件主程序2 =====================================================    
-
-@CatchException
-def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
-    # <-------------- information about this plugin ------------->
-    chatbot.append([
-        "函数插件功能？",
-        "对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # <-------------- more requirements ------------->
-    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    more_req = plugin_kwargs.get("advanced_arg", "")
-    no_cache = more_req.startswith("--no-cache")
-    if no_cache: more_req.lstrip("--no-cache")
-    allow_cache = not no_cache
-    _switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
-
-    # <-------------- check deps ------------->
-    try:
-        import glob, os, time, subprocess
-        subprocess.Popen(['pdflatex', '-version'])
-        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
-    except Exception as e:
-        chatbot.append([ f"解析项目: {txt}",
-            f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- clear history and read input ------------->
-    history = []
-    txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
-    if txt.endswith('.pdf'):
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    if os.path.exists(txt):
-        project_folder = txt
-    else:
-        if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无法处理: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
-    if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-    
-
-    # <-------------- if is a zip/tar file ------------->
-    project_folder = desend_to_extracted_folder_if_exist(project_folder)
-
-
-    # <-------------- move latex project away from temp folder ------------->
-    project_folder = move_project(project_folder, arxiv_id)
-
-
-    # <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
-    if not os.path.exists(project_folder + '/merge_translate_zh.tex'):
-        yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, 
-                                chatbot, history, system_prompt, mode='translate_zh', switch_prompt=_switch_prompt_)
-
-
-    # <-------------- compile PDF ------------->
-    success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_translate_zh', mode='translate_zh', 
-                             work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
-
-    # <-------------- zip PDF ------------->
-    zip_res = zip_result(project_folder)
-    if success:
-        chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-    else:
-        chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 您可以到Github Issue区, 用该压缩包进行反馈。如系统是Linux，请检查系统字体（见Github wiki） ...'))
-        yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
-        promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
-
-
-    # <-------------- we are done ------------->
-    return success

crazy_functions/PDF批量翻译.py

@@ -0,0 +1,324 @@
+from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
+from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
+from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
+from toolbox import generate_file_link, zip_folder, trimmed_format_exc, trimmed_format_exc_markdown
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+from .crazy_utils import read_and_clean_pdf_text
+from .crazy_utils import get_files_from_everything
+from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
+from colorful import *
+import os
+
+
+@CatchException
+def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+
+    disable_auto_promotion(chatbot)
+    # 基本信息：功能、贡献者
+    chatbot.append([None, "插件功能：批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        check_packages(["fitz", "tiktoken", "scipdf"])
+    except:
+        report_exception(chatbot, history,
+                         a=f"解析项目: {txt}",
+                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf tiktoken scipdf_parser```。")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 清空历史，以免输入溢出
+    history = []
+
+    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
+    # 检测输入参数，如没有给定输入参数，直接退出
+    if not success:
+        if txt == "": txt = '空空如也的输入栏'
+
+    # 如果没找到任何文件
+    if len(file_manifest) == 0:
+        report_exception(chatbot, history,
+                         a=f"解析项目: {txt}", b=f"找不到任何.pdf拓展名的文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 开始正式执行任务
+    DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
+    # ------- 第一种方法，效果最好，但是需要DOC2X服务 -------
+    if len(DOC2X_API_KEY) != 0:
+        try:
+            yield from 解析PDF_DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
+            return
+        except:
+            chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
+            yield from update_ui(chatbot=chatbot, history=history)
+
+    # ------- 第二种方法，效果次优 -------
+    grobid_url = get_avail_grobid_url()
+    if grobid_url is not None:
+        yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
+        return
+
+    # ------- 第三种方法，早期代码，效果不理想 -------
+    yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
+    yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+    return
+
+
+
+def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
+
+    def pdf2markdown(filepath):
+        import requests, json, os
+        markdown_dir = get_log_folder(plugin_name="pdf_ocr")
+        doc2x_api_key = DOC2X_API_KEY
+        if doc2x_api_key.startswith('sk-'):
+            url = "https://api.doc2x.noedgeai.com/api/v1/pdf"
+        else:
+            url = "https://api.doc2x.noedgeai.com/api/platform/pdf"
+
+        chatbot.append((None, "加载PDF文件，发送至DOC2X解析..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        res = requests.post(
+            url,
+            files={"file": open(filepath, "rb")},
+            data={"ocr": "1"},
+            headers={"Authorization": "Bearer " + doc2x_api_key}
+        )
+        res_json = []
+        if res.status_code == 200:
+            decoded = res.content.decode("utf-8")
+            for z_decoded in decoded.split('\n'):
+                if len(z_decoded) == 0: continue
+                assert z_decoded.startswith("data: ")
+                z_decoded = z_decoded[len("data: "):]
+                decoded_json = json.loads(z_decoded)
+                res_json.append(decoded_json)
+        else:
+            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+        uuid = res_json[0]['uuid']
+        to = "md" # latex, md, docx
+        url = "https://api.doc2x.noedgeai.com/api/export"+"?request_id="+uuid+"&to="+to
+
+        chatbot.append((None, f"读取解析: {url} ..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        res = requests.get(url, headers={"Authorization": "Bearer " + doc2x_api_key})
+        md_zip_path = os.path.join(markdown_dir, gen_time_str() + '.zip')
+        if res.status_code == 200:
+            with open(md_zip_path, "wb") as f: f.write(res.content)
+        else:
+            raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
+        promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
+        chatbot.append((None, f"完成解析 {md_zip_path} ..."))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return md_zip_path
+
+    def deliver_to_markdown_plugin(md_zip_path, user_request):
+        from crazy_functions.批量Markdown翻译 import Markdown英译中
+        import shutil, re
+
+        time_tag = gen_time_str()
+        target_path_base = get_log_folder(chatbot.get_user())
+        file_origin_name = os.path.basename(md_zip_path)
+        this_file_path = os.path.join(target_path_base, file_origin_name)
+        os.makedirs(target_path_base, exist_ok=True)
+        shutil.copyfile(md_zip_path, this_file_path)
+        ex_folder = this_file_path + ".extract"
+        extract_archive(
+            file_path=this_file_path, dest_dir=ex_folder
+        )
+
+        # edit markdown files
+        success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
+        for generated_fp in file_manifest:
+            # 修正一些公式问题
+            with open(generated_fp, 'r', encoding='utf8') as f:
+                content = f.read()
+            # 将公式中的\[ \]替换成$$
+            content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
+            # 将公式中的\( \)替换成$
+            content = content.replace(r'\(', r'$').replace(r'\)', r'$')
+            content = content.replace('```markdown', '\n').replace('```', '\n')
+            with open(generated_fp, 'w', encoding='utf8') as f:
+                f.write(content)
+            promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+            # 生成在线预览html
+            file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
+            preview_fp = os.path.join(ex_folder, file_name)
+            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            with open(generated_fp, "r", encoding="utf-8") as f:
+                md = f.read()
+                # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
+                md = re.sub(r'^<table>', r'😃<table>', md, flags=re.MULTILINE)
+            html = markdown_convertion_for_file(md)
+            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
+            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
+
+
+
+        chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
+        plugin_kwargs['markdown_expected_output_dir'] = ex_folder
+
+        translated_f_name = 'translated_markdown.md'
+        generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+        if os.path.exists(generated_fp):
+            # 修正一些公式问题
+            with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
+            content = content.replace('```markdown', '\n').replace('```', '\n')
+            # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
+            content = re.sub(r'^<table>', r'😃<table>', content, flags=re.MULTILINE)
+            with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
+            # 生成在线预览html
+            file_name = '在线预览翻译' + gen_time_str() + '.html'
+            preview_fp = os.path.join(ex_folder, file_name)
+            from shared_utils.advanced_markdown_format import markdown_convertion_for_file
+            with open(generated_fp, "r", encoding="utf-8") as f:
+                md = f.read()
+            html = markdown_convertion_for_file(md)
+            with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
+            promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
+            # 生成包含图片的压缩包
+            dest_folder = get_log_folder(chatbot.get_user())
+            zip_name = '翻译后的带图文档.zip'
+            zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
+            zip_fp = os.path.join(dest_folder, zip_name)
+            promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    md_zip_path = yield from pdf2markdown(fp)
+    yield from deliver_to_markdown_plugin(md_zip_path, user_request)
+
+def 解析PDF_DOC2X(file_manifest, *args):
+    for index, fp in enumerate(file_manifest):
+        yield from 解析PDF_DOC2X_单文件(fp, *args)
+    return
+
+def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
+    import copy, json
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
+    generated_conclusion_files = []
+    generated_html_files = []
+    DST_LANG = "中文"
+    from crazy_functions.pdf_fns.report_gen_html import construct_html
+    for index, fp in enumerate(file_manifest):
+        chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        article_dict = parse_pdf(fp, grobid_url)
+        grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
+        with open(grobid_json_res, 'w+', encoding='utf8') as f:
+            f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
+        promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
+
+        if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
+        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
+    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+
+def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+    """
+    此函数已经弃用
+    """
+    import copy
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
+    generated_conclusion_files = []
+    generated_html_files = []
+    from crazy_functions.pdf_fns.report_gen_html import construct_html
+    for index, fp in enumerate(file_manifest):
+        # 读取PDF文件
+        file_content, page_one = read_and_clean_pdf_text(fp)
+        file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+        page_one = str(page_one).encode('utf-8', 'ignore').decode()      # avoid reading non-utf8 chars
+
+        # 递归地切割PDF文件
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+        page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=page_one, limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
+
+        # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
+        paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
+
+        # 单线，获取文章meta信息
+        paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
+            inputs_show_user=f"请从{fp}中提取出“标题”、“收录会议或期刊”等基本信息。",
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot, history=[],
+            sys_prompt="Your job is to collect information from materials。",
+        )
+
+        # 多线，翻译
+        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+            inputs_array=[
+                f"你需要翻译以下内容：\n{frag}" for frag in paper_fragments],
+            inputs_show_user_array=[f"\n---\n 原文： \n\n {frag.replace('#', '')}  \n---\n 翻译：\n " for frag in paper_fragments],
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot,
+            history_array=[[paper_meta] for _ in paper_fragments],
+            sys_prompt_array=[
+                "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
+            # max_workers=5  # OpenAI所允许的最大并行过载
+        )
+        gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
+        # 整理报告的格式
+        for i,k in enumerate(gpt_response_collection_md):
+            if i%2==0:
+                gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
+            else:
+                gpt_response_collection_md[i] = gpt_response_collection_md[i]
+        final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
+        final.extend(gpt_response_collection_md)
+        create_report_file_name = f"{os.path.basename(fp)}.trans.md"
+        res = write_history_to_file(final, create_report_file_name)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
+
+        # 更新UI
+        generated_conclusion_files.append(f'{get_log_folder()}/{create_report_file_name}')
+        chatbot.append((f"{fp}完成了吗？", res))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        # write html
+        try:
+            ch = construct_html()
+            orig = ""
+            trans = ""
+            gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
+            for i,k in enumerate(gpt_response_collection_html):
+                if i%2==0:
+                    gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
+                else:
+                    gpt_response_collection_html[i] = gpt_response_collection_html[i]
+            final = ["论文概况", paper_meta_info.replace('# ', '### '),  "二、论文翻译",  ""]
+            final.extend(gpt_response_collection_html)
+            for i, k in enumerate(final):
+                if i%2==0:
+                    orig = k
+                if i%2==1:
+                    trans = k
+                    ch.add_row(a=orig, b=trans)
+            create_report_file_name = f"{os.path.basename(fp)}.trans.html"
+            generated_html_files.append(ch.save_file(create_report_file_name))
+        except:
+            from toolbox import trimmed_format_exc
+            print('writing html result failed:', trimmed_format_exc())
+
+    # 准备文件的下载
+    for pdf_path in generated_conclusion_files:
+        # 重命名文件
+        rename_file = f'翻译-{os.path.basename(pdf_path)}'
+        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
+    for html_path in generated_html_files:
+        # 重命名文件
+        rename_file = f'翻译-{os.path.basename(html_path)}'
+        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
+    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+

crazy_functions/agent_fns/auto_agent.py

@@ -0,0 +1,23 @@
+from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
+from toolbox import report_exception, get_log_folder, update_ui_lastest_msg, Singleton
+from crazy_functions.agent_fns.pipe import PluginMultiprocessManager, PipeCom
+from crazy_functions.agent_fns.general import AutoGenGeneral
+
+
+
+class AutoGenMath(AutoGenGeneral):
+
+    def define_agents(self):
+        from autogen import AssistantAgent, UserProxyAgent
+        return [
+            {
+                "name": "assistant",            # name of the agent.
+                "cls":  AssistantAgent,         # class of the agent.
+            },
+            {
+                "name": "user_proxy",           # name of the agent.
+                "cls":  UserProxyAgent,         # class of the agent.
+                "human_input_mode": "ALWAYS",   # always ask for human input.
+                "llm_config": False,            # disables llm-based auto reply.
+            },
+        ]

crazy_functions/agent_fns/echo_agent.py

@@ -0,0 +1,19 @@
+from crazy_functions.agent_fns.pipe import PluginMultiprocessManager, PipeCom
+
+class EchoDemo(PluginMultiprocessManager):
+    def subprocess_worker(self, child_conn):
+        # ⭐⭐ 子进程
+        self.child_conn = child_conn
+        while True:
+            msg = self.child_conn.recv() # PipeCom
+            if msg.cmd == "user_input":
+                # wait futher user input
+                self.child_conn.send(PipeCom("show", msg.content))
+                wait_success = self.subprocess_worker_wait_user_feedback(wait_msg="我准备好处理下一个问题了.")
+                if not wait_success:
+                    # wait timeout, terminate this subprocess_worker
+                    break
+            elif msg.cmd == "terminate":
+                self.child_conn.send(PipeCom("done", ""))
+                break
+        print('[debug] subprocess_worker terminated')

crazy_functions/agent_fns/general.py

@@ -0,0 +1,138 @@
+from toolbox import trimmed_format_exc, get_conf, ProxyNetworkActivate
+from crazy_functions.agent_fns.pipe import PluginMultiprocessManager, PipeCom
+from request_llms.bridge_all import predict_no_ui_long_connection
+import time
+
+def gpt_academic_generate_oai_reply(
+    self,
+    messages,
+    sender,
+    config,
+):
+    llm_config = self.llm_config if config is None else config
+    if llm_config is False:
+        return False, None
+    if messages is None:
+        messages = self._oai_messages[sender]
+
+    inputs = messages[-1]['content']
+    history = []
+    for message in messages[:-1]:
+        history.append(message['content'])
+    context=messages[-1].pop("context", None)
+    assert context is None, "预留参数 context 未实现"
+
+    reply = predict_no_ui_long_connection(
+        inputs=inputs,
+        llm_kwargs=llm_config,
+        history=history,
+        sys_prompt=self._oai_system_message[0]['content'],
+        console_slience=True
+    )
+    assumed_done = reply.endswith('\nTERMINATE')
+    return True, reply
+
+class AutoGenGeneral(PluginMultiprocessManager):
+    def gpt_academic_print_override(self, user_proxy, message, sender):
+        # ⭐⭐ run in subprocess
+        try:
+            print_msg = sender.name + "\n\n---\n\n" + message["content"]
+        except:
+            print_msg = sender.name + "\n\n---\n\n" + message
+        self.child_conn.send(PipeCom("show", print_msg))
+
+    def gpt_academic_get_human_input(self, user_proxy, message):
+        # ⭐⭐ run in subprocess
+        patience = 300
+        begin_waiting_time = time.time()
+        self.child_conn.send(PipeCom("interact", message))
+        while True:
+            time.sleep(0.5)
+            if self.child_conn.poll():
+                wait_success = True
+                break
+            if time.time() - begin_waiting_time > patience:
+                self.child_conn.send(PipeCom("done", ""))
+                wait_success = False
+                break
+        if wait_success:
+            return self.child_conn.recv().content
+        else:
+            raise TimeoutError("等待用户输入超时")
+
+    def define_agents(self):
+        raise NotImplementedError
+
+    def exe_autogen(self, input):
+        # ⭐⭐ run in subprocess
+        input = input.content
+        code_execution_config = {"work_dir": self.autogen_work_dir, "use_docker": self.use_docker}
+        agents = self.define_agents()
+        user_proxy = None
+        assistant = None
+        for agent_kwargs in agents:
+            agent_cls = agent_kwargs.pop('cls')
+            kwargs = {
+                'llm_config':self.llm_kwargs,
+                'code_execution_config':code_execution_config
+            }
+            kwargs.update(agent_kwargs)
+            agent_handle = agent_cls(**kwargs)
+            agent_handle._print_received_message = lambda a,b: self.gpt_academic_print_override(agent_kwargs, a, b)
+            for d in agent_handle._reply_func_list:
+                if hasattr(d['reply_func'],'__name__') and d['reply_func'].__name__ == 'generate_oai_reply':
+                    d['reply_func'] = gpt_academic_generate_oai_reply
+            if agent_kwargs['name'] == 'user_proxy':
+                agent_handle.get_human_input = lambda a: self.gpt_academic_get_human_input(user_proxy, a)
+                user_proxy = agent_handle
+            if agent_kwargs['name'] == 'assistant': assistant = agent_handle
+        try:
+            if user_proxy is None or assistant is None: raise Exception("用户代理或助理代理未定义")
+            with ProxyNetworkActivate("AutoGen"):
+                user_proxy.initiate_chat(assistant, message=input)
+        except Exception as e:
+            tb_str = '```\n' + trimmed_format_exc() + '```'
+            self.child_conn.send(PipeCom("done", "AutoGen 执行失败: \n\n" + tb_str))
+
+    def subprocess_worker(self, child_conn):
+        # ⭐⭐ run in subprocess
+        self.child_conn = child_conn
+        while True:
+            msg = self.child_conn.recv()  # PipeCom
+            self.exe_autogen(msg)
+
+
+class AutoGenGroupChat(AutoGenGeneral):
+    def exe_autogen(self, input):
+        # ⭐⭐ run in subprocess
+        import autogen
+
+        input = input.content
+        with ProxyNetworkActivate("AutoGen"):
+            code_execution_config = {"work_dir": self.autogen_work_dir, "use_docker": self.use_docker}
+            agents = self.define_agents()
+            agents_instances = []
+            for agent_kwargs in agents:
+                agent_cls = agent_kwargs.pop("cls")
+                kwargs = {"code_execution_config": code_execution_config}
+                kwargs.update(agent_kwargs)
+                agent_handle = agent_cls(**kwargs)
+                agent_handle._print_received_message = lambda a, b: self.gpt_academic_print_override(agent_kwargs, a, b)
+                agents_instances.append(agent_handle)
+                if agent_kwargs["name"] == "user_proxy":
+                    user_proxy = agent_handle
+                    user_proxy.get_human_input = lambda a: self.gpt_academic_get_human_input(user_proxy, a)
+            try:
+                groupchat = autogen.GroupChat(agents=agents_instances, messages=[], max_round=50)
+                manager = autogen.GroupChatManager(groupchat=groupchat, **self.define_group_chat_manager_config())
+                manager._print_received_message = lambda a, b: self.gpt_academic_print_override(agent_kwargs, a, b)
+                manager.get_human_input = lambda a: self.gpt_academic_get_human_input(manager, a)
+                if user_proxy is None:
+                    raise Exception("user_proxy is not defined")
+                user_proxy.initiate_chat(manager, message=input)
+            except Exception:
+                tb_str = "```\n" + trimmed_format_exc() + "```"
+                self.child_conn.send(PipeCom("done", "AutoGen exe failed: \n\n" + tb_str))
+
+    def define_group_chat_manager_config(self):
+        raise NotImplementedError

crazy_functions/agent_fns/persistent.py

@@ -0,0 +1,16 @@
+from toolbox import Singleton
+@Singleton
+class GradioMultiuserManagerForPersistentClasses():
+    def __init__(self):
+        self.mapping = {}
+
+    def already_alive(self, key):
+        return (key in self.mapping) and (self.mapping[key].is_alive())
+
+    def set(self, key, x):
+        self.mapping[key] = x
+        return self.mapping[key]
+
+    def get(self, key):
+        return self.mapping[key]
+

crazy_functions/agent_fns/pipe.py

@@ -0,0 +1,194 @@
+from toolbox import get_log_folder, update_ui, gen_time_str, get_conf, promote_file_to_downloadzone
+from crazy_functions.agent_fns.watchdog import WatchDog
+import time, os
+
+class PipeCom:
+    def __init__(self, cmd, content) -> None:
+        self.cmd = cmd
+        self.content = content
+
+
+class PluginMultiprocessManager:
+    def __init__(self, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+        # ⭐ run in main process
+        self.autogen_work_dir = os.path.join(get_log_folder("autogen"), gen_time_str())
+        self.previous_work_dir_files = {}
+        self.llm_kwargs = llm_kwargs
+        self.plugin_kwargs = plugin_kwargs
+        self.chatbot = chatbot
+        self.history = history
+        self.system_prompt = system_prompt
+        # self.user_request = user_request
+        self.alive = True
+        self.use_docker = get_conf("AUTOGEN_USE_DOCKER")
+        self.last_user_input = ""
+        # create a thread to monitor self.heartbeat, terminate the instance if no heartbeat for a long time
+        timeout_seconds = 5 * 60
+        self.heartbeat_watchdog = WatchDog(timeout=timeout_seconds, bark_fn=self.terminate, interval=5)
+        self.heartbeat_watchdog.begin_watch()
+
+    def feed_heartbeat_watchdog(self):
+        # feed this `dog`, so the dog will not `bark` (bark_fn will terminate the instance)
+        self.heartbeat_watchdog.feed()
+
+    def is_alive(self):
+        return self.alive
+
+    def launch_subprocess_with_pipe(self):
+        # ⭐ run in main process
+        from multiprocessing import Process, Pipe
+
+        parent_conn, child_conn = Pipe()
+        self.p = Process(target=self.subprocess_worker, args=(child_conn,))
+        self.p.daemon = True
+        self.p.start()
+        return parent_conn
+
+    def terminate(self):
+        self.p.terminate()
+        self.alive = False
+        print("[debug] instance terminated")
+
+    def subprocess_worker(self, child_conn):
+        # ⭐⭐ run in subprocess
+        raise NotImplementedError
+
+    def send_command(self, cmd):
+        # ⭐ run in main process
+        repeated = False
+        if cmd == self.last_user_input:
+            repeated = True
+            cmd = ""
+        else:
+            self.last_user_input = cmd
+        self.parent_conn.send(PipeCom("user_input", cmd))
+        return repeated, cmd
+
+    def immediate_showoff_when_possible(self, fp):
+        # ⭐ 主进程
+        # 获取fp的拓展名
+        file_type = fp.split('.')[-1]
+        # 如果是文本文件, 则直接显示文本内容
+        if file_type.lower() in ['png', 'jpg']:
+            image_path = os.path.abspath(fp)
+            self.chatbot.append([
+                '检测到新生图像:',
+                f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
+            ])
+            yield from update_ui(chatbot=self.chatbot, history=self.history)
+
+    def overwatch_workdir_file_change(self):
+        # ⭐ 主进程 Docker 外挂文件夹监控
+        path_to_overwatch = self.autogen_work_dir
+        change_list = []
+        # 扫描路径下的所有文件, 并与self.previous_work_dir_files中所记录的文件进行对比，
+        # 如果有新文件出现，或者文件的修改时间发生变化，则更新self.previous_work_dir_files中
+        # 把新文件和发生变化的文件的路径记录到 change_list 中
+        for root, dirs, files in os.walk(path_to_overwatch):
+            for file in files:
+                file_path = os.path.join(root, file)
+                if file_path not in self.previous_work_dir_files.keys():
+                    last_modified_time = os.stat(file_path).st_mtime
+                    self.previous_work_dir_files.update({file_path: last_modified_time})
+                    change_list.append(file_path)
+                else:
+                    last_modified_time = os.stat(file_path).st_mtime
+                    if last_modified_time != self.previous_work_dir_files[file_path]:
+                        self.previous_work_dir_files[file_path] = last_modified_time
+                        change_list.append(file_path)
+        if len(change_list) > 0:
+            file_links = ""
+            for f in change_list:
+                res = promote_file_to_downloadzone(f)
+                file_links += f'<br/><a href="file={res}" target="_blank">{res}</a>'
+                yield from self.immediate_showoff_when_possible(f)
+
+            self.chatbot.append(['检测到新生文档.', f'文档清单如下: {file_links}'])
+            yield from update_ui(chatbot=self.chatbot, history=self.history)
+        return change_list
+
+
+    def main_process_ui_control(self, txt, create_or_resume) -> str:
+        # ⭐ 主进程
+        if create_or_resume == 'create':
+            self.cnt = 1
+            self.parent_conn = self.launch_subprocess_with_pipe() # ⭐⭐⭐
+        repeated, cmd_to_autogen = self.send_command(txt)
+        if txt == 'exit':
+            self.chatbot.append([f"结束", "结束信号已明确，终止AutoGen程序。"])
+            yield from update_ui(chatbot=self.chatbot, history=self.history)
+            self.terminate()
+            return "terminate"
+
+        # patience = 10
+
+        while True:
+            time.sleep(0.5)
+            if not self.alive:
+                # the heartbeat watchdog might have it killed
+                self.terminate()
+                return "terminate"
+            if self.parent_conn.poll():
+                self.feed_heartbeat_watchdog()
+                if "[GPT-Academic] 等待中" in self.chatbot[-1][-1]:
+                    self.chatbot.pop(-1)  # remove the last line
+                if "等待您的进一步指令" in self.chatbot[-1][-1]:
+                    self.chatbot.pop(-1)  # remove the last line
+                if '[GPT-Academic] 等待中' in self.chatbot[-1][-1]:
+                    self.chatbot.pop(-1)    # remove the last line
+                msg = self.parent_conn.recv() # PipeCom
+                if msg.cmd == "done":
+                    self.chatbot.append([f"结束", msg.content])
+                    self.cnt += 1
+                    yield from update_ui(chatbot=self.chatbot, history=self.history)
+                    self.terminate()
+                    break
+                if msg.cmd == "show":
+                    yield from self.overwatch_workdir_file_change()
+                    notice = ""
+                    if repeated: notice = "（自动忽略重复的输入）"
+                    self.chatbot.append([f"运行阶段-{self.cnt}（上次用户反馈输入为: 「{cmd_to_autogen}」{notice}", msg.content])
+                    self.cnt += 1
+                    yield from update_ui(chatbot=self.chatbot, history=self.history)
+                if msg.cmd == "interact":
+                    yield from self.overwatch_workdir_file_change()
+                    self.chatbot.append([f"程序抵达用户反馈节点.", msg.content +
+                                         "\n\n等待您的进一步指令." +
+                                         "\n\n(1) 一般情况下您不需要说什么, 清空输入区, 然后直接点击“提交”以继续. " +
+                                         "\n\n(2) 如果您需要补充些什么, 输入要反馈的内容, 直接点击“提交”以继续. " +
+                                         "\n\n(3) 如果您想终止程序, 输入exit, 直接点击“提交”以终止AutoGen并解锁. "
+                    ])
+                    yield from update_ui(chatbot=self.chatbot, history=self.history)
+                    # do not terminate here, leave the subprocess_worker instance alive
+                    return "wait_feedback"
+            else:
+                self.feed_heartbeat_watchdog()
+                if '[GPT-Academic] 等待中' not in self.chatbot[-1][-1]:
+                    # begin_waiting_time = time.time()
+                    self.chatbot.append(["[GPT-Academic] 等待AutoGen执行结果 ...", "[GPT-Academic] 等待中"])
+                self.chatbot[-1] = [self.chatbot[-1][0], self.chatbot[-1][1].replace("[GPT-Academic] 等待中", "[GPT-Academic] 等待中.")]
+                yield from update_ui(chatbot=self.chatbot, history=self.history)
+                # if time.time() - begin_waiting_time > patience:
+                #     self.chatbot.append([f"结束", "等待超时, 终止AutoGen程序。"])
+                #     yield from update_ui(chatbot=self.chatbot, history=self.history)
+                #     self.terminate()
+                #     return "terminate"
+
+        self.terminate()
+        return "terminate"
+
+    def subprocess_worker_wait_user_feedback(self, wait_msg="wait user feedback"):
+        # ⭐⭐ run in subprocess
+        patience = 5 * 60
+        begin_waiting_time = time.time()
+        self.child_conn.send(PipeCom("interact", wait_msg))
+        while True:
+            time.sleep(0.5)
+            if self.child_conn.poll():
+                wait_success = True
+                break
+            if time.time() - begin_waiting_time > patience:
+                self.child_conn.send(PipeCom("done", ""))
+                wait_success = False
+                break
+        return wait_success

crazy_functions/agent_fns/watchdog.py

@@ -0,0 +1,28 @@
+import threading, time
+
+class WatchDog():
+    def __init__(self, timeout, bark_fn, interval=3, msg="") -> None:
+        self.last_feed = None
+        self.timeout = timeout
+        self.bark_fn = bark_fn
+        self.interval = interval
+        self.msg = msg
+        self.kill_dog = False
+
+    def watch(self):
+        while True:
+            if self.kill_dog: break
+            if time.time() - self.last_feed > self.timeout:
+                if len(self.msg) > 0: print(self.msg)
+                self.bark_fn()
+                break
+            time.sleep(self.interval)
+
+    def begin_watch(self):
+        self.last_feed = time.time()
+        th = threading.Thread(target=self.watch)
+        th.daemon = True
+        th.start()
+
+    def feed(self):
+        self.last_feed = time.time()

crazy_functions/chatglm微调工具.py

@@ -32,7 +32,7 @@ def string_to_options(arguments):
     return args
 
 @CatchException
-def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -40,13 +40,13 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
     chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     args = plugin_kwargs.get("advanced_arg", None)
-    if args is None: 
+    if args is None:
         chatbot.append(("没给定指令", "退出"))
         yield from update_ui(chatbot=chatbot, history=history); return
     else:
@@ -69,7 +69,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             sys_prompt_array=[arguments.system_prompt for _ in (batch)],
             max_workers=10  # OpenAI所允许的最大并行过载
         )
-    
+
         with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
             for b, r in zip(batch, res[1::2]):
                 f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n')
@@ -80,7 +80,7 @@ def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
 
 @CatchException
-def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -88,19 +88,19 @@ def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     import subprocess
     history = []    # 清空历史，以免输入溢出
     chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     args = plugin_kwargs.get("advanced_arg", None)
-    if args is None: 
+    if args is None:
         chatbot.append(("没给定指令", "退出"))
         yield from update_ui(chatbot=chatbot, history=history); return
     else:
         arguments = string_to_options(arguments=args)
-      
+
 
 
     pre_seq_len = arguments.pre_seq_len             # 128

crazy_functions/crazy_utils.py

@@ -1,18 +1,18 @@
-from toolbox import update_ui, get_conf, trimmed_format_exc, get_log_folder
+from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
 import threading
 import os
 import logging
 
 def input_clipping(inputs, history, max_token_limit):
     import numpy as np
-    from request_llm.bridge_all import model_info
+    from request_llms.bridge_all import model_info
     enc = model_info["gpt-3.5-turbo"]['tokenizer']
     def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
 
     mode = 'input-and-history'
     # 当 输入部分的token占比 小于 全文的一半时，只裁剪历史
     input_token_num = get_token_num(inputs)
-    if input_token_num < max_token_limit//2: 
+    if input_token_num < max_token_limit//2:
         mode = 'only-history'
         max_token_limit = max_token_limit - input_token_num
 
@@ -21,7 +21,7 @@ def input_clipping(inputs, history, max_token_limit):
     n_token = get_token_num('\n'.join(everything))
     everything_token = [get_token_num(e) for e in everything]
     delta = max(everything_token) // 16 # 截断时的颗粒度
-        
+
     while n_token > max_token_limit:
         where = np.argmax(everything_token)
         encoded = enc.encode(everything[where], disallowed_special=())
@@ -38,9 +38,9 @@ def input_clipping(inputs, history, max_token_limit):
     return inputs, history
 
 def request_gpt_model_in_new_thread_with_ui_alive(
-        inputs, inputs_show_user, llm_kwargs, 
+        inputs, inputs_show_user, llm_kwargs,
         chatbot, history, sys_prompt, refresh_interval=0.2,
-        handle_token_exceed=True, 
+        handle_token_exceed=True,
         retry_times_at_unknown_error=2,
         ):
     """
@@ -63,18 +63,21 @@ def request_gpt_model_in_new_thread_with_ui_alive(
     """
     import time
     from concurrent.futures import ThreadPoolExecutor
-    from request_llm.bridge_all import predict_no_ui_long_connection
+    from request_llms.bridge_all import predict_no_ui_long_connection
     # 用户反馈
     chatbot.append([inputs_show_user, ""])
     yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
     executor = ThreadPoolExecutor(max_workers=16)
     mutable = ["", time.time(), ""]
+    # 看门狗耐心
+    watch_dog_patience = 5
+    # 请求任务
     def _req_gpt(inputs, history, sys_prompt):
         retry_op = retry_times_at_unknown_error
         exceeded_cnt = 0
         while True:
             # watchdog error
-            if len(mutable) >= 2 and (time.time()-mutable[1]) > 5: 
+            if len(mutable) >= 2 and (time.time()-mutable[1]) > watch_dog_patience:
                 raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
@@ -89,7 +92,7 @@ def request_gpt_model_in_new_thread_with_ui_alive(
                     # 【选择处理】 尝试计算比例，尽可能多地保留文本
                     from toolbox import get_reduce_token_percent
                     p_ratio, n_exceed = get_reduce_token_percent(str(token_exceeded_error))
-                    MAX_TOKEN = 4096
+                    MAX_TOKEN = get_max_token(llm_kwargs)
                     EXCEED_ALLO = 512 + 512 * exceeded_cnt
                     inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN-EXCEED_ALLO)
                     mutable[0] += f'[Local Message] 警告，文本过长将进行截断，Token溢出数：{n_exceed}。\n\n'
@@ -132,15 +135,29 @@ def request_gpt_model_in_new_thread_with_ui_alive(
     yield from update_ui(chatbot=chatbot, history=[]) # 如果最后成功了，则删除报错信息
     return final_result
 
-def can_multi_process(llm):
-    if llm.startswith('gpt-'): return True
-    if llm.startswith('api2d-'): return True
-    if llm.startswith('azure-'): return True
-    return False
+def can_multi_process(llm) -> bool:
+    from request_llms.bridge_all import model_info
+
+    def default_condition(llm) -> bool:
+        # legacy condition
+        if llm.startswith('gpt-'): return True
+        if llm.startswith('api2d-'): return True
+        if llm.startswith('azure-'): return True
+        if llm.startswith('spark'): return True
+        if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
+        return False
+
+    if llm in model_info:
+        if 'can_multi_thread' in model_info[llm]:
+            return model_info[llm]['can_multi_thread']
+        else:
+            return default_condition(llm)
+    else:
+        return default_condition(llm)
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-        inputs_array, inputs_show_user_array, llm_kwargs, 
-        chatbot, history_array, sys_prompt_array, 
+        inputs_array, inputs_show_user_array, llm_kwargs,
+        chatbot, history_array, sys_prompt_array,
         refresh_interval=0.2, max_workers=-1, scroller_max_len=30,
         handle_token_exceed=True, show_user_at_complete=False,
         retry_times_at_unknown_error=2,
@@ -174,17 +191,17 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     """
     import time, random
     from concurrent.futures import ThreadPoolExecutor
-    from request_llm.bridge_all import predict_no_ui_long_connection
+    from request_llms.bridge_all import predict_no_ui_long_connection
     assert len(inputs_array) == len(history_array)
     assert len(inputs_array) == len(sys_prompt_array)
     if max_workers == -1: # 读取配置文件
-        try: max_workers, = get_conf('DEFAULT_WORKER_NUM')
+        try: max_workers = get_conf('DEFAULT_WORKER_NUM')
         except: max_workers = 8
         if max_workers <= 0: max_workers = 3
     # 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
     if not can_multi_process(llm_kwargs['llm_model']):
         max_workers = 1
-        
+
     executor = ThreadPoolExecutor(max_workers=max_workers)
     n_frag = len(inputs_array)
     # 用户反馈
@@ -193,33 +210,35 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     # 跨线程传递
     mutable = [["", time.time(), "等待中"] for _ in range(n_frag)]
 
+    # 看门狗耐心
+    watch_dog_patience = 5
+
     # 子线程任务
     def _req_gpt(index, inputs, history, sys_prompt):
         gpt_say = ""
         retry_op = retry_times_at_unknown_error
         exceeded_cnt = 0
         mutable[index][2] = "执行中"
+        detect_timeout = lambda: len(mutable[index]) >= 2 and (time.time()-mutable[index][1]) > watch_dog_patience
         while True:
             # watchdog error
-            if len(mutable[index]) >= 2 and (time.time()-mutable[index][1]) > 5: 
-                raise RuntimeError("检测到程序终止。")
+            if detect_timeout(): raise RuntimeError("检测到程序终止。")
             try:
                 # 【第一种情况】：顺利完成
-                # time.sleep(10); raise RuntimeError("测试")
                 gpt_say = predict_no_ui_long_connection(
-                    inputs=inputs, llm_kwargs=llm_kwargs, history=history, 
+                    inputs=inputs, llm_kwargs=llm_kwargs, history=history,
                     sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
                 )
                 mutable[index][2] = "已成功"
                 return gpt_say
             except ConnectionAbortedError as token_exceeded_error:
-                # 【第二种情况】：Token溢出，
+                # 【第二种情况】：Token溢出
                 if handle_token_exceed:
                     exceeded_cnt += 1
                     # 【选择处理】 尝试计算比例，尽可能多地保留文本
                     from toolbox import get_reduce_token_percent
                     p_ratio, n_exceed = get_reduce_token_percent(str(token_exceeded_error))
-                    MAX_TOKEN = 4096
+                    MAX_TOKEN = get_max_token(llm_kwargs)
                     EXCEED_ALLO = 512 + 512 * exceeded_cnt
                     inputs, history = input_clipping(inputs, history, max_token_limit=MAX_TOKEN-EXCEED_ALLO)
                     gpt_say += f'[Local Message] 警告，文本过长将进行截断，Token溢出数：{n_exceed}。\n\n'
@@ -234,11 +253,12 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     return gpt_say # 放弃
             except:
                 # 【第三种情况】：其他错误
+                if detect_timeout(): raise RuntimeError("检测到程序终止。")
                 tb_str = '```\n' + trimmed_format_exc() + '```'
                 print(tb_str)
                 gpt_say += f"[Local Message] 警告，线程{index}在执行过程中遭遇问题, Traceback：\n\n{tb_str}\n\n"
                 if len(mutable[index][0]) > 0: gpt_say += "此线程失败前收到的回答：\n\n" + mutable[index][0]
-                if retry_op > 0: 
+                if retry_op > 0:
                     retry_op -= 1
                     wait = random.randint(5, 20)
                     if ("Rate limit reached" in tb_str) or ("Too Many Requests" in tb_str):
@@ -250,6 +270,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     for i in range(wait):
                         mutable[index][2] = f"{fail_info}等待重试 {wait-i}"; time.sleep(1)
                     # 开始重试
+                    if detect_timeout(): raise RuntimeError("检测到程序终止。")
                     mutable[index][2] = f"重试中 {retry_times_at_unknown_error-retry_op}/{retry_times_at_unknown_error}"
                     continue # 返回重试
                 else:
@@ -275,12 +296,11 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         # 在前端打印些好玩的东西
         for thread_index, _ in enumerate(worker_done):
             print_something_really_funny = "[ ...`"+mutable[thread_index][0][-scroller_max_len:].\
-                replace('\n', '').replace('```', '...').replace(
-                    ' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
+                replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
             observe_win.append(print_something_really_funny)
         # 在前端打印些好玩的东西
-        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n' 
-                            if not done else f'`{mutable[thread_index][2]}`\n\n' 
+        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
+                            if not done else f'`{mutable[thread_index][2]}`\n\n'
                             for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
         # 在前端打印些好玩的东西
         chatbot[-1] = [chatbot[-1][0], f'多线程操作已经开始，完成情况: \n\n{stat_str}' + ''.join(['.']*(cnt % 10+1))]
@@ -294,106 +314,17 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
     for inputs_show_user, f in zip(inputs_show_user_array, futures):
         gpt_res = f.result()
         gpt_response_collection.extend([inputs_show_user, gpt_res])
-    
+
     # 是否在结束时，在界面上显示结果
     if show_user_at_complete:
         for inputs_show_user, f in zip(inputs_show_user_array, futures):
             gpt_res = f.result()
             chatbot.append([inputs_show_user, gpt_res])
             yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
-            time.sleep(0.3)
+            time.sleep(0.5)
     return gpt_response_collection
 
 
-def breakdown_txt_to_satisfy_token_limit(txt, get_token_fn, limit):
-    def cut(txt_tocut, must_break_at_empty_line):  # 递归
-        if get_token_fn(txt_tocut) <= limit:
-            return [txt_tocut]
-        else:
-            lines = txt_tocut.split('\n')
-            estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
-            estimated_line_cut = int(estimated_line_cut)
-            for cnt in reversed(range(estimated_line_cut)):
-                if must_break_at_empty_line:
-                    if lines[cnt] != "":
-                        continue
-                print(cnt)
-                prev = "\n".join(lines[:cnt])
-                post = "\n".join(lines[cnt:])
-                if get_token_fn(prev) < limit:
-                    break
-            if cnt == 0:
-                raise RuntimeError("存在一行极长的文本！")
-            # print(len(post))
-            # 列表递归接龙
-            result = [prev]
-            result.extend(cut(post, must_break_at_empty_line))
-            return result
-    try:
-        return cut(txt, must_break_at_empty_line=True)
-    except RuntimeError:
-        return cut(txt, must_break_at_empty_line=False)
-
-
-def force_breakdown(txt, limit, get_token_fn):
-    """
-    当无法用标点、空行分割时，我们用最暴力的方法切割
-    """
-    for i in reversed(range(len(txt))):
-        if get_token_fn(txt[:i]) < limit:
-            return txt[:i], txt[i:]
-    return "Tiktoken未知错误", "Tiktoken未知错误"
-
-def breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn, limit):
-    # 递归
-    def cut(txt_tocut, must_break_at_empty_line, break_anyway=False):  
-        if get_token_fn(txt_tocut) <= limit:
-            return [txt_tocut]
-        else:
-            lines = txt_tocut.split('\n')
-            estimated_line_cut = limit / get_token_fn(txt_tocut) * len(lines)
-            estimated_line_cut = int(estimated_line_cut)
-            cnt = 0
-            for cnt in reversed(range(estimated_line_cut)):
-                if must_break_at_empty_line:
-                    if lines[cnt] != "":
-                        continue
-                prev = "\n".join(lines[:cnt])
-                post = "\n".join(lines[cnt:])
-                if get_token_fn(prev) < limit:
-                    break
-            if cnt == 0:
-                if break_anyway:
-                    prev, post = force_breakdown(txt_tocut, limit, get_token_fn)
-                else:
-                    raise RuntimeError(f"存在一行极长的文本！{txt_tocut}")
-            # print(len(post))
-            # 列表递归接龙
-            result = [prev]
-            result.extend(cut(post, must_break_at_empty_line, break_anyway=break_anyway))
-            return result
-    try:
-        # 第1次尝试，将双空行（\n\n）作为切分点
-        return cut(txt, must_break_at_empty_line=True)
-    except RuntimeError:
-        try:
-            # 第2次尝试，将单空行（\n）作为切分点
-            return cut(txt, must_break_at_empty_line=False)
-        except RuntimeError:
-            try:
-                # 第3次尝试，将英文句号（.）作为切分点
-                res = cut(txt.replace('.', '。\n'), must_break_at_empty_line=False) # 这个中文的句号是故意的，作为一个标识而存在
-                return [r.replace('。\n', '.') for r in res]
-            except RuntimeError as e:
-                try:
-                    # 第4次尝试，将中文句号（。）作为切分点
-                    res = cut(txt.replace('。', '。。\n'), must_break_at_empty_line=False)
-                    return [r.replace('。。\n', '。') for r in res]
-                except RuntimeError as e:
-                    # 第5次尝试，没办法了，随便切一下敷衍吧
-                    return cut(txt, must_break_at_empty_line=False, break_anyway=True)
-
-
 
 def read_and_clean_pdf_text(fp):
     """
@@ -433,7 +364,7 @@ def read_and_clean_pdf_text(fp):
             if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
             fsize_statiscs[wtf['size']] += len(wtf['text'])
         return max(fsize_statiscs, key=fsize_statiscs.get)
-        
+
     def ffsize_same(a,b):
         """
         提取字体大小是否近似相等
@@ -469,7 +400,7 @@ def read_and_clean_pdf_text(fp):
             if index == 0:
                 page_one_meta = [" ".join(["".join([wtf['text'] for wtf in l['spans']]) for l in t['lines']]).replace(
                     '- ', '') for t in text_areas['blocks'] if 'lines' in t]
-                
+
         ############################## <第 2 步，获取正文主字体> ##################################
         try:
             fsize_statiscs = {}
@@ -485,7 +416,7 @@ def read_and_clean_pdf_text(fp):
         mega_sec = []
         sec = []
         for index, line in enumerate(meta_line):
-            if index == 0: 
+            if index == 0:
                 sec.append(line[fc])
                 continue
             if REMOVE_FOOT_NOTE:
@@ -546,6 +477,9 @@ def read_and_clean_pdf_text(fp):
                     return True
                 else:
                     return False
+            # 对于某些PDF会有第一个段落就以小写字母开头,为了避免索引错误将其更改为大写
+            if starts_with_lowercase_word(meta_txt[0]):
+                meta_txt[0] = meta_txt[0].capitalize()
             for _ in range(100):
                 for index, block_txt in enumerate(meta_txt):
                     if starts_with_lowercase_word(block_txt):
@@ -579,12 +513,12 @@ def get_files_from_everything(txt, type): # type='.md'
     """
     这个函数是用来获取指定目录下所有指定类型（如.md）的文件，并且对于网络上的文件，也可以获取它。
     下面是对每个参数和返回值的说明：
-    参数 
-    - txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。 
+    参数
+    - txt: 路径或网址，表示要搜索的文件或者文件夹路径或网络上的文件。
     - type: 字符串，表示要搜索的文件类型。默认是.md。
-    返回值 
-    - success: 布尔值，表示函数是否成功执行。 
-    - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。 
+    返回值
+    - success: 布尔值，表示函数是否成功执行。
+    - file_manifest: 文件路径列表，里面包含以指定类型为后缀名的所有文件的绝对路径。
     - project_folder: 字符串，表示文件所在的文件夹路径。如果是网络上的文件，就是临时文件夹的路径。
     该函数详细注释已添加，请确认是否满足您的需要。
     """
@@ -596,7 +530,7 @@ def get_files_from_everything(txt, type): # type='.md'
         import requests
         from toolbox import get_conf
         from toolbox import get_log_folder, gen_time_str
-        proxies, = get_conf('proxies')
+        proxies = get_conf('proxies')
         try:
             r = requests.get(txt, proxies=proxies)
         except:
@@ -624,90 +558,6 @@ def get_files_from_everything(txt, type): # type='.md'
 
 
 
-
-def Singleton(cls):
-    _instance = {}
- 
-    def _singleton(*args, **kargs):
-        if cls not in _instance:
-            _instance[cls] = cls(*args, **kargs)
-        return _instance[cls]
- 
-    return _singleton
-
-
-@Singleton
-class knowledge_archive_interface():
-    def __init__(self) -> None:
-        self.threadLock = threading.Lock()
-        self.current_id = ""
-        self.kai_path = None
-        self.qa_handle = None
-        self.text2vec_large_chinese = None
-
-    def get_chinese_text2vec(self):
-        if self.text2vec_large_chinese is None:
-            # < -------------------预热文本向量化模组--------------- >
-            from toolbox import ProxyNetworkActivate
-            print('Checking Text2vec ...')
-            from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-            with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
-                self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
-
-        return self.text2vec_large_chinese
-
-
-    def feed_archive(self, file_manifest, id="default"):
-        self.threadLock.acquire()
-        # import uuid
-        self.current_id = id
-        from zh_langchain import construct_vector_store
-        self.qa_handle, self.kai_path = construct_vector_store(   
-            vs_id=self.current_id, 
-            files=file_manifest, 
-            sentence_size=100,
-            history=[],
-            one_conent="",
-            one_content_segmentation="",
-            text2vec = self.get_chinese_text2vec(),
-        )
-        self.threadLock.release()
-
-    def get_current_archive_id(self):
-        return self.current_id
-    
-    def get_loaded_file(self):
-        return self.qa_handle.get_loaded_file()
-
-    def answer_with_archive_by_id(self, txt, id):
-        self.threadLock.acquire()
-        if not self.current_id == id:
-            self.current_id = id
-            from zh_langchain import construct_vector_store
-            self.qa_handle, self.kai_path = construct_vector_store(   
-                vs_id=self.current_id, 
-                files=[], 
-                sentence_size=100,
-                history=[],
-                one_conent="",
-                one_content_segmentation="",
-                text2vec = self.get_chinese_text2vec(),
-            )
-        VECTOR_SEARCH_SCORE_THRESHOLD = 0
-        VECTOR_SEARCH_TOP_K = 4
-        CHUNK_SIZE = 512
-        resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
-            query = txt,
-            vs_path = self.kai_path,
-            score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
-            vector_search_top_k=VECTOR_SEARCH_TOP_K, 
-            chunk_conent=True,
-            chunk_size=CHUNK_SIZE,
-            text2vec = self.get_chinese_text2vec(),
-        )
-        self.threadLock.release()
-        return resp, prompt
-    
 @Singleton
 class nougat_interface():
     def __init__(self):
@@ -715,8 +565,10 @@ class nougat_interface():
 
     def nougat_with_timeout(self, command, cwd, timeout=3600):
         import subprocess
+        from toolbox import ProxyNetworkActivate
         logging.info(f'正在执行命令 {command}')
-        process = subprocess.Popen(command, shell=True, cwd=cwd)
+        with ProxyNetworkActivate("Nougat_Download"):
+            process = subprocess.Popen(command, shell=False, cwd=cwd, env=os.environ)
         try:
             stdout, stderr = process.communicate(timeout=timeout)
         except subprocess.TimeoutExpired:
@@ -730,7 +582,7 @@ class nougat_interface():
     def NOUGAT_parse_pdf(self, fp, chatbot, history):
         from toolbox import update_ui_lastest_msg
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...", 
+        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
                                          chatbot=chatbot, history=history, delay=0)
         self.threadLock.acquire()
         import glob, threading, os
@@ -738,9 +590,10 @@ class nougat_interface():
         dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
         os.makedirs(dst)
 
-        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）", 
+        yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
                                          chatbot=chatbot, history=history, delay=0)
-        self.nougat_with_timeout(f'nougat --out "{os.path.abspath(dst)}" "{os.path.abspath(fp)}"', os.getcwd(), timeout=3600)
+        command = ['nougat', '--out', os.path.abspath(dst), os.path.abspath(fp)]
+        self.nougat_with_timeout(command, cwd=os.getcwd(), timeout=3600)
         res = glob.glob(os.path.join(dst,'*.mmd'))
         if len(res) == 0:
             self.threadLock.release()
@@ -761,54 +614,6 @@ def try_install_deps(deps, reload_m=[]):
         importlib.reload(__import__(m))
 
 
-HTML_CSS = """
-.row {
-  display: flex;
-  flex-wrap: wrap;
-}
-.column {
-  flex: 1;
-  padding: 10px;
-}
-.table-header {
-  font-weight: bold;
-  border-bottom: 1px solid black;
-}
-.table-row {
-  border-bottom: 1px solid lightgray;
-}
-.table-cell {
-  padding: 5px;
-}
-"""
-
-TABLE_CSS = """
-<div class="row table-row">
-    <div class="column table-cell">REPLACE_A</div>
-    <div class="column table-cell">REPLACE_B</div>
-</div>
-"""
-
-class construct_html():
-    def __init__(self) -> None:
-        self.css = HTML_CSS
-        self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
-
-
-    def add_row(self, a, b):
-        tmp = TABLE_CSS
-        from toolbox import markdown_convertion
-        tmp = tmp.replace('REPLACE_A', markdown_convertion(a))
-        tmp = tmp.replace('REPLACE_B', markdown_convertion(b))
-        self.html_string += tmp
-
-
-    def save_file(self, file_name):
-        with open(os.path.join(get_log_folder(), file_name), 'w', encoding='utf8') as f:
-            f.write(self.html_string.encode('utf-8', 'ignore').decode())
-        return os.path.join(get_log_folder(), file_name)
-
-
 def get_plugin_arg(plugin_kwargs, key, default):
     # 如果参数是空的
     if (key in plugin_kwargs) and (plugin_kwargs[key] == ""): plugin_kwargs.pop(key)

crazy_functions/diagram_fns/file_tree.py

@@ -0,0 +1,122 @@
+import os
+from textwrap import indent
+
+class FileNode:
+    def __init__(self, name):
+        self.name = name
+        self.children = []
+        self.is_leaf = False
+        self.level = 0
+        self.parenting_ship = []
+        self.comment = ""
+        self.comment_maxlen_show = 50
+
+    @staticmethod
+    def add_linebreaks_at_spaces(string, interval=10):
+        return '\n'.join(string[i:i+interval] for i in range(0, len(string), interval))
+
+    def sanitize_comment(self, comment):
+        if len(comment) > self.comment_maxlen_show: suf = '...'
+        else: suf = ''
+        comment = comment[:self.comment_maxlen_show]
+        comment = comment.replace('\"', '').replace('`', '').replace('\n', '').replace('`', '').replace('$', '')
+        comment = self.add_linebreaks_at_spaces(comment, 10)
+        return '`' + comment + suf + '`'
+
+    def add_file(self, file_path, file_comment):
+        directory_names, file_name = os.path.split(file_path)
+        current_node = self
+        level = 1
+        if directory_names == "":
+            new_node = FileNode(file_name)
+            current_node.children.append(new_node)
+            new_node.is_leaf = True
+            new_node.comment = self.sanitize_comment(file_comment)
+            new_node.level = level
+            current_node = new_node
+        else:
+            dnamesplit = directory_names.split(os.sep)
+            for i, directory_name in enumerate(dnamesplit):
+                found_child = False
+                level += 1
+                for child in current_node.children:
+                    if child.name == directory_name:
+                        current_node = child
+                        found_child = True
+                        break
+                if not found_child:
+                    new_node = FileNode(directory_name)
+                    current_node.children.append(new_node)
+                    new_node.level = level - 1
+                    current_node = new_node
+            term = FileNode(file_name)
+            term.level = level
+            term.comment = self.sanitize_comment(file_comment)
+            term.is_leaf = True
+            current_node.children.append(term)
+
+    def print_files_recursively(self, level=0, code="R0"):
+        print('    '*level + self.name + ' ' + str(self.is_leaf) + ' ' + str(self.level))
+        for j, child in enumerate(self.children):
+            child.print_files_recursively(level=level+1, code=code+str(j))
+            self.parenting_ship.extend(child.parenting_ship)
+            p1 = f"""{code}[\"🗎{self.name}\"]""" if self.is_leaf else f"""{code}[[\"📁{self.name}\"]]"""
+            p2 = """ --> """
+            p3 = f"""{code+str(j)}[\"🗎{child.name}\"]""" if child.is_leaf else f"""{code+str(j)}[[\"📁{child.name}\"]]"""
+            edge_code = p1 + p2 + p3
+            if edge_code in self.parenting_ship:
+                continue
+            self.parenting_ship.append(edge_code)
+        if self.comment != "":
+            pc1 = f"""{code}[\"🗎{self.name}\"]""" if self.is_leaf else f"""{code}[[\"📁{self.name}\"]]"""
+            pc2 = f""" -.-x """
+            pc3 = f"""C{code}[\"{self.comment}\"]:::Comment"""
+            edge_code = pc1 + pc2 + pc3
+            self.parenting_ship.append(edge_code)
+
+
+MERMAID_TEMPLATE = r"""
+```mermaid
+flowchart LR
+    %% <gpt_academic_hide_mermaid_code> 一个特殊标记，用于在生成mermaid图表时隐藏代码块
+    classDef Comment stroke-dasharray: 5 5
+    subgraph {graph_name}
+{relationship}
+    end
+```
+"""
+
+def build_file_tree_mermaid_diagram(file_manifest, file_comments, graph_name):
+    # Create the root node
+    file_tree_struct = FileNode("root")
+    # Build the tree structure
+    for file_path, file_comment in zip(file_manifest, file_comments):
+        file_tree_struct.add_file(file_path, file_comment)
+    file_tree_struct.print_files_recursively()
+    cc = "\n".join(file_tree_struct.parenting_ship)
+    ccc = indent(cc, prefix=" "*8)
+    return MERMAID_TEMPLATE.format(graph_name=graph_name, relationship=ccc)
+
+if __name__ == "__main__":
+    # File manifest
+    file_manifest = [
+        "cradle_void_terminal.ipynb",
+        "tests/test_utils.py",
+        "tests/test_plugins.py",
+        "tests/test_llms.py",
+        "config.py",
+        "build/ChatGLM-6b-onnx-u8s8/chatglm-6b-int8-onnx-merged/model_weights_0.bin",
+        "crazy_functions/latex_fns/latex_actions.py",
+        "crazy_functions/latex_fns/latex_toolbox.py"
+    ]
+    file_comments = [
+        "根据位置和名称，可能是一个模块的初始化文件根据位置和名称，可能是一个模块的初始化文件根据位置和名称，可能是一个模块的初始化文件",
+        "包含一些用于文本处理和模型微调的函数和装饰器包含一些用于文本处理和模型微调的函数和装饰器包含一些用于文本处理和模型微调的函数和装饰器",
+        "用于构建HTML报告的类和方法用于构建HTML报告的类和方法用于构建HTML报告的类和方法",
+        "包含了用于文本切分的函数，以及处理PDF文件的示例代码包含了用于文本切分的函数，以及处理PDF文件的示例代码包含了用于文本切分的函数，以及处理PDF文件的示例代码",
+        "用于解析和翻译PDF文件的功能和相关辅助函数用于解析和翻译PDF文件的功能和相关辅助函数用于解析和翻译PDF文件的功能和相关辅助函数",
+        "是一个包的初始化文件，用于初始化包的属性和导入模块是一个包的初始化文件，用于初始化包的属性和导入模块是一个包的初始化文件，用于初始化包的属性和导入模块",
+        "用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器用于加载和分割文件中的文本的通用文件加载器",
+        "包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类包含了用于构建和管理向量数据库的函数和类",
+    ]
+    print(build_file_tree_mermaid_diagram(file_manifest, file_comments, "项目文件树"))

crazy_functions/game_fns/game_ascii_art.py

@@ -0,0 +1,42 @@
+from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
+import random
+
+
+class MiniGame_ASCII_Art(GptAcademicGameBaseState):
+    def step(self, prompt, chatbot, history):
+        if self.step_cnt == 0:
+            chatbot.append(["我画你猜（动物）", "请稍等..."])
+        else:
+            if prompt.strip() == 'exit':
+                self.delete_game = True
+                yield from update_ui_lastest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
+                return
+            chatbot.append([prompt, ""])
+        yield from update_ui(chatbot=chatbot, history=history)
+
+        if self.step_cnt == 0:
+            self.lock_plugin(chatbot)
+            self.cur_task = 'draw'
+
+        if self.cur_task == 'draw':
+            avail_obj = ["狗","猫","鸟","鱼","老鼠","蛇"]
+            self.obj = random.choice(avail_obj)
+            inputs = "I want to play a game called Guess the ASCII art. You can draw the ASCII art and I will try to guess it. " + \
+                f"This time you draw a {self.obj}. Note that you must not indicate what you have draw in the text, and you should only produce the ASCII art wrapped by ```. "
+            raw_res = predict_no_ui_long_connection(inputs=inputs, llm_kwargs=self.llm_kwargs, history=[], sys_prompt="")
+            self.cur_task = 'identify user guess'
+            res = get_code_block(raw_res)
+            history += ['', f'the answer is {self.obj}', inputs, res]
+            yield from update_ui_lastest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
+
+        elif self.cur_task == 'identify user guess':
+            if is_same_thing(self.obj, prompt, self.llm_kwargs):
+                self.delete_game = True
+                yield from update_ui_lastest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
+            else:
+                self.cur_task = 'identify user guess'
+                yield from update_ui_lastest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)

crazy_functions/game_fns/game_interactive_story.py

@@ -0,0 +1,212 @@
+prompts_hs = """ 请以“{headstart}”为开头，编写一个小说的第一幕。
+
+- 尽量短，不要包含太多情节，因为你接下来将会与用户互动续写下面的情节，要留出足够的互动空间。
+- 出现人物时，给出人物的名字。
+- 积极地运用环境描写、人物描写等手法，让读者能够感受到你的故事世界。
+- 积极地运用修辞手法，比如比喻、拟人、排比、对偶、夸张等等。
+- 字数要求：第一幕的字数少于300字，且少于2个段落。
+"""
+
+prompts_interact = """ 小说的前文回顾：
+「
+{previously_on_story}
+」
+
+你是一个作家，根据以上的情节，给出4种不同的后续剧情发展方向，每个发展方向都精明扼要地用一句话说明。稍后，我将在这4个选择中，挑选一种剧情发展。
+
+输出格式例如：
+1. 后续剧情发展1
+2. 后续剧情发展2
+3. 后续剧情发展3
+4. 后续剧情发展4
+"""
+
+
+prompts_resume = """小说的前文回顾：
+「
+{previously_on_story}
+」
+
+你是一个作家，我们正在互相讨论，确定后续剧情的发展。
+在以下的剧情发展中，
+「
+{choice}
+」
+我认为更合理的是：{user_choice}。
+请在前文的基础上（不要重复前文），围绕我选定的剧情情节，编写小说的下一幕。
+
+- 禁止杜撰不符合我选择的剧情。
+- 尽量短，不要包含太多情节，因为你接下来将会与用户互动续写下面的情节，要留出足够的互动空间。
+- 不要重复前文。
+- 出现人物时，给出人物的名字。
+- 积极地运用环境描写、人物描写等手法，让读者能够感受到你的故事世界。
+- 积极地运用修辞手法，比如比喻、拟人、排比、对偶、夸张等等。
+- 小说的下一幕字数少于300字，且少于2个段落。
+"""
+
+
+prompts_terminate = """小说的前文回顾：
+「
+{previously_on_story}
+」
+
+你是一个作家，我们正在互相讨论，确定后续剧情的发展。
+现在，故事该结束了，我认为最合理的故事结局是：{user_choice}。
+
+请在前文的基础上（不要重复前文），编写小说的最后一幕。
+
+- 不要重复前文。
+- 出现人物时，给出人物的名字。
+- 积极地运用环境描写、人物描写等手法，让读者能够感受到你的故事世界。
+- 积极地运用修辞手法，比如比喻、拟人、排比、对偶、夸张等等。
+- 字数要求：最后一幕的字数少于1000字。
+"""
+
+
+from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
+import random
+
+
+class MiniGame_ResumeStory(GptAcademicGameBaseState):
+    story_headstart = [
+        '先行者知道，他现在是全宇宙中唯一的一个人了。',
+        '深夜，一个年轻人穿过天安门广场向纪念堂走去。在二十二世纪编年史中，计算机把他的代号定为M102。',
+        '他知道，这最后一课要提前讲了。又一阵剧痛从肝部袭来，几乎使他晕厥过去。',
+        '在距地球五万光年的远方，在银河系的中心，一场延续了两万年的星际战争已接近尾声。那里的太空中渐渐隐现出一个方形区域，仿佛灿烂的群星的背景被剪出一个方口。',
+        '伊依一行三人乘坐一艘游艇在南太平洋上做吟诗航行，他们的目的地是南极，如果几天后能顺利到达那里，他们将钻出地壳去看诗云。',
+        '很多人生来就会莫名其妙地迷上一样东西，仿佛他的出生就是要和这东西约会似的，正是这样，圆圆迷上了肥皂泡。'
+    ]
+
+
+    def begin_game_step_0(self, prompt, chatbot, history):
+        # init game at step 0
+        self.headstart = random.choice(self.story_headstart)
+        self.story = []
+        chatbot.append(["互动写故事", f"这次的故事开头是：{self.headstart}"])
+        self.sys_prompt_ = '你是一个想象力丰富的杰出作家。正在与你的朋友互动，一起写故事，因此你每次写的故事段落应少于300字（结局除外）。'
+
+
+    def generate_story_image(self, story_paragraph):
+        try:
+            from crazy_functions.图片生成 import gen_image
+            prompt_ = predict_no_ui_long_connection(inputs=story_paragraph, llm_kwargs=self.llm_kwargs, history=[], sys_prompt='你需要根据用户给出的小说段落，进行简短的环境描写。要求：80字以内。')
+            image_url, image_path = gen_image(self.llm_kwargs, prompt_, '512x512', model="dall-e-2", quality='standard', style='natural')
+            return f'<br/><div align="center"><img src="file={image_path}"></div>'
+        except:
+            return ''
+
+    def step(self, prompt, chatbot, history):
+
+        """
+        首先，处理游戏初始化等特殊情况
+        """
+        if self.step_cnt == 0:
+            self.begin_game_step_0(prompt, chatbot, history)
+            self.lock_plugin(chatbot)
+            self.cur_task = 'head_start'
+        else:
+            if prompt.strip() == 'exit' or prompt.strip() == '结束剧情':
+                # should we terminate game here?
+                self.delete_game = True
+                yield from update_ui_lastest_msg(lastmsg=f"游戏结束。", chatbot=chatbot, history=history, delay=0.)
+                return
+            if '剧情收尾' in prompt:
+                self.cur_task = 'story_terminate'
+            # # well, game resumes
+            # chatbot.append([prompt, ""])
+        # update ui, don't keep the user waiting
+        yield from update_ui(chatbot=chatbot, history=history)
+
+
+        """
+        处理游戏的主体逻辑
+        """
+        if self.cur_task == 'head_start':
+            """
+            这是游戏的第一步
+            """
+            inputs_ = prompts_hs.format(headstart=self.headstart)
+            history_ = []
+            story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, '故事开头', self.llm_kwargs,
+                chatbot, history_, self.sys_prompt_
+            )
+            self.story.append(story_paragraph)
+            # # 配图
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+
+            # # 构建后续剧情引导
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
+            history_ = []
+            self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, '请在以下几种故事走向中，选择一种（当然，您也可以选择给出其他故事走向）：', self.llm_kwargs,
+                chatbot,
+                history_,
+                self.sys_prompt_
+            )
+            self.cur_task = 'user_choice'
+
+
+        elif self.cur_task == 'user_choice':
+            """
+            根据用户的提示，确定故事的下一步
+            """
+            if '请在以下几种故事走向中，选择一种' in chatbot[-1][0]: chatbot.pop(-1)
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_resume.format(previously_on_story=previously_on_story, choice=self.next_choices, user_choice=prompt)
+            history_ = []
+            story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, f'下一段故事（您的选择是：{prompt}）。', self.llm_kwargs,
+                chatbot, history_, self.sys_prompt_
+            )
+            self.story.append(story_paragraph)
+            # # 配图
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+
+            # # 构建后续剧情引导
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_interact.format(previously_on_story=previously_on_story)
+            history_ = []
+            self.next_choices = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_,
+                '请在以下几种故事走向中，选择一种。当然，您也可以给出您心中的其他故事走向。另外，如果您希望剧情立即收尾，请输入剧情走向，并以“剧情收尾”四个字提示程序。', self.llm_kwargs,
+                chatbot,
+                history_,
+                self.sys_prompt_
+            )
+            self.cur_task = 'user_choice'
+
+
+        elif self.cur_task == 'story_terminate':
+            """
+            根据用户的提示，确定故事的结局
+            """
+            previously_on_story = ""
+            for s in self.story:
+                previously_on_story += s + '\n'
+            inputs_ = prompts_terminate.format(previously_on_story=previously_on_story, user_choice=prompt)
+            history_ = []
+            story_paragraph = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs_, f'故事收尾（您的选择是：{prompt}）。', self.llm_kwargs,
+                chatbot, history_, self.sys_prompt_
+            )
+            # # 配图
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
+            yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
+
+            # terminate game
+            self.delete_game = True
+            return

crazy_functions/game_fns/game_utils.py

@@ -0,0 +1,35 @@
+
+from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
+from request_llms.bridge_all import predict_no_ui_long_connection
+def get_code_block(reply):
+    import re
+    pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
+    matches = re.findall(pattern, reply) # find all code blocks in text
+    if len(matches) == 1:
+        return "```" + matches[0] + "```" #  code block
+    raise RuntimeError("GPT is not generating proper code.")
+
+def is_same_thing(a, b, llm_kwargs):
+    from pydantic import BaseModel, Field
+    class IsSameThing(BaseModel):
+        is_same_thing: bool = Field(description="determine whether two objects are same thing.", default=False)
+
+    def run_gpt_fn(inputs, sys_prompt, history=[]):
+        return predict_no_ui_long_connection(
+            inputs=inputs, llm_kwargs=llm_kwargs,
+            history=history, sys_prompt=sys_prompt, observe_window=[]
+        )
+
+    gpt_json_io = GptJsonIO(IsSameThing)
+    inputs_01 = "Identity whether the user input and the target is the same thing: \n target object: {a} \n user input object: {b} \n\n\n".format(a=a, b=b)
+    inputs_01 += "\n\n\n Note that the user may describe the target object with a different language, e.g. cat and 猫 are the same thing."
+    analyze_res_cot_01 = run_gpt_fn(inputs_01, "", [])
+
+    inputs_02 = inputs_01 + gpt_json_io.format_instructions
+    analyze_res = run_gpt_fn(inputs_02, "", [inputs_01, analyze_res_cot_01])
+
+    try:
+        res = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
+        return res.is_same_thing
+    except JsonStringError as e:
+        return False

crazy_functions/gen_fns/gen_fns_shared.py

@@ -41,11 +41,11 @@ def is_function_successfully_generated(fn_path, class_name, return_dict):
         # Now you can create an instance of the class
         instance = some_class()
         return_dict['success'] = True
-        return 
+        return
     except:
         return_dict['traceback'] = trimmed_format_exc()
         return
-    
+
 def subprocess_worker(code, file_path, return_dict):
     return_dict['result'] = None
     return_dict['success'] = False

crazy_functions/ipc_fns/mp.py

@@ -0,0 +1,37 @@
+import platform
+import pickle
+import multiprocessing
+
+def run_in_subprocess_wrapper_func(v_args):
+    func, args, kwargs, return_dict, exception_dict = pickle.loads(v_args)
+    import sys
+    try:
+        result = func(*args, **kwargs)
+        return_dict['result'] = result
+    except Exception as e:
+        exc_info = sys.exc_info()
+        exception_dict['exception'] = exc_info
+
+def run_in_subprocess_with_timeout(func, timeout=60):
+    if platform.system() == 'Linux':
+        def wrapper(*args, **kwargs):
+            return_dict = multiprocessing.Manager().dict()
+            exception_dict = multiprocessing.Manager().dict()
+            v_args = pickle.dumps((func, args, kwargs, return_dict, exception_dict))
+            process = multiprocessing.Process(target=run_in_subprocess_wrapper_func, args=(v_args,))
+            process.start()
+            process.join(timeout)
+            if process.is_alive():
+                process.terminate()
+                raise TimeoutError(f'功能单元{str(func)}未能在规定时间内完成任务')
+            process.close()
+            if 'exception' in exception_dict:
+                # ooops, the subprocess ran into an exception
+                exc_info = exception_dict['exception']
+                raise exc_info[1].with_traceback(exc_info[2])
+            if 'result' in return_dict.keys():
+                # If the subprocess ran successfully, return the result
+                return return_dict['result']
+        return wrapper
+    else:
+        return func

crazy_functions/json_fns/pydantic_io.py

@@ -62,8 +62,8 @@ class GptJsonIO():
         if "type" in reduced_schema:
             del reduced_schema["type"]
         # Ensure json in context is well-formed with double quotes.
+        schema_str = json.dumps(reduced_schema)
         if self.example_instruction:
-            schema_str = json.dumps(reduced_schema)
             return PYDANTIC_FORMAT_INSTRUCTIONS.format(schema=schema_str)
         else:
             return PYDANTIC_FORMAT_INSTRUCTIONS_SIMPLE.format(schema=schema_str)
@@ -89,7 +89,7 @@ class GptJsonIO():
                  error + "\n\n" + \
                 "Now, fix this json string. \n\n"
         return prompt
-    
+
     def generate_output_auto_repair(self, response, gpt_gen_fn):
         """
         response: string containing canidate json

crazy_functions/latex_fns/latex_actions.py

@@ -1,9 +1,11 @@
 from toolbox import update_ui, update_ui_lastest_msg, get_log_folder
-from toolbox import zip_folder, objdump, objload, promote_file_to_downloadzone
+from toolbox import get_conf, promote_file_to_downloadzone
 from .latex_toolbox import PRESERVE, TRANSFORM
 from .latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
 from .latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
 from .latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
+from .latex_toolbox import find_title_and_abs
+from .latex_pickle_io import objdump, objload
 
 import os, shutil
 import re
@@ -89,8 +91,19 @@ class LatexPaperSplit():
             "版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
             "项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
         # 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
-        self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\" 
+        self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
+        self.title = "unknown"
+        self.abstract = "unknown"
 
+    def read_title_and_abstract(self, txt):
+        try:
+            title, abstract = find_title_and_abs(txt)
+            if title is not None:
+                self.title = title.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
+            if abstract is not None:
+                self.abstract = abstract.replace('\n', ' ').replace('\\\\', ' ').replace('  ', '').replace('  ', '')
+        except:
+            pass
 
     def merge_result(self, arr, mode, msg, buggy_lines=[], buggy_line_surgery_n_lines=10):
         """
@@ -99,7 +112,7 @@ class LatexPaperSplit():
         result_string = ""
         node_cnt = 0
         line_cnt = 0
-        
+
         for node in self.nodes:
             if node.preserve:
                 line_cnt += node.string.count('\n')
@@ -132,7 +145,7 @@ class LatexPaperSplit():
         return result_string
 
 
-    def split(self, txt, project_folder, opts): 
+    def split(self, txt, project_folder, opts):
         """
         break down latex file to a linked list,
         each node use a preserve flag to indicate whether it should
@@ -143,7 +156,7 @@ class LatexPaperSplit():
         manager = multiprocessing.Manager()
         return_dict = manager.dict()
         p = multiprocessing.Process(
-            target=split_subprocess, 
+            target=split_subprocess,
             args=(txt, project_folder, return_dict, opts))
         p.start()
         p.join()
@@ -163,9 +176,8 @@ class LatexPaperFileGroup():
         self.sp_file_contents = []
         self.sp_file_index = []
         self.sp_file_tag = []
-
         # count_token
-        from request_llm.bridge_all import model_info
+        from request_llms.bridge_all import model_info
         enc = model_info["gpt-3.5-turbo"]['tokenizer']
         def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
         self.get_token_num = get_token_num
@@ -180,13 +192,12 @@ class LatexPaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from ..crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.tex")
-        print('Segmentation: done')
 
     def merge_result(self):
         self.file_result = ["" for _ in range(len(self.file_paths))]
@@ -207,13 +218,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
 
-    #  <-------- 寻找主tex文件 ----------> 
+    #  <-------- 寻找主tex文件 ---------->
     maintex = find_main_tex_file(file_manifest, mode)
     chatbot.append((f"定位主Latex文件", f'[Local Message] 分析结果：该项目的Latex主文件是{maintex}, 如果分析错误, 请立即终止程序, 删除或修改歧义文件, 然后重试。主程序即将开始, 请稍候。'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     time.sleep(3)
 
-    #  <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ----------> 
+    #  <-------- 读取Latex文件, 将多文件tex工程融合为一个巨型tex ---------->
     main_tex_basename = os.path.basename(maintex)
     assert main_tex_basename.endswith('.tex')
     main_tex_basename_bare = main_tex_basename[:-4]
@@ -230,13 +241,13 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     with open(project_folder + '/merge.tex', 'w', encoding='utf-8', errors='replace') as f:
         f.write(merged_content)
 
-    #  <-------- 精细切分latex文件 ----------> 
+    #  <-------- 精细切分latex文件 ---------->
     chatbot.append((f"Latex文件融合完成", f'[Local Message] 正在精细切分latex文件，这需要一段时间计算，文档越长耗时越长，请耐心等待。'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     lps = LatexPaperSplit()
+    lps.read_title_and_abstract(merged_content)
     res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数
-
-    #  <-------- 拆分过长的latex片段 ----------> 
+    #  <-------- 拆分过长的latex片段 ---------->
     pfg = LatexPaperFileGroup()
     for index, r in enumerate(res):
         pfg.file_paths.append('segment-' + str(index))
@@ -245,54 +256,61 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 根据需要切换prompt ----------> 
+    #  <-------- 根据需要切换prompt ---------->
     inputs_array, sys_prompt_array = switch_prompt(pfg, mode)
     inputs_show_user_array = [f"{mode} {f}" for f in pfg.sp_file_tag]
 
     if os.path.exists(pj(project_folder,'temp.pkl')):
 
-        #  <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ----------> 
+        #  <-------- 【仅调试】如果存在调试缓存文件，则跳过GPT请求环节 ---------->
         pfg = objload(file=pj(project_folder,'temp.pkl'))
 
     else:
-        #  <-------- gpt 多线程请求 ----------> 
+        #  <-------- gpt 多线程请求 ---------->
+        history_array = [[""] for _ in range(n_split)]
+        # LATEX_EXPERIMENTAL, = get_conf('LATEX_EXPERIMENTAL')
+        # if LATEX_EXPERIMENTAL:
+        #     paper_meta = f"The paper you processing is `{lps.title}`, a part of the abstraction is `{lps.abstract}`"
+        #     paper_meta_max_len = 888
+        #     history_array = [[ paper_meta[:paper_meta_max_len] + '...',  "Understand, what should I do?"] for _ in range(n_split)]
+
         gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             inputs_array=inputs_array,
             inputs_show_user_array=inputs_show_user_array,
             llm_kwargs=llm_kwargs,
             chatbot=chatbot,
-            history_array=[[""] for _ in range(n_split)],
+            history_array=history_array,
             sys_prompt_array=sys_prompt_array,
             # max_workers=5,  # 并行任务数量限制, 最多同时执行5个, 其他的排队等待
             scroller_max_len = 40
         )
 
-        #  <-------- 文本碎片重组为完整的tex片段 ----------> 
+        #  <-------- 文本碎片重组为完整的tex片段 ---------->
         pfg.sp_file_result = []
         for i_say, gpt_say, orig_content in zip(gpt_response_collection[0::2], gpt_response_collection[1::2], pfg.sp_file_contents):
             pfg.sp_file_result.append(gpt_say)
         pfg.merge_result()
 
-        # <-------- 临时存储用于调试 ----------> 
+        # <-------- 临时存储用于调试 ---------->
         pfg.get_token_num = None
         objdump(pfg, file=pj(project_folder,'temp.pkl'))
 
     write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
 
-    #  <-------- 写出文件 ----------> 
+    #  <-------- 写出文件 ---------->
     msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
     final_tex = lps.merge_result(pfg.file_result, mode, msg)
     objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
 
     with open(project_folder + f'/merge_{mode}.tex', 'w', encoding='utf-8', errors='replace') as f:
         if mode != 'translate_zh' or "binary" in final_tex: f.write(final_tex)
-        
 
-    #  <-------- 整理结果, 退出 ----------> 
+
+    #  <-------- 整理结果, 退出 ---------->
     chatbot.append((f"完成了吗？", 'GPT结果已输出, 即将编译PDF'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-    #  <-------- 返回 ----------> 
+    #  <-------- 返回 ---------->
     return project_folder + f'/merge_{mode}.tex'
 
 
@@ -345,7 +363,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
 
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history)   # 刷新Gradio前端界面
         ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
-        
+
         if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
             # 只有第二步成功，才能继续下面的步骤
             yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history)    # 刷新Gradio前端界面
@@ -376,36 +394,39 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
         original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
         modified_pdf_success = os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf'))
         diff_pdf_success     = os.path.exists(pj(work_folder, f'merge_diff.pdf'))
-        results_ += f"原始PDF编译是否成功: {original_pdf_success};" 
-        results_ += f"转化PDF编译是否成功: {modified_pdf_success};" 
-        results_ += f"对比PDF编译是否成功: {diff_pdf_success};" 
+        results_ += f"原始PDF编译是否成功: {original_pdf_success};"
+        results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
+        results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
         yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
 
         if diff_pdf_success:
             result_pdf = pj(work_folder_modified, f'merge_diff.pdf')    # get pdf path
             promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
         if modified_pdf_success:
-            yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 即将退出 ...', chatbot, history)    # 刷新Gradio前端界面
+            yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history)    # 刷新Gradio前端界面
             result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
             origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
             if os.path.exists(pj(work_folder, '..', 'translation')):
                 shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
             promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
             # 将两个PDF拼接
-            if original_pdf_success: 
+            if original_pdf_success:
                 try:
                     from .latex_toolbox import merge_pdfs
                     concat_pdf = pj(work_folder_modified, f'comparison.pdf')
                     merge_pdfs(origin_pdf, result_pdf, concat_pdf)
+                    if os.path.exists(pj(work_folder, '..', 'translation')):
+                        shutil.copyfile(concat_pdf, pj(work_folder, '..', 'translation', 'comparison.pdf'))
                     promote_file_to_downloadzone(concat_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
                 except Exception as e:
+                    print(e)
                     pass
             return True # 成功啦
         else:
             if n_fix>=max_try: break
             n_fix += 1
             can_retry, main_file_modified, buggy_lines = remove_buggy_lines(
-                file_path=pj(work_folder_modified, f'{main_file_modified}.tex'), 
+                file_path=pj(work_folder_modified, f'{main_file_modified}.tex'),
                 log_path=pj(work_folder_modified, f'{main_file_modified}.log'),
                 tex_name=f'{main_file_modified}.tex',
                 tex_name_pure=f'{main_file_modified}',
@@ -423,16 +444,16 @@ def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
     # write html
     try:
         import shutil
-        from ..crazy_utils import construct_html
+        from crazy_functions.pdf_fns.report_gen_html import construct_html
         from toolbox import gen_time_str
-        ch = construct_html() 
+        ch = construct_html()
         orig = ""
         trans = ""
         final = []
-        for c,r in zip(sp_file_contents, sp_file_result): 
+        for c,r in zip(sp_file_contents, sp_file_result):
             final.append(c)
             final.append(r)
-        for i, k in enumerate(final): 
+        for i, k in enumerate(final):
             if i%2==0:
                 orig = k
             if i%2==1:

crazy_functions/latex_fns/latex_pickle_io.py

@@ -0,0 +1,38 @@
+import pickle
+
+
+class SafeUnpickler(pickle.Unpickler):
+
+    def get_safe_classes(self):
+        from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
+        # 定义允许的安全类
+        safe_classes = {
+            # 在这里添加其他安全的类
+            'LatexPaperFileGroup': LatexPaperFileGroup,
+            'LatexPaperSplit' : LatexPaperSplit,
+        }
+        return safe_classes
+
+    def find_class(self, module, name):
+        # 只允许特定的类进行反序列化
+        self.safe_classes = self.get_safe_classes()
+        if f'{module}.{name}' in self.safe_classes:
+            return self.safe_classes[f'{module}.{name}']
+        # 如果尝试加载未授权的类，则抛出异常
+        raise pickle.UnpicklingError(f"Attempted to deserialize unauthorized class '{name}' from module '{module}'")
+
+def objdump(obj, file="objdump.tmp"):
+
+    with open(file, "wb+") as f:
+        pickle.dump(obj, f)
+    return
+
+
+def objload(file="objdump.tmp"):
+    import os
+
+    if not os.path.exists(file):
+        return
+    with open(file, "rb") as f:
+        unpickler = SafeUnpickler(f)
+        return unpickler.load()

crazy_functions/latex_fns/latex_toolbox.py

@@ -1,15 +1,18 @@
 import os, shutil
 import re
 import numpy as np
+
 PRESERVE = 0
 TRANSFORM = 1
 
 pj = os.path.join
 
-class LinkedListNode():
+
+class LinkedListNode:
     """
     Linked List Node
     """
+
     def __init__(self, string, preserve=True) -> None:
         self.string = string
         self.preserve = preserve
@@ -18,41 +21,47 @@ class LinkedListNode():
         # self.begin_line = 0
         # self.begin_char = 0
 
+
 def convert_to_linklist(text, mask):
     root = LinkedListNode("", preserve=True)
     current_node = root
     for c, m, i in zip(text, mask, range(len(text))):
-        if (m==PRESERVE and current_node.preserve) \
-            or (m==TRANSFORM and not current_node.preserve):
+        if (m == PRESERVE and current_node.preserve) or (
+            m == TRANSFORM and not current_node.preserve
+        ):
             # add
             current_node.string += c
         else:
-            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
+            current_node.next = LinkedListNode(c, preserve=(m == PRESERVE))
             current_node = current_node.next
     return root
 
+
 def post_process(root):
     # 修复括号
     node = root
     while True:
         string = node.string
-        if node.preserve: 
+        if node.preserve:
             node = node.next
-            if node is None: break
+            if node is None:
+                break
             continue
+
         def break_check(string):
-            str_stack = [""] # (lv, index)
+            str_stack = [""]  # (lv, index)
             for i, c in enumerate(string):
-                if c == '{':
-                    str_stack.append('{')
-                elif c == '}':
+                if c == "{":
+                    str_stack.append("{")
+                elif c == "}":
                     if len(str_stack) == 1:
-                        print('stack fix')
+                        print("stack fix")
                         return i
                     str_stack.pop(-1)
                 else:
                     str_stack[-1] += c
             return -1
+
         bp = break_check(string)
 
         if bp == -1:
@@ -69,51 +78,66 @@ def post_process(root):
             node.next = q
 
         node = node.next
-        if node is None: break
+        if node is None:
+            break
 
     # 屏蔽空行和太短的句子
     node = root
     while True:
-        if len(node.string.strip('\n').strip(''))==0: node.preserve = True
-        if len(node.string.strip('\n').strip(''))<42: node.preserve = True
+        if len(node.string.strip("\n").strip("")) == 0:
+            node.preserve = True
+        if len(node.string.strip("\n").strip("")) < 42:
+            node.preserve = True
         node = node.next
-        if node is None: break
+        if node is None:
+            break
     node = root
     while True:
         if node.next and node.preserve and node.next.preserve:
             node.string += node.next.string
             node.next = node.next.next
         node = node.next
-        if node is None: break
+        if node is None:
+            break
 
     # 将前后断行符脱离
     node = root
     prev_node = None
     while True:
         if not node.preserve:
-            lstriped_ = node.string.lstrip().lstrip('\n')
-            if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
-                prev_node.string += node.string[:-len(lstriped_)]
+            lstriped_ = node.string.lstrip().lstrip("\n")
+            if (
+                (prev_node is not None)
+                and (prev_node.preserve)
+                and (len(lstriped_) != len(node.string))
+            ):
+                prev_node.string += node.string[: -len(lstriped_)]
                 node.string = lstriped_
-            rstriped_ = node.string.rstrip().rstrip('\n')
-            if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
-                node.next.string = node.string[len(rstriped_):] + node.next.string
+            rstriped_ = node.string.rstrip().rstrip("\n")
+            if (
+                (node.next is not None)
+                and (node.next.preserve)
+                and (len(rstriped_) != len(node.string))
+            ):
+                node.next.string = node.string[len(rstriped_) :] + node.next.string
                 node.string = rstriped_
-        # =====
+        # =-=-=
         prev_node = node
         node = node.next
-        if node is None: break
+        if node is None:
+            break
 
     # 标注节点的行数范围
     node = root
     n_line = 0
     expansion = 2
     while True:
-        n_l = node.string.count('\n')
-        node.range = [n_line-expansion, n_line+n_l+expansion]   # 失败时，扭转的范围
-        n_line = n_line+n_l
+        n_l = node.string.count("\n")
+        node.range = [n_line - expansion, n_line + n_l + expansion]  # 失败时，扭转的范围
+        n_line = n_line + n_l
         node = node.next
-        if node is None: break
+        if node is None:
+            break
     return root
 
 
@@ -128,97 +152,125 @@ def set_forbidden_text(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper
     e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
-    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
+    you can mask out (mask = PRESERVE so that text become untouchable for GPT)
     everything between "\begin{equation}" and "\end{equation}"
     """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    if isinstance(pattern, list):
+        pattern = "|".join(pattern)
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
-        mask[res.span()[0]:res.span()[1]] = PRESERVE
+        mask[res.span()[0] : res.span()[1]] = PRESERVE
     return text, mask
 
+
 def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
     """
     Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
+    count the number of the braces so as to catch compelete text area.
     e.g.
-    \begin{abstract} blablablablablabla. \end{abstract} 
+    \begin{abstract} blablablablablabla. \end{abstract}
     """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    if isinstance(pattern, list):
+        pattern = "|".join(pattern)
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         if not forbid_wrapper:
-            mask[res.span()[0]:res.span()[1]] = TRANSFORM
+            mask[res.span()[0] : res.span()[1]] = TRANSFORM
         else:
-            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
-            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
-            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
+            mask[res.regs[0][0] : res.regs[1][0]] = PRESERVE  # '\\begin{abstract}'
+            mask[res.regs[1][0] : res.regs[1][1]] = TRANSFORM  # abstract
+            mask[res.regs[1][1] : res.regs[0][1]] = PRESERVE  # abstract
     return text, mask
 
+
 def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
     """
     Add a preserve text area in this paper (text become untouchable for GPT).
-    count the number of the braces so as to catch compelete text area. 
+    count the number of the braces so as to catch compelete text area.
     e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    \caption{blablablablabla\texbf{blablabla}blablabla.}
     """
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         brace_level = -1
         p = begin = end = res.regs[0][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
+        for _ in range(1024 * 16):
+            if text[p] == "}" and brace_level == 0:
+                break
+            elif text[p] == "}":
+                brace_level -= 1
+            elif text[p] == "{":
+                brace_level += 1
             p += 1
-        end = p+1
+        end = p + 1
         mask[begin:end] = PRESERVE
     return text, mask
 
-def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
+
+def reverse_forbidden_text_careful_brace(
+    text, mask, pattern, flags=0, forbid_wrapper=True
+):
     """
     Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
+    count the number of the braces so as to catch compelete text area.
     e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    \caption{blablablablabla\texbf{blablabla}blablabla.}
     """
     pattern_compile = re.compile(pattern, flags)
     for res in pattern_compile.finditer(text):
         brace_level = 0
         p = begin = end = res.regs[1][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
+        for _ in range(1024 * 16):
+            if text[p] == "}" and brace_level == 0:
+                break
+            elif text[p] == "}":
+                brace_level -= 1
+            elif text[p] == "{":
+                brace_level += 1
             p += 1
         end = p
         mask[begin:end] = TRANSFORM
         if forbid_wrapper:
-            mask[res.regs[0][0]:begin] = PRESERVE
-            mask[end:res.regs[0][1]] = PRESERVE
+            mask[res.regs[0][0] : begin] = PRESERVE
+            mask[end : res.regs[0][1]] = PRESERVE
     return text, mask
 
+
 def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
     """
     Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
     Add it to preserve area
     """
     pattern_compile = re.compile(pattern, flags)
+
     def search_with_line_limit(text, mask):
         for res in pattern_compile.finditer(text):
             cmd = res.group(1)  # begin{what}
-            this = res.group(2) # content between begin and end
-            this_mask = mask[res.regs[2][0]:res.regs[2][1]]
-            white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof', 
-                          'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
-            if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
+            this = res.group(2)  # content between begin and end
+            this_mask = mask[res.regs[2][0] : res.regs[2][1]]
+            white_list = [
+                "document",
+                "abstract",
+                "lemma",
+                "definition",
+                "sproof",
+                "em",
+                "emph",
+                "textit",
+                "textbf",
+                "itemize",
+                "enumerate",
+            ]
+            if (cmd in white_list) or this.count(
+                "\n"
+            ) >= limit_n_lines:  # use a magical number 42
                 this, this_mask = search_with_line_limit(this, this_mask)
-                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
+                mask[res.regs[2][0] : res.regs[2][1]] = this_mask
             else:
-                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
+                mask[res.regs[0][0] : res.regs[0][1]] = PRESERVE
         return text, mask
-    return search_with_line_limit(text, mask) 
 
+    return search_with_line_limit(text, mask)
 
 
 """
@@ -227,6 +279,7 @@ Latex Merge File
 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 """
 
+
 def find_main_tex_file(file_manifest, mode):
     """
     在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
@@ -234,27 +287,36 @@ def find_main_tex_file(file_manifest, mode):
     """
     canidates = []
     for texf in file_manifest:
-        if os.path.basename(texf).startswith('merge'):
+        if os.path.basename(texf).startswith("merge"):
             continue
-        with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+        with open(texf, "r", encoding="utf8", errors="ignore") as f:
             file_content = f.read()
-        if r'\documentclass' in file_content:
+        if r"\documentclass" in file_content:
             canidates.append(texf)
         else:
             continue
 
     if len(canidates) == 0:
-        raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
+        raise RuntimeError("无法找到一个主Tex文件（包含documentclass关键字）")
     elif len(canidates) == 1:
         return canidates[0]
-    else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
+    else:  # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
         canidates_score = []
         # 给出一些判定模板文档的词作为扣分项
-        unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
-        expected_words = ['\input', '\ref', '\cite']
+        unexpected_words = [
+            "\\LaTeX",
+            "manuscript",
+            "Guidelines",
+            "font",
+            "citations",
+            "rejected",
+            "blind review",
+            "reviewers",
+        ]
+        expected_words = ["\\input", "\\ref", "\\cite"]
         for texf in canidates:
             canidates_score.append(0)
-            with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+            with open(texf, "r", encoding="utf8", errors="ignore") as f:
                 file_content = f.read()
                 file_content = rm_comments(file_content)
             for uw in unexpected_words:
@@ -263,9 +325,10 @@ def find_main_tex_file(file_manifest, mode):
             for uw in expected_words:
                 if uw in file_content:
                     canidates_score[-1] += 1
-        select = np.argmax(canidates_score) # 取评分最高者返回
+        select = np.argmax(canidates_score)  # 取评分最高者返回
         return canidates[select]
-    
+
+
 def rm_comments(main_file):
     new_file_remove_comment_lines = []
     for l in main_file.splitlines():
@@ -274,30 +337,39 @@ def rm_comments(main_file):
             pass
         else:
             new_file_remove_comment_lines.append(l)
-    main_file = '\n'.join(new_file_remove_comment_lines)
+    main_file = "\n".join(new_file_remove_comment_lines)
     # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
-    main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
+    main_file = re.sub(r"(?<!\\)%.*", "", main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
     return main_file
 
+
 def find_tex_file_ignore_case(fp):
     dir_name = os.path.dirname(fp)
     base_name = os.path.basename(fp)
     # 如果输入的文件路径是正确的
-    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    if os.path.isfile(pj(dir_name, base_name)):
+        return pj(dir_name, base_name)
     # 如果不正确，试着加上.tex后缀试试
-    if not base_name.endswith('.tex'): base_name+='.tex'
-    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    if not base_name.endswith(".tex"):
+        base_name += ".tex"
+    if os.path.isfile(pj(dir_name, base_name)):
+        return pj(dir_name, base_name)
     # 如果还找不到，解除大小写限制，再试一次
     import glob
-    for f in glob.glob(dir_name+'/*.tex'):
+
+    for f in glob.glob(dir_name + "/*.tex"):
         base_name_s = os.path.basename(fp)
         base_name_f = os.path.basename(f)
-        if base_name_s.lower() == base_name_f.lower(): return f
+        if base_name_s.lower() == base_name_f.lower():
+            return f
         # 试着加上.tex后缀试试
-        if not base_name_s.endswith('.tex'): base_name_s+='.tex'
-        if base_name_s.lower() == base_name_f.lower(): return f
+        if not base_name_s.endswith(".tex"):
+            base_name_s += ".tex"
+        if base_name_s.lower() == base_name_f.lower():
+            return f
     return None
 
+
 def merge_tex_files_(project_foler, main_file, mode):
     """
     Merge Tex project recrusively
@@ -308,13 +380,51 @@ def merge_tex_files_(project_foler, main_file, mode):
         fp = os.path.join(project_foler, f)
         fp_ = find_tex_file_ignore_case(fp)
         if fp_:
-            with open(fp_, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
+            try:
+                with open(fp_, "r", encoding="utf-8", errors="replace") as fx:
+                    c = fx.read()
+            except:
+                c = f"\n\nWarning from GPT-Academic: LaTex source file is missing!\n\n"
         else:
-            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
+            raise RuntimeError(f"找不到{fp}，Tex源文件缺失！")
         c = merge_tex_files_(project_foler, c, mode)
-        main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
+        main_file = main_file[: s.span()[0]] + c + main_file[s.span()[1] :]
     return main_file
 
+
+def find_title_and_abs(main_file):
+    def extract_abstract_1(text):
+        pattern = r"\\abstract\{(.*?)\}"
+        match = re.search(pattern, text, re.DOTALL)
+        if match:
+            return match.group(1)
+        else:
+            return None
+
+    def extract_abstract_2(text):
+        pattern = r"\\begin\{abstract\}(.*?)\\end\{abstract\}"
+        match = re.search(pattern, text, re.DOTALL)
+        if match:
+            return match.group(1)
+        else:
+            return None
+
+    def extract_title(string):
+        pattern = r"\\title\{(.*?)\}"
+        match = re.search(pattern, string, re.DOTALL)
+
+        if match:
+            return match.group(1)
+        else:
+            return None
+
+    abstract = extract_abstract_1(main_file)
+    if abstract is None:
+        abstract = extract_abstract_2(main_file)
+    title = extract_title(main_file)
+    return title, abstract
+
+
 def merge_tex_files(project_foler, main_file, mode):
     """
     Merge Tex project recrusively
@@ -324,46 +434,105 @@ def merge_tex_files(project_foler, main_file, mode):
     main_file = merge_tex_files_(project_foler, main_file, mode)
     main_file = rm_comments(main_file)
 
-    if mode == 'translate_zh':
+    if mode == "translate_zh":
         # find paper documentclass
-        pattern = re.compile(r'\\documentclass.*\n')
+        pattern = re.compile(r"\\documentclass.*\n")
         match = pattern.search(main_file)
         assert match is not None, "Cannot find documentclass statement!"
         position = match.end()
-        add_ctex = '\\usepackage{ctex}\n'
-        add_url = '\\usepackage{url}\n' if '{url}' not in main_file else ''
+        add_ctex = "\\usepackage{ctex}\n"
+        add_url = "\\usepackage{url}\n" if "{url}" not in main_file else ""
         main_file = main_file[:position] + add_ctex + add_url + main_file[position:]
         # fontset=windows
         import platform
-        main_file = re.sub(r"\\documentclass\[(.*?)\]{(.*?)}", r"\\documentclass[\1,fontset=windows,UTF8]{\2}",main_file)
-        main_file = re.sub(r"\\documentclass{(.*?)}", r"\\documentclass[fontset=windows,UTF8]{\1}",main_file)
+
+        main_file = re.sub(
+            r"\\documentclass\[(.*?)\]{(.*?)}",
+            r"\\documentclass[\1,fontset=windows,UTF8]{\2}",
+            main_file,
+        )
+        main_file = re.sub(
+            r"\\documentclass{(.*?)}",
+            r"\\documentclass[fontset=windows,UTF8]{\1}",
+            main_file,
+        )
         # find paper abstract
-        pattern_opt1 = re.compile(r'\\begin\{abstract\}.*\n')
+        pattern_opt1 = re.compile(r"\\begin\{abstract\}.*\n")
         pattern_opt2 = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
         match_opt1 = pattern_opt1.search(main_file)
         match_opt2 = pattern_opt2.search(main_file)
-        assert (match_opt1 is not None) or (match_opt2 is not None), "Cannot find paper abstract section!"
+        if (match_opt1 is None) and (match_opt2 is None):
+            # "Cannot find paper abstract section!"
+            main_file = insert_abstract(main_file)
+        match_opt1 = pattern_opt1.search(main_file)
+        match_opt2 = pattern_opt2.search(main_file)
+        assert (match_opt1 is not None) or (
+            match_opt2 is not None
+        ), "Cannot find paper abstract section!"
     return main_file
 
 
+insert_missing_abs_str = r"""
+\begin{abstract}
+The GPT-Academic program cannot find abstract section in this paper.
+\end{abstract}
+"""
+
+
+def insert_abstract(tex_content):
+    if "\\maketitle" in tex_content:
+        # find the position of "\maketitle"
+        find_index = tex_content.index("\\maketitle")
+        # find the nearest ending line
+        end_line_index = tex_content.find("\n", find_index)
+        # insert "abs_str" on the next line
+        modified_tex = (
+            tex_content[: end_line_index + 1]
+            + "\n\n"
+            + insert_missing_abs_str
+            + "\n\n"
+            + tex_content[end_line_index + 1 :]
+        )
+        return modified_tex
+    elif r"\begin{document}" in tex_content:
+        # find the position of "\maketitle"
+        find_index = tex_content.index(r"\begin{document}")
+        # find the nearest ending line
+        end_line_index = tex_content.find("\n", find_index)
+        # insert "abs_str" on the next line
+        modified_tex = (
+            tex_content[: end_line_index + 1]
+            + "\n\n"
+            + insert_missing_abs_str
+            + "\n\n"
+            + tex_content[end_line_index + 1 :]
+        )
+        return modified_tex
+    else:
+        return tex_content
+
+
 """
 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 Post process
 =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
 """
+
+
 def mod_inbraket(match):
     """
-    为啥chatgpt会把cite里面的逗号换成中文逗号呀 
+    为啥chatgpt会把cite里面的逗号换成中文逗号呀
     """
     # get the matched string
     cmd = match.group(1)
     str_to_modify = match.group(2)
     # modify the matched string
-    str_to_modify = str_to_modify.replace('：', ':')    # 前面是中文冒号，后面是英文冒号
-    str_to_modify = str_to_modify.replace('，', ',')    # 前面是中文逗号，后面是英文逗号
+    str_to_modify = str_to_modify.replace("：", ":")  # 前面是中文冒号，后面是英文冒号
+    str_to_modify = str_to_modify.replace("，", ",")  # 前面是中文逗号，后面是英文逗号
     # str_to_modify = 'BOOM'
     return "\\" + cmd + "{" + str_to_modify + "}"
 
+
 def fix_content(final_tex, node_string):
     """
     Fix common GPT errors to increase success rate
@@ -374,10 +543,10 @@ def fix_content(final_tex, node_string):
     final_tex = re.sub(r"\\([a-z]{2,10})\{([^\}]*?)\}", mod_inbraket, string=final_tex)
 
     if "Traceback" in final_tex and "[Local Message]" in final_tex:
-        final_tex = node_string # 出问题了，还原原文
-    if node_string.count('\\begin') != final_tex.count('\\begin'):
-        final_tex = node_string # 出问题了，还原原文
-    if node_string.count('\_') > 0 and node_string.count('\_') > final_tex.count('\_'):
+        final_tex = node_string  # 出问题了，还原原文
+    if node_string.count("\\begin") != final_tex.count("\\begin"):
+        final_tex = node_string  # 出问题了，还原原文
+    if node_string.count("\_") > 0 and node_string.count("\_") > final_tex.count("\_"):
         # walk and replace any _ without \
         final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
 
@@ -385,24 +554,32 @@ def fix_content(final_tex, node_string):
         # this function count the number of { and }
         brace_level = 0
         for c in string:
-            if c == "{": brace_level += 1
-            elif c == "}": brace_level -= 1
+            if c == "{":
+                brace_level += 1
+            elif c == "}":
+                brace_level -= 1
         return brace_level
+
     def join_most(tex_t, tex_o):
         # this function join translated string and original string when something goes wrong
         p_t = 0
         p_o = 0
+
         def find_next(string, chars, begin):
             p = begin
             while p < len(string):
-                if string[p] in chars: return p, string[p]
+                if string[p] in chars:
+                    return p, string[p]
                 p += 1
             return None, None
+
         while True:
-            res1, char = find_next(tex_o, ['{','}'], p_o)
-            if res1 is None: break
+            res1, char = find_next(tex_o, ["{", "}"], p_o)
+            if res1 is None:
+                break
             res2, char = find_next(tex_t, [char], p_t)
-            if res2 is None: break
+            if res2 is None:
+                break
             p_o = res1 + 1
             p_t = res2 + 1
         return tex_t[:p_t] + tex_o[p_o:]
@@ -411,10 +588,14 @@ def fix_content(final_tex, node_string):
         # 出问题了，还原部分原文，保证括号正确
         final_tex = join_most(final_tex, node_string)
     return final_tex
-    
+
+
 def compile_latex_with_timeout(command, cwd, timeout=60):
     import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
+
+    process = subprocess.Popen(
+        command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd
+    )
     try:
         stdout, stderr = process.communicate(timeout=timeout)
     except subprocess.TimeoutExpired:
@@ -425,15 +606,51 @@ def compile_latex_with_timeout(command, cwd, timeout=60):
     return True
 
 
+def run_in_subprocess_wrapper_func(func, args, kwargs, return_dict, exception_dict):
+    import sys
+
+    try:
+        result = func(*args, **kwargs)
+        return_dict["result"] = result
+    except Exception as e:
+        exc_info = sys.exc_info()
+        exception_dict["exception"] = exc_info
+
+
+def run_in_subprocess(func):
+    import multiprocessing
+
+    def wrapper(*args, **kwargs):
+        return_dict = multiprocessing.Manager().dict()
+        exception_dict = multiprocessing.Manager().dict()
+        process = multiprocessing.Process(
+            target=run_in_subprocess_wrapper_func,
+            args=(func, args, kwargs, return_dict, exception_dict),
+        )
+        process.start()
+        process.join()
+        process.close()
+        if "exception" in exception_dict:
+            # ooops, the subprocess ran into an exception
+            exc_info = exception_dict["exception"]
+            raise exc_info[1].with_traceback(exc_info[2])
+        if "result" in return_dict.keys():
+            # If the subprocess ran successfully, return the result
+            return return_dict["result"]
+
+    return wrapper
+
+
+def _merge_pdfs(pdf1_path, pdf2_path, output_path):
+    import PyPDF2  # PyPDF2这个库有严重的内存泄露问题，把它放到子进程中运行，从而方便内存的释放
 
-def merge_pdfs(pdf1_path, pdf2_path, output_path):
-    import PyPDF2
     Percent = 0.95
+    # raise RuntimeError('PyPDF2 has a serious memory leak problem, please use other tools to merge PDF files.')
     # Open the first PDF file
-    with open(pdf1_path, 'rb') as pdf1_file:
+    with open(pdf1_path, "rb") as pdf1_file:
         pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
         # Open the second PDF file
-        with open(pdf2_path, 'rb') as pdf2_file:
+        with open(pdf2_path, "rb") as pdf2_file:
             pdf2_reader = PyPDF2.PdfFileReader(pdf2_file)
             # Create a new PDF file to store the merged pages
             output_writer = PyPDF2.PdfFileWriter()
@@ -453,12 +670,25 @@ def merge_pdfs(pdf1_path, pdf2_path, output_path):
                     page2 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
                 # Create a new empty page with double width
                 new_page = PyPDF2.PageObject.createBlankPage(
-                    width = int(int(page1.mediaBox.getWidth()) + int(page2.mediaBox.getWidth()) * Percent),
-                    height = max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight())
+                    width=int(
+                        int(page1.mediaBox.getWidth())
+                        + int(page2.mediaBox.getWidth()) * Percent
+                    ),
+                    height=max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight()),
                 )
                 new_page.mergeTranslatedPage(page1, 0, 0)
-                new_page.mergeTranslatedPage(page2, int(int(page1.mediaBox.getWidth())-int(page2.mediaBox.getWidth())* (1-Percent)), 0)
+                new_page.mergeTranslatedPage(
+                    page2,
+                    int(
+                        int(page1.mediaBox.getWidth())
+                        - int(page2.mediaBox.getWidth()) * (1 - Percent)
+                    ),
+                    0,
+                )
                 output_writer.addPage(new_page)
             # Save the merged PDF file
-            with open(output_path, 'wb') as output_file:
+            with open(output_path, "wb") as output_file:
                 output_writer.write(output_file)
+
+
+merge_pdfs = run_in_subprocess(_merge_pdfs)  # PyPDF2这个库有严重的内存泄露问题，把它放到子进程中运行，从而方便内存的释放

crazy_functions/live_audio/aliyunASR.py

@@ -1,4 +1,106 @@
-import time, logging, json
+import time, logging, json, sys, struct
+import numpy as np
+from scipy.io.wavfile import WAVE_FORMAT
+
+def write_numpy_to_wave(filename, rate, data, add_header=False):
+    """
+    Write a NumPy array as a WAV file.
+    """
+    def _array_tofile(fid, data):
+        # ravel gives a c-contiguous buffer
+        fid.write(data.ravel().view('b').data)
+
+    if hasattr(filename, 'write'):
+        fid = filename
+    else:
+        fid = open(filename, 'wb')
+
+    fs = rate
+
+    try:
+        dkind = data.dtype.kind
+        if not (dkind == 'i' or dkind == 'f' or (dkind == 'u' and
+                                                 data.dtype.itemsize == 1)):
+            raise ValueError("Unsupported data type '%s'" % data.dtype)
+
+        header_data = b''
+
+        header_data += b'RIFF'
+        header_data += b'\x00\x00\x00\x00'
+        header_data += b'WAVE'
+
+        # fmt chunk
+        header_data += b'fmt '
+        if dkind == 'f':
+            format_tag = WAVE_FORMAT.IEEE_FLOAT
+        else:
+            format_tag = WAVE_FORMAT.PCM
+        if data.ndim == 1:
+            channels = 1
+        else:
+            channels = data.shape[1]
+        bit_depth = data.dtype.itemsize * 8
+        bytes_per_second = fs*(bit_depth // 8)*channels
+        block_align = channels * (bit_depth // 8)
+
+        fmt_chunk_data = struct.pack('<HHIIHH', format_tag, channels, fs,
+                                     bytes_per_second, block_align, bit_depth)
+        if not (dkind == 'i' or dkind == 'u'):
+            # add cbSize field for non-PCM files
+            fmt_chunk_data += b'\x00\x00'
+
+        header_data += struct.pack('<I', len(fmt_chunk_data))
+        header_data += fmt_chunk_data
+
+        # fact chunk (non-PCM files)
+        if not (dkind == 'i' or dkind == 'u'):
+            header_data += b'fact'
+            header_data += struct.pack('<II', 4, data.shape[0])
+
+        # check data size (needs to be immediately before the data chunk)
+        if ((len(header_data)-4-4) + (4+4+data.nbytes)) > 0xFFFFFFFF:
+            raise ValueError("Data exceeds wave file size limit")
+        if add_header:
+            fid.write(header_data)
+            # data chunk
+            fid.write(b'data')
+            fid.write(struct.pack('<I', data.nbytes))
+            if data.dtype.byteorder == '>' or (data.dtype.byteorder == '=' and
+                                            sys.byteorder == 'big'):
+                data = data.byteswap()
+        _array_tofile(fid, data)
+
+        if add_header:
+            # Determine file size and place it in correct
+            #  position at start of the file.
+            size = fid.tell()
+            fid.seek(4)
+            fid.write(struct.pack('<I', size-8))
+
+    finally:
+        if not hasattr(filename, 'write'):
+            fid.close()
+        else:
+            fid.seek(0)
+
+def is_speaker_speaking(vad, data, sample_rate):
+    # Function to detect if the speaker is speaking
+    # The WebRTC VAD only accepts 16-bit mono PCM audio,
+    # sampled at 8000, 16000, 32000 or 48000 Hz.
+    # A frame must be either 10, 20, or 30 ms in duration:
+    frame_duration = 30
+    n_bit_each = int(sample_rate * frame_duration / 1000)*2 # x2 because audio is 16 bit (2 bytes)
+    res_list = []
+    for t in range(len(data)):
+        if t!=0 and t % n_bit_each == 0:
+            res_list.append(vad.is_speech(data[t-n_bit_each:t], sample_rate))
+
+    info = ''.join(['^' if r else '.' for r in res_list])
+    info = info[:10]
+    if any(res_list):
+        return True, info
+    else:
+        return False, info
 
 
 class AliyunASR():
@@ -66,25 +168,55 @@ class AliyunASR():
                     on_close=self.test_on_close,
                     callback_args=[uuid.hex]
                 )
-
+        timeout_limit_second = 20
         r = sr.start(aformat="pcm",
+                timeout=timeout_limit_second,
                 enable_intermediate_result=True,
                 enable_punctuation_prediction=True,
                 enable_inverse_text_normalization=True)
 
+        import webrtcvad
+        vad = webrtcvad.Vad()
+        vad.set_mode(1)
+
+        is_previous_frame_transmitted = False   # 上一帧是否有人说话
+        previous_frame_data = None
+        echo_cnt = 0        # 在没有声音之后，继续向服务器发送n次音频数据
+        echo_cnt_max = 4   # 在没有声音之后，继续向服务器发送n次音频数据
+        keep_alive_last_send_time = time.time()
         while not self.stop:
             # time.sleep(self.capture_interval)
-            audio = rad.read(uuid.hex) 
+            audio = rad.read(uuid.hex)
             if audio is not None:
                 # convert to pcm file
-                temp_file = f'{temp_folder}/{uuid.hex}.pcm' # 
+                temp_file = f'{temp_folder}/{uuid.hex}.pcm' #
                 dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
-                io.wavfile.write(temp_file, NEW_SAMPLERATE, dsdata)
+                write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata)
                 # read pcm binary
                 with open(temp_file, "rb") as f: data = f.read()
-                # print('audio len:', len(audio), '\t ds len:', len(dsdata), '\t need n send:', len(data)//640)
-                slices = zip(*(iter(data),) * 640)    # 640个字节为一组
-                for i in slices: sr.send_audio(bytes(i))
+                is_speaking, info = is_speaker_speaking(vad, data, NEW_SAMPLERATE)
+
+                if is_speaking or echo_cnt > 0:
+                    # 如果话筒激活 / 如果处于回声收尾阶段
+                    echo_cnt -= 1
+                    if not is_previous_frame_transmitted:   # 上一帧没有人声，但是我们把上一帧同样加上
+                        if previous_frame_data is not None: data = previous_frame_data + data
+                    if is_speaking:
+                        echo_cnt = echo_cnt_max
+                    slices = zip(*(iter(data),) * 640)      # 640个字节为一组
+                    for i in slices: sr.send_audio(bytes(i))
+                    keep_alive_last_send_time = time.time()
+                    is_previous_frame_transmitted = True
+                else:
+                    is_previous_frame_transmitted = False
+                    echo_cnt = 0
+                    # 保持链接激活，即使没有声音，也根据时间间隔，发送一些音频片段给服务器
+                    if time.time() - keep_alive_last_send_time > timeout_limit_second/2:
+                        slices = zip(*(iter(data),) * 640)    # 640个字节为一组
+                        for i in slices: sr.send_audio(bytes(i))
+                        keep_alive_last_send_time = time.time()
+                        is_previous_frame_transmitted = True
+                self.audio_shape = info
             else:
                 time.sleep(0.1)
 

crazy_functions/live_audio/audio_io.py

@@ -3,12 +3,12 @@ from scipy import interpolate
 
 def Singleton(cls):
     _instance = {}
- 
+
     def _singleton(*args, **kargs):
         if cls not in _instance:
             _instance[cls] = cls(*args, **kargs)
         return _instance[cls]
- 
+
     return _singleton
 
 
@@ -35,11 +35,11 @@ class RealtimeAudioDistribution():
     def read(self, uuid):
         if uuid in self.data:
             res = self.data.pop(uuid)
-            print('\r read-', len(res), '-', max(res), end='', flush=True)
+            # print('\r read-', len(res), '-', max(res), end='', flush=True)
         else:
             res = None
         return res
-    
+
 def change_sample_rate(audio, old_sr, new_sr):
     duration = audio.shape[0] / old_sr
 

crazy_functions/multi_stage/multi_stage_utils.py

@@ -0,0 +1,93 @@
+from pydantic import BaseModel, Field
+from typing import List
+from toolbox import update_ui_lastest_msg, disable_auto_promotion
+from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log_folder
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
+import time
+import pickle
+
+def have_any_recent_upload_files(chatbot):
+    _5min = 5 * 60
+    if not chatbot: return False    # chatbot is None
+    most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
+    if not most_recent_uploaded: return False   # most_recent_uploaded is None
+    if time.time() - most_recent_uploaded["time"] < _5min: return True # most_recent_uploaded is new
+    else: return False  # most_recent_uploaded is too old
+
+class GptAcademicState():
+    def __init__(self):
+        self.reset()
+
+    def reset(self):
+        pass
+
+    def dump_state(self, chatbot):
+        chatbot._cookies['plugin_state'] = pickle.dumps(self)
+
+    def set_state(self, chatbot, key, value):
+        setattr(self, key, value)
+        chatbot._cookies['plugin_state'] = pickle.dumps(self)
+
+    def get_state(chatbot, cls=None):
+        state = chatbot._cookies.get('plugin_state', None)
+        if state is not None:   state = pickle.loads(state)
+        elif cls is not None:   state = cls()
+        else:                   state = GptAcademicState()
+        state.chatbot = chatbot
+        return state
+
+
+class GptAcademicGameBaseState():
+    """
+    1. first init: __init__ ->
+    """
+    def init_game(self, chatbot, lock_plugin):
+        self.plugin_name = None
+        self.callback_fn = None
+        self.delete_game = False
+        self.step_cnt = 0
+
+    def lock_plugin(self, chatbot):
+        if self.callback_fn is None:
+            raise ValueError("callback_fn is None")
+        chatbot._cookies['lock_plugin'] = self.callback_fn
+        self.dump_state(chatbot)
+
+    def get_plugin_name(self):
+        if self.plugin_name is None:
+            raise ValueError("plugin_name is None")
+        return self.plugin_name
+
+    def dump_state(self, chatbot):
+        chatbot._cookies[f'plugin_state/{self.get_plugin_name()}'] = pickle.dumps(self)
+
+    def set_state(self, chatbot, key, value):
+        setattr(self, key, value)
+        chatbot._cookies[f'plugin_state/{self.get_plugin_name()}'] = pickle.dumps(self)
+
+    @staticmethod
+    def sync_state(chatbot, llm_kwargs, cls, plugin_name, callback_fn, lock_plugin=True):
+        state = chatbot._cookies.get(f'plugin_state/{plugin_name}', None)
+        if state is not None:
+            state = pickle.loads(state)
+        else:
+            state = cls()
+            state.init_game(chatbot, lock_plugin)
+        state.plugin_name = plugin_name
+        state.llm_kwargs = llm_kwargs
+        state.chatbot = chatbot
+        state.callback_fn = callback_fn
+        return state
+
+    def continue_game(self, prompt, chatbot, history):
+        # 游戏主体
+        yield from self.step(prompt, chatbot, history)
+        self.step_cnt += 1
+        # 保存状态，收尾
+        self.dump_state(chatbot)
+        # 如果游戏结束，清理
+        if self.delete_game:
+            chatbot._cookies['lock_plugin'] = None
+            chatbot._cookies[f'plugin_state/{self.get_plugin_name()}'] = None
+        yield from update_ui(chatbot=chatbot, history=history)

crazy_functions/pdf_fns/breakdown_txt.py

@@ -0,0 +1,125 @@
+from crazy_functions.ipc_fns.mp import run_in_subprocess_with_timeout
+
+def force_breakdown(txt, limit, get_token_fn):
+    """ 当无法用标点、空行分割时，我们用最暴力的方法切割
+    """
+    for i in reversed(range(len(txt))):
+        if get_token_fn(txt[:i]) < limit:
+            return txt[:i], txt[i:]
+    return "Tiktoken未知错误", "Tiktoken未知错误"
+
+
+def maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage):
+    """ 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
+    当 remain_txt_to_cut < `_min` 时，我们再把 remain_txt_to_cut_storage 中的部分文字取出
+    """
+    _min = int(5e4)
+    _max = int(1e5)
+    # print(len(remain_txt_to_cut), len(remain_txt_to_cut_storage))
+    if len(remain_txt_to_cut) < _min and len(remain_txt_to_cut_storage) > 0:
+        remain_txt_to_cut = remain_txt_to_cut + remain_txt_to_cut_storage
+        remain_txt_to_cut_storage = ""
+    if len(remain_txt_to_cut) > _max:
+        remain_txt_to_cut_storage = remain_txt_to_cut[_max:] + remain_txt_to_cut_storage
+        remain_txt_to_cut = remain_txt_to_cut[:_max]
+    return remain_txt_to_cut, remain_txt_to_cut_storage
+
+
+def cut(limit, get_token_fn, txt_tocut, must_break_at_empty_line, break_anyway=False):
+    """ 文本切分
+    """
+    res = []
+    total_len = len(txt_tocut)
+    fin_len = 0
+    remain_txt_to_cut = txt_tocut
+    remain_txt_to_cut_storage = ""
+    # 为了加速计算，我们采样一个特殊的手段。当 remain_txt_to_cut > `_max` 时， 我们把 _max 后的文字转存至 remain_txt_to_cut_storage
+    remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
+
+    while True:
+        if get_token_fn(remain_txt_to_cut) <= limit:
+            # 如果剩余文本的token数小于限制，那么就不用切了
+            res.append(remain_txt_to_cut); fin_len+=len(remain_txt_to_cut)
+            break
+        else:
+            # 如果剩余文本的token数大于限制，那么就切
+            lines = remain_txt_to_cut.split('\n')
+
+            # 估计一个切分点
+            estimated_line_cut = limit / get_token_fn(remain_txt_to_cut) * len(lines)
+            estimated_line_cut = int(estimated_line_cut)
+
+            # 开始查找合适切分点的偏移（cnt）
+            cnt = 0
+            for cnt in reversed(range(estimated_line_cut)):
+                if must_break_at_empty_line:
+                    # 首先尝试用双空行（\n\n）作为切分点
+                    if lines[cnt] != "":
+                        continue
+                prev = "\n".join(lines[:cnt])
+                post = "\n".join(lines[cnt:])
+                if get_token_fn(prev) < limit:
+                    break
+
+            if cnt == 0:
+                # 如果没有找到合适的切分点
+                if break_anyway:
+                    # 是否允许暴力切分
+                    prev, post = force_breakdown(remain_txt_to_cut, limit, get_token_fn)
+                else:
+                    # 不允许直接报错
+                    raise RuntimeError(f"存在一行极长的文本！{remain_txt_to_cut}")
+
+            # 追加列表
+            res.append(prev); fin_len+=len(prev)
+            # 准备下一次迭代
+            remain_txt_to_cut = post
+            remain_txt_to_cut, remain_txt_to_cut_storage = maintain_storage(remain_txt_to_cut, remain_txt_to_cut_storage)
+            process = fin_len/total_len
+            print(f'正在文本切分 {int(process*100)}%')
+            if len(remain_txt_to_cut.strip()) == 0:
+                break
+    return res
+
+
+def breakdown_text_to_satisfy_token_limit_(txt, limit, llm_model="gpt-3.5-turbo"):
+    """ 使用多种方式尝试切分文本，以满足 token 限制
+    """
+    from request_llms.bridge_all import model_info
+    enc = model_info[llm_model]['tokenizer']
+    def get_token_fn(txt): return len(enc.encode(txt, disallowed_special=()))
+    try:
+        # 第1次尝试，将双空行（\n\n）作为切分点
+        return cut(limit, get_token_fn, txt, must_break_at_empty_line=True)
+    except RuntimeError:
+        try:
+            # 第2次尝试，将单空行（\n）作为切分点
+            return cut(limit, get_token_fn, txt, must_break_at_empty_line=False)
+        except RuntimeError:
+            try:
+                # 第3次尝试，将英文句号（.）作为切分点
+                res = cut(limit, get_token_fn, txt.replace('.', '。\n'), must_break_at_empty_line=False) # 这个中文的句号是故意的，作为一个标识而存在
+                return [r.replace('。\n', '.') for r in res]
+            except RuntimeError as e:
+                try:
+                    # 第4次尝试，将中文句号（。）作为切分点
+                    res = cut(limit, get_token_fn, txt.replace('。', '。。\n'), must_break_at_empty_line=False)
+                    return [r.replace('。。\n', '。') for r in res]
+                except RuntimeError as e:
+                    # 第5次尝试，没办法了，随便切一下吧
+                    return cut(limit, get_token_fn, txt, must_break_at_empty_line=False, break_anyway=True)
+
+breakdown_text_to_satisfy_token_limit = run_in_subprocess_with_timeout(breakdown_text_to_satisfy_token_limit_, timeout=60)
+
+if __name__ == '__main__':
+    from crazy_functions.crazy_utils import read_and_clean_pdf_text
+    file_content, page_one = read_and_clean_pdf_text("build/assets/at.pdf")
+
+    from request_llms.bridge_all import model_info
+    for i in range(5):
+        file_content += file_content
+
+    print(len(file_content))
+    TOKEN_LIMIT_PER_FRAGMENT = 2500
+    res = breakdown_text_to_satisfy_token_limit(file_content, TOKEN_LIMIT_PER_FRAGMENT)
+

crazy_functions/pdf_fns/parse_pdf.py

@@ -14,7 +14,7 @@ import math
 class GROBID_OFFLINE_EXCEPTION(Exception): pass
 
 def get_avail_grobid_url():
-    GROBID_URLS, = get_conf('GROBID_URLS')
+    GROBID_URLS = get_conf('GROBID_URLS')
     if len(GROBID_URLS) == 0: return None
     try:
         _grobid_url = random.choice(GROBID_URLS) # 随机负载均衡
@@ -64,8 +64,8 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
             # 再做一个小修改：重新修改当前part的标题，默认用英文的
             cur_value += value
             translated_res_array.append(cur_value)
-    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + translated_res_array, 
-                                     file_basename = f"{gen_time_str()}-translated_only.md", 
+    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + translated_res_array,
+                                     file_basename = f"{gen_time_str()}-translated_only.md",
                                      file_fullname = None,
                                      auto_caption = False)
     promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
@@ -73,8 +73,8 @@ def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chat
     return res_path
 
 def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
-    from crazy_functions.crazy_utils import construct_html
-    from crazy_functions.crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+    from crazy_functions.pdf_fns.report_gen_html import construct_html
+    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
     from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
     from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
@@ -82,7 +82,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
     # title
     title = article_dict.get('title', '无法获取 title'); prompt += f'title:{title}\n\n'
     # authors
-    authors = article_dict.get('authors', '无法获取 authors'); prompt += f'authors:{authors}\n\n'
+    authors = article_dict.get('authors', '无法获取 authors')[:100]; prompt += f'authors:{authors}\n\n'
     # abstract
     abstract = article_dict.get('abstract', '无法获取 abstract'); prompt += f'abstract:{abstract}\n\n'
     # command
@@ -103,7 +103,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
     inputs_show_user_array = []
 
     # get_token_num
-    from request_llm.bridge_all import model_info
+    from request_llms.bridge_all import model_info
     enc = model_info[llm_kwargs['llm_model']]['tokenizer']
     def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
 
@@ -116,7 +116,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
             # find a smooth token limit to achieve even seperation
             count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
             token_limit_smooth = raw_token_num // count + count
-            return breakdown_txt_to_satisfy_token_limit_for_pdf(txt, get_token_fn=get_token_num, limit=token_limit_smooth)
+            return breakdown_text_to_satisfy_token_limit(txt, limit=token_limit_smooth, llm_model=llm_kwargs['llm_model'])
 
     for section in article_dict.get('sections'):
         if len(section['text']) == 0: continue
@@ -144,11 +144,11 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
     produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
 
     # -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
-    ch = construct_html() 
+    ch = construct_html()
     orig = ""
     trans = ""
     gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-    for i,k in enumerate(gpt_response_collection_html): 
+    for i,k in enumerate(gpt_response_collection_html):
         if i%2==0:
             gpt_response_collection_html[i] = inputs_show_user_array[i//2]
         else:
@@ -159,7 +159,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
 
     final = ["", "", "一、论文概况",  "", "Abstract", paper_meta_info,  "二、论文翻译",  ""]
     final.extend(gpt_response_collection_html)
-    for i, k in enumerate(final): 
+    for i, k in enumerate(final):
         if i%2==0:
             orig = k
         if i%2==1:

crazy_functions/pdf_fns/parse_word.py

@@ -0,0 +1,85 @@
+from crazy_functions.crazy_utils import read_and_clean_pdf_text, get_files_from_everything
+import os
+import re
+def extract_text_from_files(txt, chatbot, history):
+    """
+    查找pdf/md/word并获取文本内容并返回状态以及文本
+
+    输入参数 Args:
+        chatbot: chatbot inputs and outputs （用户界面对话窗口句柄，用于数据流可视化）
+        history (list): List of chat history （历史，对话历史列表）
+
+    输出 Returns:
+        文件是否存在(bool)
+        final_result(list):文本内容
+        page_one(list):第一页内容/摘要
+        file_manifest(list):文件路径
+        excption(string):需要用户手动处理的信息,如没出错则保持为空
+    """
+
+    final_result = []
+    page_one = []
+    file_manifest = []
+    excption = ""
+
+    if txt == "":
+        final_result.append(txt)
+        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+
+    #查找输入区内容中的文件
+    file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
+    file_md,md_manifest,folder_md = get_files_from_everything(txt, '.md')
+    file_word,word_manifest,folder_word = get_files_from_everything(txt, '.docx')
+    file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
+
+    if file_doc:
+        excption = "word"
+        return False, final_result, page_one, file_manifest, excption
+
+    file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
+    if file_num == 0:
+        final_result.append(txt)
+        return False, final_result, page_one, file_manifest, excption   #如输入区内容不是文件则直接返回输入区内容
+
+    if file_pdf:
+        try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+            import fitz
+        except:
+            excption = "pdf"
+            return False, final_result, page_one, file_manifest, excption
+        for index, fp in enumerate(pdf_manifest):
+            file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
+            file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+            pdf_one = str(pdf_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
+            final_result.append(file_content)
+            page_one.append(pdf_one)
+            file_manifest.append(os.path.relpath(fp, folder_pdf))
+
+    if file_md:
+        for index, fp in enumerate(md_manifest):
+            with open(fp, 'r', encoding='utf-8', errors='replace') as f:
+                file_content = f.read()
+            file_content = file_content.encode('utf-8', 'ignore').decode()
+            headers = re.findall(r'^#\s(.*)$', file_content, re.MULTILINE)  #接下来提取md中的一级/二级标题作为摘要
+            if len(headers) > 0:
+                page_one.append("\n".join(headers)) #合并所有的标题,以换行符分割
+            else:
+                page_one.append("")
+            final_result.append(file_content)
+            file_manifest.append(os.path.relpath(fp, folder_md))
+
+    if file_word:
+        try:    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+            from docx import Document
+        except:
+            excption = "word_pip"
+            return False, final_result, page_one, file_manifest, excption
+        for index, fp in enumerate(word_manifest):
+            doc = Document(fp)
+            file_content = '\n'.join([p.text for p in doc.paragraphs])
+            file_content = file_content.encode('utf-8', 'ignore').decode()
+            page_one.append(file_content[:200])
+            final_result.append(file_content)
+            file_manifest.append(os.path.relpath(fp, folder_word))
+
+    return True, final_result, page_one, file_manifest, excption

crazy_functions/pdf_fns/report_gen_html.py

@@ -0,0 +1,58 @@
+from toolbox import update_ui, get_conf, trimmed_format_exc, get_log_folder
+import os
+
+
+
+
+class construct_html():
+    def __init__(self) -> None:
+        self.html_string = ""
+
+    def add_row(self, a, b):
+        from toolbox import markdown_convertion
+        template = """
+            {
+                primary_col: {
+                    header: String.raw`__PRIMARY_HEADER__`,
+                    msg: String.raw`__PRIMARY_MSG__`,
+                },
+                secondary_rol: {
+                    header: String.raw`__SECONDARY_HEADER__`,
+                    msg: String.raw`__SECONDARY_MSG__`,
+                }
+            },
+        """
+        def std(str):
+            str = str.replace(r'`',r'`')
+            if str.endswith("\\"): str += ' '
+            if str.endswith("}"): str += ' '
+            if str.endswith("$"): str += ' '
+            return str
+
+        template_ = template
+        a_lines = a.split('\n')
+        b_lines = b.split('\n')
+
+        if len(a_lines) == 1 or len(a_lines[0]) > 50:
+            template_ = template_.replace("__PRIMARY_HEADER__", std(a[:20]))
+            template_ = template_.replace("__PRIMARY_MSG__", std(markdown_convertion(a)))
+        else:
+            template_ = template_.replace("__PRIMARY_HEADER__", std(a_lines[0]))
+            template_ = template_.replace("__PRIMARY_MSG__", std(markdown_convertion('\n'.join(a_lines[1:]))))
+
+        if len(b_lines) == 1 or len(b_lines[0]) > 50:
+            template_ = template_.replace("__SECONDARY_HEADER__", std(b[:20]))
+            template_ = template_.replace("__SECONDARY_MSG__", std(markdown_convertion(b)))
+        else:
+            template_ = template_.replace("__SECONDARY_HEADER__", std(b_lines[0]))
+            template_ = template_.replace("__SECONDARY_MSG__", std(markdown_convertion('\n'.join(b_lines[1:]))))
+        self.html_string += template_
+
+    def save_file(self, file_name):
+        from toolbox import get_log_folder
+        with open('crazy_functions/pdf_fns/report_template.html', 'r', encoding='utf8') as f:
+            html_template = f.read()
+        html_template = html_template.replace("__TF_ARR__", self.html_string)
+        with open(os.path.join(get_log_folder(), file_name), 'w', encoding='utf8') as f:
+            f.write(html_template.encode('utf-8', 'ignore').decode())
+        return os.path.join(get_log_folder(), file_name)

crazy_functions/pdf_fns/report_template_v2.html

@@ -0,0 +1,73 @@
+<!DOCTYPE html>
+<html xmlns="http://www.w3.org/1999/xhtml">
+
+<head>
+    <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" />
+    <title>GPT-Academic 翻译报告书</title>
+    <style>
+        .centered-a {
+            color: red;
+            text-align: center;
+            margin-bottom: 2%;
+            font-size: 1.5em;
+        }
+        .centered-b {
+            color: red;
+            text-align: center;
+            margin-top: 10%;
+            margin-bottom: 20%;
+            font-size: 1.5em;
+        }
+        .centered-c {
+            color: rgba(255, 0, 0, 0);
+            text-align: center;
+            margin-top: 2%;
+            margin-bottom: 20%;
+            font-size: 7em;
+        }
+    </style>
+<script>
+        // Configure MathJax settings
+        MathJax = {
+            tex: {
+                inlineMath: [
+                    ['$', '$'],
+                    ['\(', '\)']
+                ]
+            }
+        }
+        addEventListener('zero-md-rendered', () => {MathJax.typeset(); console.log('MathJax typeset!');})
+    </script>
+    <!-- Load MathJax library -->
+    <script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml.js"></script>
+    <script
+        type="module"
+        src="https://cdn.jsdelivr.net/gh/zerodevx/zero-md@2/dist/zero-md.min.js"
+    ></script>
+
+</head>
+
+<body>
+    <div class="test_temp1" style="width:10%; height: 500px; float:left;">
+
+    </div>
+    <div class="test_temp2" style="width:80%; height: 500px; float:left;">
+        <!-- Simply set the `src` attribute to your MD file and win -->
+        <div class="centered-a">
+            请按Ctrl+S保存此页面，否则该页面可能在几分钟后失效。
+        </div>
+        <zero-md src="translated_markdown.md" no-shadow>
+        </zero-md>
+        <div class="centered-b">
+            本报告由GPT-Academic开源项目生成，地址：https://github.com/binary-husky/gpt_academic。
+        </div>
+        <div class="centered-c">
+            本报告由GPT-Academic开源项目生成，地址：https://github.com/binary-husky/gpt_academic。
+        </div>
+    </div>
+    <div class="test_temp3" style="width:10%; height: 500px; float:left;">
+    </div>
+
+    </body>
+
+</html>

crazy_functions/vector_fns/general_file_loader.py

@@ -0,0 +1,70 @@
+# From project chatglm-langchain
+
+
+from langchain.document_loaders import UnstructuredFileLoader
+from langchain.text_splitter import CharacterTextSplitter
+import re
+from typing import List
+
+class ChineseTextSplitter(CharacterTextSplitter):
+    def __init__(self, pdf: bool = False, sentence_size: int = None, **kwargs):
+        super().__init__(**kwargs)
+        self.pdf = pdf
+        self.sentence_size = sentence_size
+
+    def split_text1(self, text: str) -> List[str]:
+        if self.pdf:
+            text = re.sub(r"\n{3,}", "\n", text)
+            text = re.sub('\s', ' ', text)
+            text = text.replace("\n\n", "")
+        sent_sep_pattern = re.compile('([﹒﹔﹖﹗．。！？]["’”」』]{0,2}|(?=["‘“「『]{1,2}|$))')  # del ：；
+        sent_list = []
+        for ele in sent_sep_pattern.split(text):
+            if sent_sep_pattern.match(ele) and sent_list:
+                sent_list[-1] += ele
+            elif ele:
+                sent_list.append(ele)
+        return sent_list
+
+    def split_text(self, text: str) -> List[str]:   ##此处需要进一步优化逻辑
+        if self.pdf:
+            text = re.sub(r"\n{3,}", r"\n", text)
+            text = re.sub('\s', " ", text)
+            text = re.sub("\n\n", "", text)
+
+        text = re.sub(r'([;；.!?。！？\?])([^”’])', r"\1\n\2", text)  # 单字符断句符
+        text = re.sub(r'(\.{6})([^"’”」』])', r"\1\n\2", text)  # 英文省略号
+        text = re.sub(r'(\…{2})([^"’”」』])', r"\1\n\2", text)  # 中文省略号
+        text = re.sub(r'([;；!?。！？\?]["’”」』]{0,2})([^;；!?，。！？\?])', r'\1\n\2', text)
+        # 如果双引号前有终止符，那么双引号才是句子的终点，把分句符\n放到双引号后，注意前面的几句都小心保留了双引号
+        text = text.rstrip()  # 段尾如果有多余的\n就去掉它
+        # 很多规则中会考虑分号;，但是这里我把它忽略不计，破折号、英文双引号等同样忽略，需要的再做些简单调整即可。
+        ls = [i for i in text.split("\n") if i]
+        for ele in ls:
+            if len(ele) > self.sentence_size:
+                ele1 = re.sub(r'([,，.]["’”」』]{0,2})([^,，.])', r'\1\n\2', ele)
+                ele1_ls = ele1.split("\n")
+                for ele_ele1 in ele1_ls:
+                    if len(ele_ele1) > self.sentence_size:
+                        ele_ele2 = re.sub(r'([\n]{1,}| {2,}["’”」』]{0,2})([^\s])', r'\1\n\2', ele_ele1)
+                        ele2_ls = ele_ele2.split("\n")
+                        for ele_ele2 in ele2_ls:
+                            if len(ele_ele2) > self.sentence_size:
+                                ele_ele3 = re.sub('( ["’”」』]{0,2})([^ ])', r'\1\n\2', ele_ele2)
+                                ele2_id = ele2_ls.index(ele_ele2)
+                                ele2_ls = ele2_ls[:ele2_id] + [i for i in ele_ele3.split("\n") if i] + ele2_ls[
+                                                                                                       ele2_id + 1:]
+                        ele_id = ele1_ls.index(ele_ele1)
+                        ele1_ls = ele1_ls[:ele_id] + [i for i in ele2_ls if i] + ele1_ls[ele_id + 1:]
+
+                id = ls.index(ele)
+                ls = ls[:id] + [i for i in ele1_ls if i] + ls[id + 1:]
+        return ls
+
+def load_file(filepath, sentence_size):
+    loader = UnstructuredFileLoader(filepath, mode="elements")
+    textsplitter = ChineseTextSplitter(pdf=False, sentence_size=sentence_size)
+    docs = loader.load_and_split(text_splitter=textsplitter)
+    # write_check_file(filepath, docs)
+    return docs
+

crazy_functions/vector_fns/vector_database.py

@@ -0,0 +1,338 @@
+# From project chatglm-langchain
+
+import threading
+from toolbox import Singleton
+import os
+import shutil
+import os
+import uuid
+import tqdm
+from langchain.vectorstores import FAISS
+from langchain.docstore.document import Document
+from typing import List, Tuple
+import numpy as np
+from crazy_functions.vector_fns.general_file_loader import load_file
+
+embedding_model_dict = {
+    "ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
+    "ernie-base": "nghuyong/ernie-3.0-base-zh",
+    "text2vec-base": "shibing624/text2vec-base-chinese",
+    "text2vec": "GanymedeNil/text2vec-large-chinese",
+}
+
+# Embedding model name
+EMBEDDING_MODEL = "text2vec"
+
+# Embedding running device
+EMBEDDING_DEVICE = "cpu"
+
+# 基于上下文的prompt模版，请务必保留"{question}"和"{context}"
+PROMPT_TEMPLATE = """已知信息：
+{context}
+
+根据上述已知信息，简洁和专业的来回答用户的问题。如果无法从中得到答案，请说 “根据已知信息无法回答该问题” 或 “没有提供足够的相关信息”，不允许在答案中添加编造成分，答案请使用中文。 问题是：{question}"""
+
+# 文本分句长度
+SENTENCE_SIZE = 100
+
+# 匹配后单段上下文长度
+CHUNK_SIZE = 250
+
+# LLM input history length
+LLM_HISTORY_LEN = 3
+
+# return top-k text chunk from vector store
+VECTOR_SEARCH_TOP_K = 5
+
+# 知识检索内容相关度 Score, 数值范围约为0-1100，如果为0，则不生效，经测试设置为小于500时，匹配结果更精准
+VECTOR_SEARCH_SCORE_THRESHOLD = 0
+
+NLTK_DATA_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "nltk_data")
+
+FLAG_USER_NAME = uuid.uuid4().hex
+
+# 是否开启跨域，默认为False，如果需要开启，请设置为True
+# is open cross domain
+OPEN_CROSS_DOMAIN = False
+
+def similarity_search_with_score_by_vector(
+        self, embedding: List[float], k: int = 4
+) -> List[Tuple[Document, float]]:
+
+    def seperate_list(ls: List[int]) -> List[List[int]]:
+        lists = []
+        ls1 = [ls[0]]
+        for i in range(1, len(ls)):
+            if ls[i - 1] + 1 == ls[i]:
+                ls1.append(ls[i])
+            else:
+                lists.append(ls1)
+                ls1 = [ls[i]]
+        lists.append(ls1)
+        return lists
+
+    scores, indices = self.index.search(np.array([embedding], dtype=np.float32), k)
+    docs = []
+    id_set = set()
+    store_len = len(self.index_to_docstore_id)
+    for j, i in enumerate(indices[0]):
+        if i == -1 or 0 < self.score_threshold < scores[0][j]:
+            # This happens when not enough docs are returned.
+            continue
+        _id = self.index_to_docstore_id[i]
+        doc = self.docstore.search(_id)
+        if not self.chunk_conent:
+            if not isinstance(doc, Document):
+                raise ValueError(f"Could not find document for id {_id}, got {doc}")
+            doc.metadata["score"] = int(scores[0][j])
+            docs.append(doc)
+            continue
+        id_set.add(i)
+        docs_len = len(doc.page_content)
+        for k in range(1, max(i, store_len - i)):
+            break_flag = False
+            for l in [i + k, i - k]:
+                if 0 <= l < len(self.index_to_docstore_id):
+                    _id0 = self.index_to_docstore_id[l]
+                    doc0 = self.docstore.search(_id0)
+                    if docs_len + len(doc0.page_content) > self.chunk_size:
+                        break_flag = True
+                        break
+                    elif doc0.metadata["source"] == doc.metadata["source"]:
+                        docs_len += len(doc0.page_content)
+                        id_set.add(l)
+            if break_flag:
+                break
+    if not self.chunk_conent:
+        return docs
+    if len(id_set) == 0 and self.score_threshold > 0:
+        return []
+    id_list = sorted(list(id_set))
+    id_lists = seperate_list(id_list)
+    for id_seq in id_lists:
+        for id in id_seq:
+            if id == id_seq[0]:
+                _id = self.index_to_docstore_id[id]
+                doc = self.docstore.search(_id)
+            else:
+                _id0 = self.index_to_docstore_id[id]
+                doc0 = self.docstore.search(_id0)
+                doc.page_content += " " + doc0.page_content
+        if not isinstance(doc, Document):
+            raise ValueError(f"Could not find document for id {_id}, got {doc}")
+        doc_score = min([scores[0][id] for id in [indices[0].tolist().index(i) for i in id_seq if i in indices[0]]])
+        doc.metadata["score"] = int(doc_score)
+        docs.append(doc)
+    return docs
+
+
+class LocalDocQA:
+    llm: object = None
+    embeddings: object = None
+    top_k: int = VECTOR_SEARCH_TOP_K
+    chunk_size: int = CHUNK_SIZE
+    chunk_conent: bool = True
+    score_threshold: int = VECTOR_SEARCH_SCORE_THRESHOLD
+
+    def init_cfg(self,
+                 top_k=VECTOR_SEARCH_TOP_K,
+                 ):
+
+        self.llm = None
+        self.top_k = top_k
+
+    def init_knowledge_vector_store(self,
+                                    filepath,
+                                    vs_path: str or os.PathLike = None,
+                                    sentence_size=SENTENCE_SIZE,
+                                    text2vec=None):
+        loaded_files = []
+        failed_files = []
+        if isinstance(filepath, str):
+            if not os.path.exists(filepath):
+                print("路径不存在")
+                return None
+            elif os.path.isfile(filepath):
+                file = os.path.split(filepath)[-1]
+                try:
+                    docs = load_file(filepath, SENTENCE_SIZE)
+                    print(f"{file} 已成功加载")
+                    loaded_files.append(filepath)
+                except Exception as e:
+                    print(e)
+                    print(f"{file} 未能成功加载")
+                    return None
+            elif os.path.isdir(filepath):
+                docs = []
+                for file in tqdm(os.listdir(filepath), desc="加载文件"):
+                    fullfilepath = os.path.join(filepath, file)
+                    try:
+                        docs += load_file(fullfilepath, SENTENCE_SIZE)
+                        loaded_files.append(fullfilepath)
+                    except Exception as e:
+                        print(e)
+                        failed_files.append(file)
+
+                if len(failed_files) > 0:
+                    print("以下文件未能成功加载：")
+                    for file in failed_files:
+                        print(f"{file}\n")
+
+        else:
+            docs = []
+            for file in filepath:
+                docs += load_file(file, SENTENCE_SIZE)
+                print(f"{file} 已成功加载")
+                loaded_files.append(file)
+
+        if len(docs) > 0:
+            print("文件加载完毕，正在生成向量库")
+            if vs_path and os.path.isdir(vs_path):
+                try:
+                    self.vector_store = FAISS.load_local(vs_path, text2vec)
+                    self.vector_store.add_documents(docs)
+                except:
+                    self.vector_store = FAISS.from_documents(docs, text2vec)
+            else:
+                self.vector_store = FAISS.from_documents(docs, text2vec)  # docs 为Document列表
+
+            self.vector_store.save_local(vs_path)
+            return vs_path, loaded_files
+        else:
+            raise RuntimeError("文件加载失败，请检查文件格式是否正确")
+
+    def get_loaded_file(self, vs_path):
+        ds = self.vector_store.docstore
+        return set([ds._dict[k].metadata['source'].split(vs_path)[-1] for k in ds._dict])
+
+
+    # query      查询内容
+    # vs_path    知识库路径
+    # chunk_conent   是否启用上下文关联
+    # score_threshold    搜索匹配score阈值
+    # vector_search_top_k   搜索知识库内容条数，默认搜索5条结果
+    # chunk_sizes    匹配单段内容的连接上下文长度
+    def get_knowledge_based_conent_test(self, query, vs_path, chunk_conent,
+                                        score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
+                                        vector_search_top_k=VECTOR_SEARCH_TOP_K, chunk_size=CHUNK_SIZE,
+                                        text2vec=None):
+        self.vector_store = FAISS.load_local(vs_path, text2vec)
+        self.vector_store.chunk_conent = chunk_conent
+        self.vector_store.score_threshold = score_threshold
+        self.vector_store.chunk_size = chunk_size
+
+        embedding = self.vector_store.embedding_function.embed_query(query)
+        related_docs_with_score = similarity_search_with_score_by_vector(self.vector_store, embedding, k=vector_search_top_k)
+
+        if not related_docs_with_score:
+            response = {"query": query,
+                        "source_documents": []}
+            return response, ""
+        # prompt = f"{query}. You should answer this question using information from following documents: \n\n"
+        prompt = f"{query}. 你必须利用以下文档中包含的信息回答这个问题: \n\n---\n\n"
+        prompt += "\n\n".join([f"({k}): " + doc.page_content for k, doc in enumerate(related_docs_with_score)])
+        prompt += "\n\n---\n\n"
+        prompt = prompt.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+        # print(prompt)
+        response = {"query": query, "source_documents": related_docs_with_score}
+        return response, prompt
+
+
+
+
+def construct_vector_store(vs_id, vs_path, files, sentence_size, history, one_conent, one_content_segmentation, text2vec):
+    for file in files:
+        assert os.path.exists(file), "输入文件不存在：" + file
+    import nltk
+    if NLTK_DATA_PATH not in nltk.data.path: nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
+    local_doc_qa = LocalDocQA()
+    local_doc_qa.init_cfg()
+    filelist = []
+    if not os.path.exists(os.path.join(vs_path, vs_id)):
+        os.makedirs(os.path.join(vs_path, vs_id))
+    for file in files:
+        file_name = file.name if not isinstance(file, str) else file
+        filename = os.path.split(file_name)[-1]
+        shutil.copyfile(file_name, os.path.join(vs_path, vs_id, filename))
+        filelist.append(os.path.join(vs_path, vs_id, filename))
+    vs_path, loaded_files = local_doc_qa.init_knowledge_vector_store(filelist, os.path.join(vs_path, vs_id), sentence_size, text2vec)
+
+    if len(loaded_files):
+        file_status = f"已添加 {'、'.join([os.path.split(i)[-1] for i in loaded_files if i])} 内容至知识库，并已加载知识库，请开始提问"
+    else:
+        pass
+        # file_status = "文件未成功加载，请重新上传文件"
+    # print(file_status)
+    return local_doc_qa, vs_path
+
+@Singleton
+class knowledge_archive_interface():
+    def __init__(self) -> None:
+        self.threadLock = threading.Lock()
+        self.current_id = ""
+        self.kai_path = None
+        self.qa_handle = None
+        self.text2vec_large_chinese = None
+
+    def get_chinese_text2vec(self):
+        if self.text2vec_large_chinese is None:
+            # < -------------------预热文本向量化模组--------------- >
+            from toolbox import ProxyNetworkActivate
+            print('Checking Text2vec ...')
+            from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+            with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
+                self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
+
+        return self.text2vec_large_chinese
+
+
+    def feed_archive(self, file_manifest, vs_path, id="default"):
+        self.threadLock.acquire()
+        # import uuid
+        self.current_id = id
+        self.qa_handle, self.kai_path = construct_vector_store(
+            vs_id=self.current_id,
+            vs_path=vs_path,
+            files=file_manifest,
+            sentence_size=100,
+            history=[],
+            one_conent="",
+            one_content_segmentation="",
+            text2vec = self.get_chinese_text2vec(),
+        )
+        self.threadLock.release()
+
+    def get_current_archive_id(self):
+        return self.current_id
+
+    def get_loaded_file(self, vs_path):
+        return self.qa_handle.get_loaded_file(vs_path)
+
+    def answer_with_archive_by_id(self, txt, id, vs_path):
+        self.threadLock.acquire()
+        if not self.current_id == id:
+            self.current_id = id
+            self.qa_handle, self.kai_path = construct_vector_store(
+                vs_id=self.current_id,
+                vs_path=vs_path,
+                files=[],
+                sentence_size=100,
+                history=[],
+                one_conent="",
+                one_content_segmentation="",
+                text2vec = self.get_chinese_text2vec(),
+            )
+        VECTOR_SEARCH_SCORE_THRESHOLD = 0
+        VECTOR_SEARCH_TOP_K = 4
+        CHUNK_SIZE = 512
+        resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
+            query = txt,
+            vs_path = self.kai_path,
+            score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
+            vector_search_top_k=VECTOR_SEARCH_TOP_K,
+            chunk_conent=True,
+            chunk_size=CHUNK_SIZE,
+            text2vec = self.get_chinese_text2vec(),
+        )
+        self.threadLock.release()
+        return resp, prompt

crazy_functions/vt_fns/vt_call_plugin.py

@@ -1,7 +1,7 @@
 from pydantic import BaseModel, Field
 from typing import List
 from toolbox import update_ui_lastest_msg, disable_auto_promotion
-from request_llm.bridge_all import predict_no_ui_long_connection
+from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
 import copy, json, pickle, os, sys, time
 
@@ -35,9 +35,9 @@ def get_recent_file_prompt_support(chatbot):
     most_recent_uploaded = chatbot._cookies.get("most_recent_uploaded", None)
     path = most_recent_uploaded['path']
     prompt =   "\nAdditional Information:\n"
-    prompt =   "In case that this plugin requires a path or a file as argument," 
-    prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`" 
-    prompt += f"Only use it when necessary, otherwise, you can ignore this file." 
+    prompt =   "In case that this plugin requires a path or a file as argument,"
+    prompt += f"it is important for you to know that the user has recently uploaded a file, located at: `{path}`"
+    prompt += f"Only use it when necessary, otherwise, you can ignore this file."
     return prompt
 
 def get_inputs_show_user(inputs, plugin_arr_enum_prompt):
@@ -82,7 +82,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
         msg += "\n但您可以尝试再试一次\n"
         yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
         return
-    
+
     # ⭐ ⭐ ⭐ 确认插件参数
     if not have_any_recent_upload_files(chatbot):
         appendix_info = ""
@@ -99,7 +99,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
     inputs = f"A plugin named {plugin_sel.plugin_selection} is selected, " + \
              "you should extract plugin_arg from the user requirement, the user requirement is: \n\n" + \
              ">> " + (txt + appendix_info).rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
-             gpt_json_io.format_instructions 
+             gpt_json_io.format_instructions
     run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
         inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
     plugin_sel = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)

crazy_functions/vt_fns/vt_modify_config.py

@@ -1,16 +1,16 @@
 from pydantic import BaseModel, Field
 from typing import List
 from toolbox import update_ui_lastest_msg, get_conf
-from request_llm.bridge_all import predict_no_ui_long_connection
+from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.json_fns.pydantic_io import GptJsonIO
 import copy, json, pickle, os, sys
 
 
 def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
-    ALLOW_RESET_CONFIG, = get_conf('ALLOW_RESET_CONFIG')
+    ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
     if not ALLOW_RESET_CONFIG:
         yield from update_ui_lastest_msg(
-            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。", 
+            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
             chatbot=chatbot, history=history, delay=2
         )
         return
@@ -35,7 +35,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     inputs = "Analyze how to change configuration according to following user input, answer me with json: \n\n" + \
              ">> " + txt.rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
              gpt_json_io.format_instructions
-    
+
     run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(
         inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
     user_intention = gpt_json_io.generate_output_auto_repair(run_gpt_fn(inputs, ""), run_gpt_fn)
@@ -45,11 +45,11 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     ok = (explicit_conf in txt)
     if ok:
         yield from update_ui_lastest_msg(
-            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}", 
+            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
             chatbot=chatbot, history=history, delay=1
         )
         yield from update_ui_lastest_msg(
-            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中", 
+            lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
             chatbot=chatbot, history=history, delay=2
         )
 
@@ -66,10 +66,10 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         )
 
 def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
-    ALLOW_RESET_CONFIG, = get_conf('ALLOW_RESET_CONFIG')
+    ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
     if not ALLOW_RESET_CONFIG:
         yield from update_ui_lastest_msg(
-            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。", 
+            lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
             chatbot=chatbot, history=history, delay=2
         )
         return

crazy_functions/vt_fns/vt_state.py

@@ -6,7 +6,7 @@ class VoidTerminalState():
 
     def reset_state(self):
         self.has_provided_explaination = False
- 
+
     def lock_plugin(self, chatbot):
         chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'
         chatbot._cookies['plugin_state'] = pickle.dumps(self)

crazy_functions/下载arxiv论文翻译摘要.py

@@ -1,6 +1,6 @@
 from toolbox import update_ui, get_log_folder
 from toolbox import write_history_to_file, promote_file_to_downloadzone
-from toolbox import CatchException, report_execption, get_conf
+from toolbox import CatchException, report_exception, get_conf
 import re, requests, unicodedata, os
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 def download_arxiv_(url_pdf):
@@ -43,7 +43,7 @@ def download_arxiv_(url_pdf):
     file_path = download_dir+title_str
 
     print('下载中')
-    proxies, = get_conf('proxies')
+    proxies = get_conf('proxies')
     r = requests.get(requests_pdf_url, proxies=proxies)
     with open(file_path, 'wb+') as f:
         f.write(r.content)
@@ -77,7 +77,7 @@ def get_name(_url_):
     #     print('在缓存中')
     #     return arxiv_recall[_url_]
 
-    proxies, = get_conf('proxies')
+    proxies = get_conf('proxies')
     res = requests.get(_url_, proxies=proxies)
 
     bs = BeautifulSoup(res.text, 'html.parser')
@@ -130,7 +130,7 @@ def get_name(_url_):
 
 
 @CatchException
-def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
 
     CRAZY_FUNCTION_INFO = "下载arxiv论文并翻译摘要，函数插件作者[binary-husky]。正在提取摘要并下载PDF文档……"
     import glob
@@ -144,8 +144,8 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
     try:
         import bs4
     except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade beautifulsoup4```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -157,12 +157,12 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
     try:
         pdf_path, info = download_arxiv_(txt)
     except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"下载pdf文件未成功")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     # 翻译摘要等
     i_say =            f"请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。材料如下：{str(info)}"
     i_say_show_user =  f'请你阅读以下学术论文相关的材料，提取摘要，翻译为中文。论文：{pdf_path}'

crazy_functions/互动小游戏.py

@@ -0,0 +1,40 @@
+from toolbox import CatchException, update_ui, update_ui_lastest_msg
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from request_llms.bridge_all import predict_no_ui_long_connection
+from crazy_functions.game_fns.game_utils import get_code_block, is_same_thing
+
+@CatchException
+def 随机小游戏(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    from crazy_functions.game_fns.game_interactive_story import MiniGame_ResumeStory
+    # 清空历史
+    history = []
+    # 选择游戏
+    cls = MiniGame_ResumeStory
+    # 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
+    state = cls.sync_state(chatbot,
+                           llm_kwargs,
+                           cls,
+                           plugin_name='MiniGame_ResumeStory',
+                           callback_fn='crazy_functions.互动小游戏->随机小游戏',
+                           lock_plugin=True
+                           )
+    yield from state.continue_game(prompt, chatbot, history)
+
+
+@CatchException
+def 随机小游戏1(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    from crazy_functions.game_fns.game_ascii_art import MiniGame_ASCII_Art
+    # 清空历史
+    history = []
+    # 选择游戏
+    cls = MiniGame_ASCII_Art
+    # 如果之前已经初始化了游戏实例，则继续该实例；否则重新初始化
+    state = cls.sync_state(chatbot,
+                           llm_kwargs,
+                           cls,
+                           plugin_name='MiniGame_ASCII_Art',
+                           callback_fn='crazy_functions.互动小游戏->随机小游戏1',
+                           lock_plugin=True
+                           )
+    yield from state.continue_game(prompt, chatbot, history)

crazy_functions/交互功能函数模板.py

@@ -3,7 +3,7 @@ from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
 
 @CatchException
-def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数, 如温度和top_p等, 一般原样传递下去就行
@@ -11,7 +11,7 @@ def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
     chatbot.append(("这是什么功能？", "交互功能函数模板。在执行完成之后, 可以将自身的状态存储到cookie中, 等待用户的再次调用。"))
@@ -38,7 +38,7 @@ def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         inputs=inputs_show_user=f"Extract all image urls in this html page, pick the first 5 images and show them with markdown format: \n\n {page_return}"
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
             inputs=inputs, inputs_show_user=inputs_show_user,
-            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
             sys_prompt="When you want to show an image, use markdown format. e.g. ![image_description](image_url). If there are no image url provided, answer 'no image url provided'"
         )
         chatbot[-1] = [chatbot[-1][0], gpt_say]

crazy_functions/函数动态生成.py

@@ -6,10 +6,10 @@
     - 将图像转为灰度图像
     - 将csv文件转excel表格
 
-Testing: 
-    - Crop the image, keeping the bottom half. 
-    - Swap the blue channel and red channel of the image. 
-    - Convert the image to grayscale. 
+Testing:
+    - Crop the image, keeping the bottom half.
+    - Swap the blue channel and red channel of the image.
+    - Convert the image to grayscale.
     - Convert the CSV file to an Excel spreadsheet.
 """
 
@@ -29,12 +29,12 @@ import multiprocessing
 
 templete = """
 ```python
-import ...  # Put dependencies here, e.g. import numpy as np. 
+import ...  # Put dependencies here, e.g. import numpy as np.
 
 class TerminalFunction(object): # Do not change the name of the class, The name of the class must be `TerminalFunction`
 
     def run(self, path):    # The name of the function must be `run`, it takes only a positional argument.
-        # rewrite the function you have just written here 
+        # rewrite the function you have just written here
         ...
         return generated_file_path
 ```
@@ -48,7 +48,7 @@ def get_code_block(reply):
     import re
     pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
     matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) == 1: 
+    if len(matches) == 1:
         return matches[0].strip('python') #  code block
     for match in matches:
         if 'class TerminalFunction' in match:
@@ -68,8 +68,8 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
 
     # 第一步
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=i_say, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo, 
+        inputs=i_say, inputs_show_user=i_say,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
         sys_prompt= r"You are a world-class programmer."
     )
     history.extend([i_say, gpt_say])
@@ -82,33 +82,33 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
     ]
     i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=inputs_show_user, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=i_say, inputs_show_user=inputs_show_user,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt= r"You are a programmer. You need to replace `...` with valid packages, do not give `...` in your answer!"
     )
     code_to_return = gpt_say
     history.extend([i_say, gpt_say])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
+
     # # 第三步
     # i_say = "Please list to packages to install to run the code above. Then show me how to use `try_install_deps` function to install them."
     # i_say += 'For instance. `try_install_deps(["opencv-python", "scipy", "numpy"])`'
     # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=inputs_show_user, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+    #     inputs=i_say, inputs_show_user=inputs_show_user,
+    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
     #     sys_prompt= r"You are a programmer."
     # )
 
-    # # # 第三步  
+    # # # 第三步
     # i_say = "Show me how to use `pip` to install packages to run the code above. "
     # i_say += 'For instance. `pip install -r opencv-python scipy numpy`'
     # installation_advance = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=i_say, inputs_show_user=i_say, 
-    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+    #     inputs=i_say, inputs_show_user=i_say,
+    #     llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
     #     sys_prompt= r"You are a programmer."
     # )
     installation_advance = ""
-    
+
     return code_to_return, installation_advance, txt, file_type, llm_kwargs, chatbot, history
 
 
@@ -117,7 +117,7 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
 def for_immediate_show_off_when_possible(file_type, fp, chatbot):
     if file_type in ['png', 'jpg']:
         image_path = os.path.abspath(fp)
-        chatbot.append(['这是一张图片, 展示如下:',  
+        chatbot.append(['这是一张图片, 展示如下:',
             f'本地文件地址: <br/>`{image_path}`<br/>'+
             f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
         ])
@@ -139,7 +139,7 @@ def get_recent_file_prompt_support(chatbot):
     return path
 
 @CatchException
-def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -147,7 +147,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
 
     # 清空历史
@@ -177,7 +177,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
         chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
         yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
         return  # 2. 如果没有文件
-    
+
     # 读取文件
     file_type = file_list[0].split('.')[-1]
 
@@ -185,7 +185,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     if is_the_upload_folder(txt):
         yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
         return
-    
+
     # 开始干正事
     MAX_TRY = 3
     for j in range(MAX_TRY):  # 最多重试5次
@@ -238,7 +238,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
             # chatbot.append(["如果是缺乏依赖，请参考以下建议", installation_advance])
             yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
             return
-        
+
         # 顺利完成，收尾
         res = str(res)
         if os.path.exists(res):
@@ -248,5 +248,5 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
             yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
         else:
             chatbot.append(["执行成功了，结果是一个字符串", "结果：" + res])
-            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新   
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
 

crazy_functions/命令行助手.py

@@ -4,7 +4,7 @@ from .crazy_utils import input_clipping
 import copy, json
 
 @CatchException
-def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本, 例如需要翻译的一段话, 再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数, 如温度和top_p等, 一般原样传递下去就行
@@ -12,7 +12,7 @@ def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     chatbot         聊天显示框的句柄, 用于显示给用户
     history         聊天历史, 前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     # 清空历史, 以免输入溢出
     history = []
@@ -21,8 +21,8 @@ def 命令行助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     i_say = "请写bash命令实现以下功能：" + txt
     # 开始
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        inputs=i_say, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
         sys_prompt="你是一个Linux大师级用户。注意，当我要求你写bash命令时，尽可能地仅用一行命令解决我的要求。"
     )
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新

crazy_functions/图片生成.py

@@ -1,14 +1,13 @@
 from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log_folder
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-import datetime
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicState
 
 
-def gen_image(llm_kwargs, prompt, resolution="256x256"):
+def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", quality=None, style=None):
     import requests, json, time, os
-    from request_llm.bridge_all import model_info
+    from request_llms.bridge_all import model_info
 
-    proxies, = get_conf('proxies')
-    # Set up OpenAI API key and model 
+    proxies = get_conf('proxies')
+    # Set up OpenAI API key and model
     api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
     chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
     # 'https://api.openai.com/v1/chat/completions'
@@ -23,8 +22,13 @@ def gen_image(llm_kwargs, prompt, resolution="256x256"):
         'prompt': prompt,
         'n': 1,
         'size': resolution,
+        'model': model,
         'response_format': 'url'
     }
+    if quality is not None:
+        data['quality'] = quality
+    if style is not None:
+        data['style'] = style
     response = requests.post(url, headers=headers, json=data, proxies=proxies)
     print(response.content)
     try:
@@ -42,28 +46,231 @@ def gen_image(llm_kwargs, prompt, resolution="256x256"):
     return image_url, file_path+file_name
 
 
+def edit_image(llm_kwargs, prompt, image_path, resolution="1024x1024", model="dall-e-2"):
+    import requests, json, time, os
+    from request_llms.bridge_all import model_info
+
+    proxies = get_conf('proxies')
+    api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
+    chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+    # 'https://api.openai.com/v1/chat/completions'
+    img_endpoint = chat_endpoint.replace('chat/completions','images/edits')
+    # # Generate the image
+    url = img_endpoint
+    n = 1
+    headers = {
+        'Authorization': f"Bearer {api_key}",
+    }
+    make_transparent(image_path, image_path+'.tsp.png')
+    make_square_image(image_path+'.tsp.png', image_path+'.tspsq.png')
+    resize_image(image_path+'.tspsq.png', image_path+'.ready.png', max_size=1024)
+    image_path = image_path+'.ready.png'
+    with open(image_path, 'rb') as f:
+        file_content = f.read()
+        files = {
+            'image': (os.path.basename(image_path), file_content),
+            # 'mask': ('mask.png', open('mask.png', 'rb'))
+            'prompt':   (None, prompt),
+            "n":        (None, str(n)),
+            'size':     (None, resolution),
+        }
+
+    response = requests.post(url, headers=headers, files=files, proxies=proxies)
+    print(response.content)
+    try:
+        image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
+    except:
+        raise RuntimeError(response.content.decode())
+    # 文件保存到本地
+    r = requests.get(image_url, proxies=proxies)
+    file_path = f'{get_log_folder()}/image_gen/'
+    os.makedirs(file_path, exist_ok=True)
+    file_name = 'Image' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.png'
+    with open(file_path+file_name, 'wb+') as f: f.write(r.content)
+
+
+    return image_url, file_path+file_name
+
 
 @CatchException
-def 图片生成(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
-    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
-    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数，暂时没有用武之地
-    chatbot         聊天显示框的句柄，用于显示给用户
-    history         聊天历史，前情提要
+    txt             输入栏用户输入的文本,例如需要翻译的一段话,再例如一个包含了待处理文件的路径
+    llm_kwargs      gpt模型参数,如温度和top_p等,一般原样传递下去就行
+    plugin_kwargs   插件模型的参数,暂时没有用武之地
+    chatbot         聊天显示框的句柄,用于显示给用户
+    history         聊天历史,前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
-    history = []    # 清空历史，以免输入溢出
-    chatbot.append(("这是什么功能？", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文效果不理想, 请尝试英文Prompt。正在处理中 ....."))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
+    history = []    # 清空历史,以免输入溢出
+    if prompt.strip() == "":
+        chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+        return
+    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
-    resolution = plugin_kwargs.get("advanced_arg", '256x256')
+    resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
     image_url, image_path = gen_image(llm_kwargs, prompt, resolution)
-    chatbot.append([prompt,  
+    chatbot.append([prompt,
         f'图像中转网址: <br/>`{image_url}`<br/>'+
         f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
         f'本地文件地址: <br/>`{image_path}`<br/>'+
         f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
     ])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+
+
+@CatchException
+def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    history = []    # 清空历史,以免输入溢出
+    if prompt.strip() == "":
+        chatbot.append((prompt, "[Local Message] 图像生成提示为空白，请在“输入区”输入图像生成提示。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+        return
+    chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    resolution_arg = plugin_kwargs.get("advanced_arg", '1024x1024-standard-vivid').lower()
+    parts = resolution_arg.split('-')
+    resolution = parts[0] # 解析分辨率
+    quality = 'standard' # 质量与风格默认值
+    style = 'vivid'
+    # 遍历检查是否有额外参数
+    for part in parts[1:]:
+        if part in ['hd', 'standard']:
+            quality = part
+        elif part in ['vivid', 'natural']:
+            style = part
+    image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality, style=style)
+    chatbot.append([prompt,
+        f'图像中转网址: <br/>`{image_url}`<br/>'+
+        f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
+        f'本地文件地址: <br/>`{image_path}`<br/>'+
+        f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
+    ])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+
+
+class ImageEditState(GptAcademicState):
+    # 尚未完成
+    def get_image_file(self, x):
+        import os, glob
+        if len(x) == 0:             return False, None
+        if not os.path.exists(x):   return False, None
+        if x.endswith('.png'):      return True, x
+        file_manifest = [f for f in glob.glob(f'{x}/**/*.png', recursive=True)]
+        confirm = (len(file_manifest) >= 1 and file_manifest[0].endswith('.png') and os.path.exists(file_manifest[0]))
+        file = None if not confirm else file_manifest[0]
+        return confirm, file
+
+    def lock_plugin(self, chatbot):
+        chatbot._cookies['lock_plugin'] = 'crazy_functions.图片生成->图片修改_DALLE2'
+        self.dump_state(chatbot)
+
+    def unlock_plugin(self, chatbot):
+        self.reset()
+        chatbot._cookies['lock_plugin'] = None
+        self.dump_state(chatbot)
+
+    def get_resolution(self, x):
+        return (x in ['256x256', '512x512', '1024x1024']), x
+
+    def get_prompt(self, x):
+        confirm = (len(x)>=5) and (not self.get_resolution(x)[0]) and (not self.get_image_file(x)[0])
+        return confirm, x
+
+    def reset(self):
+        self.req = [
+            {'value':None, 'description': '请先上传图像（必须是.png格式）, 然后再次点击本插件',                      'verify_fn': self.get_image_file},
+            {'value':None, 'description': '请输入分辨率,可选：256x256, 512x512 或 1024x1024, 然后再次点击本插件',   'verify_fn': self.get_resolution},
+            {'value':None, 'description': '请输入修改需求,建议您使用英文提示词, 然后再次点击本插件',                 'verify_fn': self.get_prompt},
+        ]
+        self.info = ""
+
+    def feed(self, prompt, chatbot):
+        for r in self.req:
+            if r['value'] is None:
+                confirm, res = r['verify_fn'](prompt)
+                if confirm:
+                    r['value'] = res
+                    self.dump_state(chatbot)
+                    break
+        return self
+
+    def next_req(self):
+        for r in self.req:
+            if r['value'] is None:
+                return r['description']
+        return "已经收集到所有信息"
+
+    def already_obtained_all_materials(self):
+        return all([x['value'] is not None for x in self.req])
+
+@CatchException
+def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    # 尚未完成
+    history = []    # 清空历史
+    state = ImageEditState.get_state(chatbot, ImageEditState)
+    state = state.feed(prompt, chatbot)
+    state.lock_plugin(chatbot)
+    if not state.already_obtained_all_materials():
+        chatbot.append(["图片修改\n\n1. 上传图片（图片中需要修改的位置用橡皮擦擦除为纯白色，即RGB=255,255,255）\n2. 输入分辨率 \n3. 输入修改需求", state.next_req()])
+        yield from update_ui(chatbot=chatbot, history=history)
+        return
+
+    image_path = state.req[0]['value']
+    resolution = state.req[1]['value']
+    prompt = state.req[2]['value']
+    chatbot.append(["图片修改, 执行中", f"图片:`{image_path}`<br/>分辨率:`{resolution}`<br/>修改需求:`{prompt}`"])
+    yield from update_ui(chatbot=chatbot, history=history)
+    image_url, image_path = edit_image(llm_kwargs, prompt, image_path, resolution)
+    chatbot.append([prompt,
+        f'图像中转网址: <br/>`{image_url}`<br/>'+
+        f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
+        f'本地文件地址: <br/>`{image_path}`<br/>'+
+        f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
+    ])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
+    state.unlock_plugin(chatbot)
+
+def make_transparent(input_image_path, output_image_path):
+    from PIL import Image
+    image = Image.open(input_image_path)
+    image = image.convert("RGBA")
+    data = image.getdata()
+    new_data = []
+    for item in data:
+        if item[0] == 255 and item[1] == 255 and item[2] == 255:
+            new_data.append((255, 255, 255, 0))
+        else:
+            new_data.append(item)
+    image.putdata(new_data)
+    image.save(output_image_path, "PNG")
+
+def resize_image(input_path, output_path, max_size=1024):
+    from PIL import Image
+    with Image.open(input_path) as img:
+        width, height = img.size
+        if width > max_size or height > max_size:
+            if width >= height:
+                new_width = max_size
+                new_height = int((max_size / width) * height)
+            else:
+                new_height = max_size
+                new_width = int((max_size / height) * width)
+
+            resized_img = img.resize(size=(new_width, new_height))
+            resized_img.save(output_path)
+        else:
+            img.save(output_path)
+
+def make_square_image(input_path, output_path):
+    from PIL import Image
+    with Image.open(input_path) as img:
+        width, height = img.size
+        size = max(width, height)
+        new_img = Image.new("RGBA", (size, size), color="black")
+        new_img.paste(img, ((size - width) // 2, (size - height) // 2))
+        new_img.save(output_path)

crazy_functions/多智能体.py

@@ -0,0 +1,101 @@
+# 本源代码中, ⭐ = 关键步骤
+"""
+测试：
+    - show me the solution of $x^2=cos(x)$, solve this problem with figure, and plot and save image to t.jpg
+
+"""
+
+
+from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
+from toolbox import get_conf, select_api_key, update_ui_lastest_msg, Singleton
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
+from crazy_functions.crazy_utils import input_clipping, try_install_deps
+from crazy_functions.agent_fns.persistent import GradioMultiuserManagerForPersistentClasses
+from crazy_functions.agent_fns.auto_agent import AutoGenMath
+import time
+
+def remove_model_prefix(llm):
+    if llm.startswith('api2d-'): llm = llm.replace('api2d-', '')
+    if llm.startswith('azure-'): llm = llm.replace('azure-', '')
+    return llm
+
+
+@CatchException
+def 多智能体终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    """
+    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
+    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
+    plugin_kwargs   插件模型的参数
+    chatbot         聊天显示框的句柄，用于显示给用户
+    history         聊天历史，前情提要
+    system_prompt   给gpt的静默提醒
+    user_request    当前用户的请求信息（IP地址等）
+    """
+    # 检查当前的模型是否符合要求
+    supported_llms = [
+        "gpt-3.5-turbo-16k",
+        'gpt-3.5-turbo-1106',
+        "gpt-4",
+        "gpt-4-32k",
+        'gpt-4-1106-preview',
+        "azure-gpt-3.5-turbo-16k",
+        "azure-gpt-3.5-16k",
+        "azure-gpt-4",
+        "azure-gpt-4-32k",
+    ]
+    from request_llms.bridge_all import model_info
+    if model_info[llm_kwargs['llm_model']]["max_token"] < 8000: # 至少是8k上下文的模型
+        chatbot.append([f"处理任务: {txt}", f"当前插件只支持{str(supported_llms)}, 当前模型{llm_kwargs['llm_model']}的最大上下文长度太短, 不能支撑AutoGen运行。"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    if model_info[llm_kwargs['llm_model']]["endpoint"] is not None: # 如果不是本地模型，加载API_KEY
+        llm_kwargs['api_key'] = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        import autogen
+        if get_conf("AUTOGEN_USE_DOCKER"):
+            import docker
+    except:
+        chatbot.append([ f"处理任务: {txt}",
+            f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pyautogen docker```。"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        import autogen
+        import glob, os, time, subprocess
+        if get_conf("AUTOGEN_USE_DOCKER"):
+            subprocess.Popen(["docker", "--version"])
+    except:
+        chatbot.append([f"处理任务: {txt}", f"缺少docker运行环境！"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    # 解锁插件
+    chatbot.get_cookies()['lock_plugin'] = None
+    persistent_class_multi_user_manager = GradioMultiuserManagerForPersistentClasses()
+    user_uuid = chatbot.get_cookies().get('uuid')
+    persistent_key = f"{user_uuid}->多智能体终端"
+    if persistent_class_multi_user_manager.already_alive(persistent_key):
+        # 当已经存在一个正在运行的多智能体终端时，直接将用户输入传递给它，而不是再次启动一个新的多智能体终端
+        print('[debug] feed new user input')
+        executor = persistent_class_multi_user_manager.get(persistent_key)
+        exit_reason = yield from executor.main_process_ui_control(txt, create_or_resume="resume")
+    else:
+        # 运行多智能体终端 (首次)
+        print('[debug] create new executor instance')
+        history = []
+        chatbot.append(["正在启动: 多智能体终端", "插件动态生成, 执行开始, 作者 Microsoft & Binary-Husky."])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        executor = AutoGenMath(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
+        persistent_class_multi_user_manager.set(persistent_key, executor)
+        exit_reason = yield from executor.main_process_ui_control(txt, create_or_resume="create")
+
+    if exit_reason == "wait_feedback":
+        # 当用户点击了“等待反馈”按钮时，将executor存储到cookie中，等待用户的再次调用
+        executor.chatbot.get_cookies()['lock_plugin'] = 'crazy_functions.多智能体->多智能体终端'
+    else:
+        executor.chatbot.get_cookies()['lock_plugin'] = None
+    yield from update_ui(chatbot=executor.chatbot, history=executor.history) # 更新状态

crazy_functions/对话历史存档.py

@@ -1,7 +1,8 @@
-from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from toolbox import CatchException, update_ui, promote_file_to_downloadzone, get_log_folder, get_user
 import re
 
+f_prefix = 'GPT-Academic对话存档'
+
 def write_chat_to_file(chatbot, history=None, file_name=None):
     """
     将对话记录history以Markdown格式写入文件中。如果没有指定文件名，则使用当前时间生成文件名。
@@ -9,8 +10,8 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
     import os
     import time
     if file_name is None:
-        file_name = 'chatGPT对话历史' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
-    fp = os.path.join(get_log_folder(), file_name)
+        file_name = f_prefix + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
+    fp = os.path.join(get_log_folder(get_user(chatbot), plugin_name='chat_history'), file_name)
     with open(fp, 'w', encoding='utf8') as f:
         from themes.theme import advanced_css
         f.write(f'<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>')
@@ -65,10 +66,10 @@ def read_file_to_chat(chatbot, history, file_name):
         i_say, gpt_say = h.split('<hr style="border-top: dotted 3px #ccc;">')
         chatbot.append([i_say, gpt_say])
     chatbot.append([f"存档文件详情？", f"[Local Message] 载入对话{len(html)}条，上下文{len(history)}条。"])
-    return chatbot, history    
+    return chatbot, history
 
 @CatchException
-def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -76,11 +77,11 @@ def 对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
 
-    chatbot.append(("保存当前对话", 
-        f"[Local Message] {write_chat_to_file(chatbot, history)}，您可以调用“载入对话历史存档”还原当下的对话。\n警告！被保存的对话历史可以被使用该系统的任何人查阅。"))
+    chatbot.append(("保存当前对话",
+        f"[Local Message] {write_chat_to_file(chatbot, history)}，您可以调用下拉菜单中的“载入对话历史存档”还原当下的对话。"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
 def hide_cwd(str):
@@ -90,7 +91,7 @@ def hide_cwd(str):
     return str.replace(current_path, replace_path)
 
 @CatchException
-def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -98,7 +99,7 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     from .crazy_utils import get_files_from_everything
     success, file_manifest, _ = get_files_from_everything(txt, type='.html')
@@ -106,7 +107,12 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     if not success:
         if txt == "": txt = '空空如也的输入栏'
         import glob
-        local_history = "<br/>".join(["`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`" for f in glob.glob(f'{get_log_folder()}/**/chatGPT对话历史*.html', recursive=True)])
+        local_history = "<br/>".join([
+            "`"+hide_cwd(f)+f" ({gen_file_preview(f)})"+"`"
+            for f in glob.glob(
+                f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html',
+                recursive=True
+            )])
         chatbot.append([f"正在查找对话历史文件（html格式）: {txt}", f"找不到任何html文件: {txt}。但本地存储了以下历史文件，您可以将任意一个文件路径粘贴到输入区，然后重试：<br/>{local_history}"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -120,7 +126,7 @@ def 载入对话历史存档(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         return
 
 @CatchException
-def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -128,12 +134,16 @@ def 删除所有本地对话历史记录(txt, llm_kwargs, plugin_kwargs, chatbot
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
 
     import glob, os
-    local_history = "<br/>".join(["`"+hide_cwd(f)+"`" for f in glob.glob(f'{get_log_folder()}/**/chatGPT对话历史*.html', recursive=True)])
-    for f in glob.glob(f'{get_log_folder()}/**/chatGPT对话历史*.html', recursive=True):
+    local_history = "<br/>".join([
+        "`"+hide_cwd(f)+"`"
+        for f in glob.glob(
+            f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True
+        )])
+    for f in glob.glob(f'{get_log_folder(get_user(chatbot), plugin_name="chat_history")}/**/{f_prefix}*.html', recursive=True):
         os.remove(f)
     chatbot.append([f"删除所有历史对话文件", f"已删除<br/>{local_history}"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面

crazy_functions/总结word文档.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 fast_debug = False
@@ -29,26 +29,21 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             except:
                 raise RuntimeError('请先将.doc文档转换为.docx文档。')
 
-        print(file_content)
         # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-        from request_llm.bridge_all import model_info
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        from request_llms.bridge_all import model_info
         max_token = model_info[llm_kwargs['llm_model']]['max_token']
         TOKEN_LIMIT_PER_FRAGMENT = max_token * 3 // 4
-        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=file_content,  
-            get_token_fn=model_info[llm_kwargs['llm_model']]['token_cnt'], 
-            limit=TOKEN_LIMIT_PER_FRAGMENT
-        )
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
         this_paper_history = []
         for i, paper_frag in enumerate(paper_fragments):
             i_say = f'请对下面的文章片段用中文做概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{paper_frag}```'
             i_say_show_user = f'请对下面的文章片段做概述: {os.path.abspath(fp)}的第{i+1}/{len(paper_fragments)}个片段。'
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say_show_user, 
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
                 llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
+                chatbot=chatbot,
                 history=[],
                 sys_prompt="总结文章。"
             )
@@ -61,10 +56,10 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
         if len(paper_fragments) > 1:
             i_say = f"根据以上的对话，总结文章{os.path.abspath(fp)}的主要内容。"
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say, 
+                inputs=i_say,
+                inputs_show_user=i_say,
                 llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
+                chatbot=chatbot,
                 history=this_paper_history,
                 sys_prompt="总结文章。"
             )
@@ -84,7 +79,7 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
 
 
 @CatchException
-def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     import glob, os
 
     # 基本信息：功能、贡献者
@@ -97,7 +92,7 @@ def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pr
     try:
         from docx import Document
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -111,7 +106,7 @@ def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pr
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
@@ -124,7 +119,7 @@ def 总结word文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pr
 
     # 如果没找到任何文件
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.docx或doc文件: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.docx或doc文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 

crazy_functions/总结音视频.py

@@ -1,4 +1,4 @@
-from toolbox import CatchException, report_execption, select_api_key, update_ui, get_conf
+from toolbox import CatchException, report_exception, select_api_key, update_ui, get_conf
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from toolbox import write_history_to_file, promote_file_to_downloadzone, get_log_folder
 
@@ -41,7 +41,7 @@ def split_audio_file(filename, split_duration=1000):
 def AnalyAudio(parse_prompt, file_manifest, llm_kwargs, chatbot, history):
     import os, requests
     from moviepy.editor import AudioFileClip
-    from request_llm.bridge_all import model_info
+    from request_llms.bridge_all import model_info
 
     # 设置OpenAI密钥和模型
     api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
@@ -79,7 +79,7 @@ def AnalyAudio(parse_prompt, file_manifest, llm_kwargs, chatbot, history):
 
             chatbot.append([f"将 {i} 发送到openai音频解析终端 (whisper)，当前参数：{parse_prompt}", "正在处理 ..."])
             yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
-            proxies, = get_conf('proxies')
+            proxies = get_conf('proxies')
             response = requests.post(url, headers=headers, files=files, data=data, proxies=proxies).text
 
             chatbot.append(["音频解析结果", response])
@@ -144,7 +144,7 @@ def 总结音视频(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     try:
         from moviepy.editor import AudioFileClip
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade moviepy```。")
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
@@ -158,7 +158,7 @@ def 总结音视频(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return
 
@@ -174,7 +174,7 @@ def 总结音视频(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
 
     # 如果没找到任何文件
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何音频或视频文件: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何音频或视频文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return
 

crazy_functions/批量Markdown翻译.py

@@ -1,6 +1,6 @@
-import glob, time, os, re, logging
-from toolbox import update_ui, trimmed_format_exc, gen_time_str, disable_auto_promotion
-from toolbox import CatchException, report_execption, get_log_folder
+import glob, shutil, os, re, logging
+from toolbox import update_ui, trimmed_format_exc, gen_time_str
+from toolbox import CatchException, report_exception, get_log_folder
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 fast_debug = False
 
@@ -13,12 +13,12 @@ class PaperFileGroup():
         self.sp_file_tag = []
 
         # count_token
-        from request_llm.bridge_all import model_info
+        from request_llms.bridge_all import model_info
         enc = model_info["gpt-3.5-turbo"]['tokenizer']
         def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
         self.get_token_num = get_token_num
 
-    def run_file_split(self, max_token_limit=1900):
+    def run_file_split(self, max_token_limit=2048):
         """
         将长文本分离开来
         """
@@ -28,8 +28,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
@@ -53,7 +53,7 @@ class PaperFileGroup():
 def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
-    #  <-------- 读取Markdown文件，删除其中的所有注释 ----------> 
+    #  <-------- 读取Markdown文件，删除其中的所有注释 ---------->
     pfg = PaperFileGroup()
 
     for index, fp in enumerate(file_manifest):
@@ -63,23 +63,23 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
             pfg.file_paths.append(fp)
             pfg.file_contents.append(file_content)
 
-    #  <-------- 拆分过长的Markdown文件 ----------> 
-    pfg.run_file_split(max_token_limit=1500)
+    #  <-------- 拆分过长的Markdown文件 ---------->
+    pfg.run_file_split(max_token_limit=2048)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 多线程翻译开始 ----------> 
+    #  <-------- 多线程翻译开始 ---------->
     if language == 'en->zh':
-        inputs_array = ["This is a Markdown file, translate it into Chinese, do not modify any existing Markdown commands:" + 
+        inputs_array = ["This is a Markdown file, translate it into Chinese, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
     elif language == 'zh->en':
-        inputs_array = [f"This is a Markdown file, translate it into English, do not modify any existing Markdown commands:" + 
+        inputs_array = [f"This is a Markdown file, translate it into English, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
     else:
-        inputs_array = [f"This is a Markdown file, translate it into {language}, do not modify any existing Markdown commands, only answer me with translated results:" + 
+        inputs_array = [f"This is a Markdown file, translate it into {language}, do NOT modify any existing Markdown commands, do NOT use code wrapper (```), ONLY answer me with translated results:" +
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
         inputs_show_user_array = [f"翻译 {f}" for f in pfg.sp_file_tag]
         sys_prompt_array = ["You are a professional academic paper translator." for _ in range(n_split)]
@@ -99,11 +99,16 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         for i_say, gpt_say in zip(gpt_response_collection[0::2], gpt_response_collection[1::2]):
             pfg.sp_file_result.append(gpt_say)
         pfg.merge_result()
-        pfg.write_result(language)
+        output_file_arr = pfg.write_result(language)
+        for output_file in output_file_arr:
+            promote_file_to_downloadzone(output_file, chatbot=chatbot)
+            if 'markdown_expected_output_path' in plugin_kwargs:
+                expected_f_name = plugin_kwargs['markdown_expected_output_path']
+                shutil.copyfile(output_file, expected_f_name)
     except:
         logging.error(trimmed_format_exc())
 
-    #  <-------- 整理结果，退出 ----------> 
+    #  <-------- 整理结果，退出 ---------->
     create_report_file_name = gen_time_str() + f"-chatgpt.md"
     res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
     promote_file_to_downloadzone(res, chatbot=chatbot)
@@ -118,7 +123,7 @@ def get_files_from_everything(txt, preference=''):
     if txt.startswith('http'):
         import requests
         from toolbox import get_conf
-        proxies, = get_conf('proxies')
+        proxies = get_conf('proxies')
         # 网络的远程文件
         if preference == 'Github':
             logging.info('正在从github下载资源 ...')
@@ -153,19 +158,18 @@ def get_files_from_everything(txt, preference=''):
 
 
 @CatchException
-def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
         "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    disable_auto_promotion(chatbot)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -177,12 +181,12 @@ def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     if not success:
         # 什么都没有
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
@@ -193,19 +197,18 @@ def Markdown英译中(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
 
 
 @CatchException
-def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
         "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    disable_auto_promotion(chatbot)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -215,30 +218,29 @@ def Markdown中译英(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     if not success:
         # 什么都没有
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='zh->en')
 
 
 @CatchException
-def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # 基本信息：功能、贡献者
     chatbot.append([
         "函数插件功能？",
         "对整个Markdown项目进行翻译。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-    disable_auto_promotion(chatbot)
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
         import tiktoken
     except:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}",
                          b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade tiktoken```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -248,14 +250,14 @@ def Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     if not success:
         # 什么都没有
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.md文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     language = plugin_kwargs.get("advanced_arg", 'Chinese')
     yield from 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language=language)

crazy_functions/批量总结PDF文档.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui, promote_file_to_downloadzone, gen_time_str
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from .crazy_utils import read_and_clean_pdf_text
@@ -17,20 +17,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
         file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
         file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
         page_one = str(page_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
-        
+
         TOKEN_LIMIT_PER_FRAGMENT = 2500
 
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-        from request_llm.bridge_all import model_info
-        enc = model_info["gpt-3.5-turbo"]['tokenizer']
-        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
-        page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+        from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+        paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content,  limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+        page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
         # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
         paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-        
+
         ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
         final_results = []
         final_results.append(paper_meta)
@@ -49,10 +44,10 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
             i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"
             i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i][:200]}"
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                                llm_kwargs, chatbot, 
+                                                                                llm_kwargs, chatbot,
                                                                                 history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
                                                                                 sys_prompt="Extract the main idea of this section with Chinese."  # 提示
-                                                                                ) 
+                                                                                )
             iteration_results.append(gpt_say)
             last_iteration_result = gpt_say
 
@@ -72,15 +67,15 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
     - (2):What are the past methods? What are the problems with them? Is the approach well motivated?
     - (3):What is the research methodology proposed in this paper?
     - (4):On what task and what performance is achieved by the methods in this paper? Can the performance support their goals?
-Follow the format of the output that follows:                  
+Follow the format of the output that follows:
 1. Title: xxx\n\n
 2. Authors: xxx\n\n
 3. Affiliation: xxx\n\n
 4. Keywords: xxx\n\n
 5. Urls: xxx or xxx , xxx \n\n
 6. Summary: \n\n
-    - (1):xxx;\n 
-    - (2):xxx;\n 
+    - (1):xxx;\n
+    - (2):xxx;\n
     - (3):xxx;\n
     - (4):xxx.\n\n
 Be sure to use Chinese answers (proper nouns need to be marked in English), statements as concise and academic as possible,
@@ -90,8 +85,8 @@ do not have too much repetitive information, numerical values using the original
         file_write_buffer.extend(final_results)
         i_say, final_results = input_clipping(i_say, final_results, max_token_limit=2000)
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, inputs_show_user='开始最终总结', 
-            llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results, 
+            inputs=i_say, inputs_show_user='开始最终总结',
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results,
             sys_prompt= f"Extract the main idea of this paper with less than {NUM_OF_WORD} Chinese characters"
         )
         final_results.append(gpt_say)
@@ -106,7 +101,7 @@ do not have too much repetitive information, numerical values using the original
 
 
 @CatchException
-def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     import glob, os
 
     # 基本信息：功能、贡献者
@@ -119,8 +114,8 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     try:
         import fitz
     except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -133,16 +128,16 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
     # 搜索需要处理的文件清单
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
-    
+
     # 如果没找到任何文件
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或.pdf文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 

crazy_functions/批量总结PDF文档pdfminer.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 
@@ -85,10 +85,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
             msg = '正常'
             # ** gpt request **
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say_show_user, 
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
                 llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
+                chatbot=chatbot,
                 history=[],
                 sys_prompt="总结文章。"
             )  # 带超时倒计时
@@ -106,10 +106,10 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
         msg = '正常'
         # ** gpt request **
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, 
-            inputs_show_user=i_say, 
+            inputs=i_say,
+            inputs_show_user=i_say,
             llm_kwargs=llm_kwargs,
-            chatbot=chatbot, 
+            chatbot=chatbot,
             history=history,
             sys_prompt="总结文章。"
         )  # 带超时倒计时
@@ -124,7 +124,7 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
 
 
 @CatchException
-def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
 
@@ -138,8 +138,8 @@ def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     try:
         import pdfminer, bs4
     except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pdfminer beautifulsoup4```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -147,7 +147,7 @@ def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, histo
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
@@ -155,7 +155,7 @@ def 批量总结PDF文档pdfminer(txt, llm_kwargs, plugin_kwargs, chatbot, histo
                     # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或pdf文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex或pdf文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/批量翻译PDF文档_NOUGAT.py

@@ -1,4 +1,4 @@
-from toolbox import CatchException, report_execption, get_log_folder, gen_time_str
+from toolbox import CatchException, report_exception, get_log_folder, gen_time_str
 from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
@@ -48,7 +48,7 @@ def markdown_to_dict(article_content):
 
 
 @CatchException
-def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
 
     disable_auto_promotion(chatbot)
     # 基本信息：功能、贡献者
@@ -57,30 +57,35 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         "批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-    # 尝试导入依赖，如果缺少依赖，则给出安装建议
-    try:
-        import nougat
-        import tiktoken
-    except:
-        report_execption(chatbot, history,
-                         a=f"解析项目: {txt}",
-                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade nougat-ocr tiktoken```。")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
     # 清空历史，以免输入溢出
     history = []
 
     from .crazy_utils import get_files_from_everything
     success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
+    if len(file_manifest) > 0:
+        # 尝试导入依赖，如果缺少依赖，则给出安装建议
+        try:
+            import nougat
+            import tiktoken
+        except:
+            report_exception(chatbot, history,
+                             a=f"解析项目: {txt}",
+                             b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade nougat-ocr tiktoken```。")
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+            return
+    success_mmd, file_manifest_mmd, _ = get_files_from_everything(txt, type='.mmd')
+    success = success or success_mmd
+    file_manifest += file_manifest_mmd
+    chatbot.append(["文件列表：", ", ".join([e.split('/')[-1] for e in file_manifest])]);
+    yield from update_ui(      chatbot=chatbot, history=history)
     # 检测输入参数，如没有给定输入参数，直接退出
     if not success:
         if txt == "": txt = '空空如也的输入栏'
 
     # 如果没找到任何文件
     if len(file_manifest) == 0:
-        report_execption(chatbot, history,
-                         a=f"解析项目: {txt}", b=f"找不到任何.tex或.pdf文件: {txt}")
+        report_exception(chatbot, history,
+                         a=f"解析项目: {txt}", b=f"找不到任何.pdf拓展名的文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 
@@ -97,12 +102,17 @@ def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwa
     generated_conclusion_files = []
     generated_html_files = []
     DST_LANG = "中文"
-    from crazy_functions.crazy_utils import nougat_interface, construct_html
+    from crazy_functions.crazy_utils import nougat_interface
+    from crazy_functions.pdf_fns.report_gen_html import construct_html
     nougat_handle = nougat_interface()
     for index, fp in enumerate(file_manifest):
-        chatbot.append(["当前进度：", f"正在解析论文，请稍候。（第一次运行时，需要花费较长时间下载NOUGAT参数）"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        fpp = yield from nougat_handle.NOUGAT_parse_pdf(fp, chatbot, history)
-        promote_file_to_downloadzone(fpp, rename_file=os.path.basename(fpp)+'.nougat.mmd', chatbot=chatbot)
+        if fp.endswith('pdf'):
+            chatbot.append(["当前进度：", f"正在解析论文，请稍候。（第一次运行时，需要花费较长时间下载NOUGAT参数）"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+            fpp = yield from nougat_handle.NOUGAT_parse_pdf(fp, chatbot, history)
+            promote_file_to_downloadzone(fpp, rename_file=os.path.basename(fpp)+'.nougat.mmd', chatbot=chatbot)
+        else:
+            chatbot.append(["当前论文无需解析：", fp]); yield from update_ui(      chatbot=chatbot, history=history)
+            fpp = fp
         with open(fpp, 'r', encoding='utf8') as f:
             article_content = f.readlines()
         article_dict = markdown_to_dict(article_content)

crazy_functions/批量翻译PDF文档_多线程.py

@@ -1,185 +0,0 @@
-from toolbox import CatchException, report_execption, get_log_folder, gen_time_str
-from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
-from toolbox import write_history_to_file, promote_file_to_downloadzone
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
-from .crazy_utils import read_and_clean_pdf_text
-from .pdf_fns.parse_pdf import parse_pdf, get_avail_grobid_url, translate_pdf
-from colorful import *
-import copy
-import os
-import math
-
-@CatchException
-def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
-
-    disable_auto_promotion(chatbot)
-    # 基本信息：功能、贡献者
-    chatbot.append([
-        "函数插件功能？",
-        "批量翻译PDF文档。函数插件贡献者: Binary-Husky"])
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    # 尝试导入依赖，如果缺少依赖，则给出安装建议
-    try:
-        import fitz
-        import tiktoken
-        import scipdf
-    except:
-        report_execption(chatbot, history,
-                         a=f"解析项目: {txt}",
-                         b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf tiktoken scipdf_parser```。")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 清空历史，以免输入溢出
-    history = []
-
-    from .crazy_utils import get_files_from_everything
-    success, file_manifest, project_folder = get_files_from_everything(txt, type='.pdf')
-    # 检测输入参数，如没有给定输入参数，直接退出
-    if not success:
-        if txt == "": txt = '空空如也的输入栏'
-
-    # 如果没找到任何文件
-    if len(file_manifest) == 0:
-        report_execption(chatbot, history,
-                         a=f"解析项目: {txt}", b=f"找不到任何.tex或.pdf文件: {txt}")
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        return
-
-    # 开始正式执行任务
-    grobid_url = get_avail_grobid_url()
-    if grobid_url is not None:
-        yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
-    else:
-        yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
-        yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
-
-
-def 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url):
-    import copy, json
-    TOKEN_LIMIT_PER_FRAGMENT = 1024
-    generated_conclusion_files = []
-    generated_html_files = []
-    DST_LANG = "中文"
-    from crazy_functions.crazy_utils import construct_html
-    for index, fp in enumerate(file_manifest):
-        chatbot.append(["当前进度：", f"正在连接GROBID服务，请稍候: {grobid_url}\n如果等待时间过长，请修改config中的GROBID_URL，可修改成本地GROBID服务。"]); yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        article_dict = parse_pdf(fp, grobid_url)
-        grobid_json_res = os.path.join(get_log_folder(), gen_time_str() + "grobid.json")
-        with open(grobid_json_res, 'w+', encoding='utf8') as f:
-            f.write(json.dumps(article_dict, indent=4, ensure_ascii=False))
-        promote_file_to_downloadzone(grobid_json_res, chatbot=chatbot)
-        
-        if article_dict is None: raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
-        yield from translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-
-def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    """
-    此函数已经弃用
-    """
-    import copy
-    TOKEN_LIMIT_PER_FRAGMENT = 1024
-    generated_conclusion_files = []
-    generated_html_files = []
-    from crazy_functions.crazy_utils import construct_html
-    for index, fp in enumerate(file_manifest):
-        # 读取PDF文件
-        file_content, page_one = read_and_clean_pdf_text(fp)
-        file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
-        page_one = str(page_one).encode('utf-8', 'ignore').decode()      # avoid reading non-utf8 chars
-
-        # 递归地切割PDF文件
-        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-        from request_llm.bridge_all import model_info
-        enc = model_info["gpt-3.5-turbo"]['tokenizer']
-        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
-        page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-            txt=page_one, get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
-
-        # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
-        paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-        
-        # 单线，获取文章meta信息
-        paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=f"以下是一篇学术论文的基础信息，请从中提取出“标题”、“收录会议或期刊”、“作者”、“摘要”、“编号”、“作者邮箱”这六个部分。请用markdown格式输出，最后用中文翻译摘要部分。请提取：{paper_meta}",
-            inputs_show_user=f"请从{fp}中提取出“标题”、“收录会议或期刊”等基本信息。",
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot, history=[],
-            sys_prompt="Your job is to collect information from materials。",
-        )
-
-        # 多线，翻译
-        gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
-            inputs_array=[
-                f"你需要翻译以下内容：\n{frag}" for frag in paper_fragments],
-            inputs_show_user_array=[f"\n---\n 原文： \n\n {frag.replace('#', '')}  \n---\n 翻译：\n " for frag in paper_fragments],
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot,
-            history_array=[[paper_meta] for _ in paper_fragments],
-            sys_prompt_array=[
-                "请你作为一个学术翻译，负责把学术论文准确翻译成中文。注意文章中的每一句话都要翻译。" for _ in paper_fragments],
-            # max_workers=5  # OpenAI所允许的最大并行过载
-        )
-        gpt_response_collection_md = copy.deepcopy(gpt_response_collection)
-        # 整理报告的格式
-        for i,k in enumerate(gpt_response_collection_md): 
-            if i%2==0:
-                gpt_response_collection_md[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection_md)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection_md)//2}]：\n "
-            else:
-                gpt_response_collection_md[i] = gpt_response_collection_md[i]
-        final = ["一、论文概况\n\n---\n\n", paper_meta_info.replace('# ', '### ') + '\n\n---\n\n', "二、论文翻译", ""]
-        final.extend(gpt_response_collection_md)
-        create_report_file_name = f"{os.path.basename(fp)}.trans.md"
-        res = write_history_to_file(final, create_report_file_name)
-        promote_file_to_downloadzone(res, chatbot=chatbot)
-
-        # 更新UI
-        generated_conclusion_files.append(f'{get_log_folder()}/{create_report_file_name}')
-        chatbot.append((f"{fp}完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-        # write html
-        try:
-            ch = construct_html() 
-            orig = ""
-            trans = ""
-            gpt_response_collection_html = copy.deepcopy(gpt_response_collection)
-            for i,k in enumerate(gpt_response_collection_html): 
-                if i%2==0:
-                    gpt_response_collection_html[i] = paper_fragments[i//2].replace('#', '')
-                else:
-                    gpt_response_collection_html[i] = gpt_response_collection_html[i]
-            final = ["论文概况", paper_meta_info.replace('# ', '### '),  "二、论文翻译",  ""]
-            final.extend(gpt_response_collection_html)
-            for i, k in enumerate(final): 
-                if i%2==0:
-                    orig = k
-                if i%2==1:
-                    trans = k
-                    ch.add_row(a=orig, b=trans)
-            create_report_file_name = f"{os.path.basename(fp)}.trans.html"
-            generated_html_files.append(ch.save_file(create_report_file_name))
-        except:
-            from toolbox import trimmed_format_exc
-            print('writing html result failed:', trimmed_format_exc())
-
-    # 准备文件的下载
-    for pdf_path in generated_conclusion_files:
-        # 重命名文件
-        rename_file = f'翻译-{os.path.basename(pdf_path)}'
-        promote_file_to_downloadzone(pdf_path, rename_file=rename_file, chatbot=chatbot)
-    for html_path in generated_html_files:
-        # 重命名文件
-        rename_file = f'翻译-{os.path.basename(html_path)}'
-        promote_file_to_downloadzone(html_path, rename_file=rename_file, chatbot=chatbot)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files + generated_html_files)))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-

crazy_functions/数学动画生成manim.py

@@ -1,6 +1,7 @@
-from toolbox import CatchException, update_ui, gen_time_str
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from .crazy_utils import input_clipping
+import os
+from toolbox import CatchException, update_ui, gen_time_str, promote_file_to_downloadzone
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import input_clipping
 
 def inspect_dependency(chatbot, history):
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
@@ -26,15 +27,16 @@ def eval_manim(code):
 
     class_name = get_class_name(code)
 
-    try: 
+    try:
+        time_str = gen_time_str()
         subprocess.check_output([sys.executable, '-c', f"from gpt_log.MyAnimation import {class_name}; {class_name}().render()"])
-        shutil.move('media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{gen_time_str()}.mp4')
-        return f'gpt_log/{gen_time_str()}.mp4'
+        shutil.move(f'media/videos/1080p60/{class_name}.mp4', f'gpt_log/{class_name}-{time_str}.mp4')
+        return f'gpt_log/{time_str}.mp4'
     except subprocess.CalledProcessError as e:
         output = e.output.decode()
         print(f"Command returned non-zero exit status {e.returncode}: {output}.")
         return f"Evaluating python script failed: {e.output}."
-    except: 
+    except:
         print('generating mp4 failed')
         return "Generating mp4 failed."
 
@@ -43,12 +45,12 @@ def get_code_block(reply):
     import re
     pattern = r"```([\s\S]*?)```" # regex pattern to match code blocks
     matches = re.findall(pattern, reply) # find all code blocks in text
-    if len(matches) != 1: 
+    if len(matches) != 1:
         raise RuntimeError("GPT is not generating proper code.")
     return matches[0].strip('python') #  code block
 
 @CatchException
-def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -56,10 +58,10 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     # 清空历史，以免输入溢出
-    history = []    
+    history = []
 
     # 基本信息：功能、贡献者
     chatbot.append([
@@ -71,29 +73,31 @@ def 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     # 尝试导入依赖, 如果缺少依赖, 则给出安装建议
     dep_ok = yield from inspect_dependency(chatbot=chatbot, history=history) # 刷新界面
     if not dep_ok: return
-    
+
     # 输入
     i_say = f'Generate a animation to show: ' + txt
     demo = ["Here is some examples of manim", examples_of_manim()]
     _, demo = input_clipping(inputs="", history=demo, max_token_limit=2560)
     # 开始
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=i_say, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo, 
+        inputs=i_say, inputs_show_user=i_say,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=demo,
         sys_prompt=
         r"Write a animation script with 3blue1brown's manim. "+
-        r"Please begin with `from manim import *`. " + 
+        r"Please begin with `from manim import *`. " +
         r"Answer me with a code block wrapped by ```."
     )
     chatbot.append(["开始生成动画", "..."])
     history.extend([i_say, gpt_say])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
-    
+
     # 将代码转为动画
     code = get_code_block(gpt_say)
     res = eval_manim(code)
 
     chatbot.append(("生成的视频文件路径", res))
+    if os.path.exists(res):
+        promote_file_to_downloadzone(res, chatbot=chatbot)
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
 
 # 在这里放一些网上搜集的demo，辅助gpt生成代码

crazy_functions/理解PDF文档内容.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from .crazy_utils import read_and_clean_pdf_text
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 fast_debug = False
@@ -15,20 +15,15 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
     file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
     page_one = str(page_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
-    
+
     TOKEN_LIMIT_PER_FRAGMENT = 2500
 
-    from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-    from request_llm.bridge_all import model_info
-    enc = model_info["gpt-3.5-turbo"]['tokenizer']
-    def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
-    paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-        txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
-    page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-        txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+    paper_fragments = breakdown_text_to_satisfy_token_limit(txt=file_content, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+    page_one_fragments = breakdown_text_to_satisfy_token_limit(txt=str(page_one), limit=TOKEN_LIMIT_PER_FRAGMENT//4, llm_model=llm_kwargs['llm_model'])
     # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
     paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
-    
+
     ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
     final_results = []
     final_results.append(paper_meta)
@@ -45,12 +40,12 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     for i in range(n_fragment):
         NUM_OF_WORD = MAX_WORD_TOTAL // n_fragment
         i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i]}"
-        i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i][:200]}"
+        i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {paper_fragments[i][:200]} ...."
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
-                                                                           llm_kwargs, chatbot, 
+                                                                           llm_kwargs, chatbot,
                                                                            history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
-                                                                           sys_prompt="Extract the main idea of this section."  # 提示
-                                                                        ) 
+                                                                           sys_prompt="Extract the main idea of this section, answer me with Chinese."  # 提示
+                                                                        )
         iteration_results.append(gpt_say)
         last_iteration_result = gpt_say
 
@@ -68,7 +63,7 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
 
 
 @CatchException
-def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     import glob, os
 
     # 基本信息：功能、贡献者
@@ -81,8 +76,8 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
     try:
         import fitz
     except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -96,7 +91,7 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
     else:
         if txt == "":
             txt = '空空如也的输入栏'
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -105,7 +100,7 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
     # 如果没找到任何文件
     if len(file_manifest) == 0:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}", b=f"找不到任何.tex或.pdf文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return

crazy_functions/生成函数注释.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 fast_debug = False
@@ -16,7 +16,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-        if not fast_debug: 
+        if not fast_debug:
             msg = '正常'
             # ** gpt request **
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@@ -27,7 +27,7 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
             if not fast_debug: time.sleep(2)
 
-    if not fast_debug: 
+    if not fast_debug:
         res = write_history_to_file(history)
         promote_file_to_downloadzone(res, chatbot=chatbot)
         chatbot.append(("完成了吗？", res))
@@ -36,21 +36,21 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
 
 
 @CatchException
-def 批量生成函数注释(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 批量生成函数注释(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.py', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)]
 
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/生成多种Mermaid图表.py

@@ -0,0 +1,296 @@
+from toolbox import CatchException, update_ui, report_exception
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+import datetime
+
+#以下是每类图表的PROMPT
+SELECT_PROMPT = """
+“{subject}”
+=============
+以上是从文章中提取的摘要,将会使用这些摘要绘制图表。请你选择一个合适的图表类型:
+1 流程图
+2 序列图
+3 类图
+4 饼图
+5 甘特图
+6 状态图
+7 实体关系图
+8 象限提示图
+不需要解释原因，仅需要输出单个不带任何标点符号的数字。
+"""
+#没有思维导图!!!测试发现模型始终会优先选择思维导图
+#流程图
+PROMPT_1 = """
+请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
+```mermaid
+graph TD
+    P(编程) --> L1(Python)
+    P(编程) --> L2(C)
+    P(编程) --> L3(C++)
+    P(编程) --> L4(Javascipt)
+    P(编程) --> L5(PHP)
+```
+"""
+#序列图
+PROMPT_2 = """
+请你给出围绕“{subject}”的序列图，使用mermaid语法，mermaid语法举例：
+```mermaid
+sequenceDiagram
+    participant A as 用户
+    participant B as 系统
+    A->>B: 登录请求
+    B->>A: 登录成功
+    A->>B: 获取数据
+    B->>A: 返回数据
+```
+"""
+#类图
+PROMPT_3 = """
+请你给出围绕“{subject}”的类图，使用mermaid语法，mermaid语法举例：
+```mermaid
+classDiagram
+    Class01 <|-- AveryLongClass : Cool
+    Class03 *-- Class04
+    Class05 o-- Class06
+    Class07 .. Class08
+    Class09 --> C2 : Where am i?
+    Class09 --* C3
+    Class09 --|> Class07
+    Class07 : equals()
+    Class07 : Object[] elementData
+    Class01 : size()
+    Class01 : int chimp
+    Class01 : int gorilla
+    Class08 <--> C2: Cool label
+```
+"""
+#饼图
+PROMPT_4 = """
+请你给出围绕“{subject}”的饼图，使用mermaid语法，mermaid语法举例：
+```mermaid
+pie title Pets adopted by volunteers
+    "狗" : 386
+    "猫" : 85
+    "兔子" : 15
+```
+"""
+#甘特图
+PROMPT_5 = """
+请你给出围绕“{subject}”的甘特图，使用mermaid语法，mermaid语法举例：
+```mermaid
+gantt
+    title 项目开发流程
+    dateFormat  YYYY-MM-DD
+    section 设计
+    需求分析 :done, des1, 2024-01-06,2024-01-08
+    原型设计 :active, des2, 2024-01-09, 3d
+    UI设计 : des3, after des2, 5d
+    section 开发
+    前端开发 :2024-01-20, 10d
+    后端开发 :2024-01-20, 10d
+```
+"""
+#状态图
+PROMPT_6 = """
+请你给出围绕“{subject}”的状态图，使用mermaid语法，mermaid语法举例：
+```mermaid
+stateDiagram-v2
+   [*] --> Still
+    Still --> [*]
+    Still --> Moving
+    Moving --> Still
+    Moving --> Crash
+    Crash --> [*]
+```
+"""
+#实体关系图
+PROMPT_7 = """
+请你给出围绕“{subject}”的实体关系图，使用mermaid语法，mermaid语法举例：
+```mermaid
+erDiagram
+    CUSTOMER ||--o{ ORDER : places
+    ORDER ||--|{ LINE-ITEM : contains
+    CUSTOMER {
+        string name
+        string id
+    }
+    ORDER {
+        string orderNumber
+        date orderDate
+        string customerID
+    }
+    LINE-ITEM {
+        number quantity
+        string productID
+    }
+```
+"""
+#象限提示图
+PROMPT_8 = """
+请你给出围绕“{subject}”的象限图，使用mermaid语法，mermaid语法举例：
+```mermaid
+graph LR
+    A[Hard skill] --> B(Programming)
+    A[Hard skill] --> C(Design)
+    D[Soft skill] --> E(Coordination)
+    D[Soft skill] --> F(Communication)
+```
+"""
+#思维导图
+PROMPT_9 = """
+{subject}
+==========
+请给出上方内容的思维导图，充分考虑其之间的逻辑，使用mermaid语法，mermaid语法举例：
+```mermaid
+mindmap
+  root((mindmap))
+    Origins
+      Long history
+      ::icon(fa fa-book)
+      Popularisation
+        British popular psychology author Tony Buzan
+    Research
+      On effectiveness<br/>and features
+      On Automatic creation
+        Uses
+            Creative techniques
+            Strategic planning
+            Argument mapping
+    Tools
+      Pen and paper
+      Mermaid
+```
+"""
+
+def 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs):
+    ############################## <第 0 步，切割输入> ##################################
+    # 借用PDF切割中的函数对文本进行切割
+    TOKEN_LIMIT_PER_FRAGMENT = 2500
+    txt = str(history).encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+    from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+    txt = breakdown_text_to_satisfy_token_limit(txt=txt, limit=TOKEN_LIMIT_PER_FRAGMENT, llm_model=llm_kwargs['llm_model'])
+    ############################## <第 1 步，迭代地历遍整个文章，提取精炼信息> ##################################
+    results = []
+    MAX_WORD_TOTAL = 4096
+    n_txt = len(txt)
+    last_iteration_result = "从以下文本中提取摘要。"
+    if n_txt >= 20: print('文章极长，不能达到预期效果')
+    for i in range(n_txt):
+        NUM_OF_WORD = MAX_WORD_TOTAL // n_txt
+        i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words in Chinese: {txt[i]}"
+        i_say_show_user = f"[{i+1}/{n_txt}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} words: {txt[i][:200]} ...."
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
+                                                                           llm_kwargs, chatbot,
+                                                                           history=["The main content of the previous section is?", last_iteration_result], # 迭代上一次的结果
+                                                                           sys_prompt="Extracts the main content from the text section where it is located for graphing purposes, answer me with Chinese."  # 提示
+                                                                        )
+        results.append(gpt_say)
+        last_iteration_result = gpt_say
+    ############################## <第 2 步，根据整理的摘要选择图表类型> ##################################
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    gpt_say = plugin_kwargs.get("advanced_arg", "")     #将图表类型参数赋值为插件参数
+    results_txt = '\n'.join(results)    #合并摘要
+    if gpt_say not in ['1','2','3','4','5','6','7','8','9']:    #如插件参数不正确则使用对话模型判断
+        i_say_show_user = f'接下来将判断适合的图表类型,如连续3次判断失败将会使用流程图进行绘制'; gpt_say = "[Local Message] 收到。"   # 用户提示
+        chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=[])    # 更新UI
+        i_say = SELECT_PROMPT.format(subject=results_txt)
+        i_say_show_user = f'请判断适合使用的流程图类型,其中数字对应关系为:1-流程图,2-序列图,3-类图,4-饼图,5-甘特图,6-状态图,7-实体关系图,8-象限提示图。由于不管提供文本是什么,模型大概率认为"思维导图"最合适,因此思维导图仅能通过参数调用。'
+        for i in range(3):
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
+                llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
+                sys_prompt=""
+            )
+            if gpt_say in ['1','2','3','4','5','6','7','8','9']:     #判断返回是否正确
+                break
+        if gpt_say not in ['1','2','3','4','5','6','7','8','9']:
+            gpt_say = '1'
+    ############################## <第 3 步，根据选择的图表类型绘制图表> ##################################
+    if gpt_say == '1':
+        i_say = PROMPT_1.format(subject=results_txt)
+    elif gpt_say == '2':
+        i_say = PROMPT_2.format(subject=results_txt)
+    elif gpt_say == '3':
+        i_say = PROMPT_3.format(subject=results_txt)
+    elif gpt_say == '4':
+        i_say = PROMPT_4.format(subject=results_txt)
+    elif gpt_say == '5':
+        i_say = PROMPT_5.format(subject=results_txt)
+    elif gpt_say == '6':
+        i_say = PROMPT_6.format(subject=results_txt)
+    elif gpt_say == '7':
+        i_say = PROMPT_7.replace("{subject}", results_txt)      #由于实体关系图用到了{}符号
+    elif gpt_say == '8':
+        i_say = PROMPT_8.format(subject=results_txt)
+    elif gpt_say == '9':
+        i_say = PROMPT_9.format(subject=results_txt)
+    i_say_show_user = f'请根据判断结果绘制相应的图表。如需绘制思维导图请使用参数调用,同时过大的图表可能需要复制到在线编辑器中进行渲染。'
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=i_say,
+        inputs_show_user=i_say_show_user,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
+        sys_prompt=""
+    )
+    history.append(gpt_say)
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+@CatchException
+def 生成多种Mermaid图表(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    """
+    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
+    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
+    plugin_kwargs   插件模型的参数，用于灵活调整复杂功能的各种参数
+    chatbot         聊天显示框的句柄，用于显示给用户
+    history         聊天历史，前情提要
+    system_prompt   给gpt的静默提醒
+    web_port        当前软件运行的端口号
+    """
+    import os
+
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "根据当前聊天历史或指定的路径文件(文件内容优先)绘制多种mermaid图表，将会由对话模型首先判断适合的图表类型，随后绘制图表。\
+        \n您也可以使用插件参数指定绘制的图表类型,函数插件贡献者: Menghuan1918"])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    if os.path.exists(txt):     #如输入区无内容则直接解析历史记录
+        from crazy_functions.pdf_fns.parse_word import extract_text_from_files
+        file_exist, final_result, page_one, file_manifest, excption = extract_text_from_files(txt, chatbot, history)
+    else:
+        file_exist = False
+        excption = ""
+        file_manifest = []
+
+    if excption != "":
+        if excption == "word":
+            report_exception(chatbot, history,
+                a = f"解析项目: {txt}",
+                b = f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。")
+
+        elif excption == "pdf":
+            report_exception(chatbot, history,
+                a = f"解析项目: {txt}",
+                b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。")
+
+        elif excption == "word_pip":
+                report_exception(chatbot, history,
+                    a=f"解析项目: {txt}",
+                    b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade python-docx pywin32```。")
+
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    else:
+        if not file_exist:
+            history.append(txt)     #如输入区不是文件则将输入区内容加入历史记录
+            i_say_show_user = f'首先你从历史记录中提取摘要。'; gpt_say = "[Local Message] 收到。"   # 用户提示
+            chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+            yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)
+        else:
+            file_num = len(file_manifest)
+            for i in range(file_num):     #依次处理文件
+                i_say_show_user = f"[{i+1}/{file_num}]处理文件{file_manifest[i]}"; gpt_say = "[Local Message] 收到。"   # 用户提示
+                chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=history)    # 更新UI
+                history = []    #如输入区内容为文件则清空历史记录
+                history.append(final_result[i])
+                yield from 解析历史输入(history,llm_kwargs,file_manifest,chatbot,plugin_kwargs)

crazy_functions/知识库问答.py

@@ -1,10 +1,19 @@
-from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_lastest_msg
+from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_lastest_msg, get_log_folder, get_user
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_files_from_everything
 
+install_msg ="""
 
+1. python -m pip install torch --index-url https://download.pytorch.org/whl/cpu
+
+2. python -m pip install transformers protobuf langchain sentence-transformers  faiss-cpu nltk beautifulsoup4 bitsandbytes tabulate icetk --upgrade
+
+3. python -m pip install unstructured[all-docs] --upgrade
+
+4. python -c 'import nltk; nltk.download("punkt")'
+"""
 
 @CatchException
-def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数, 如温度和top_p等, 一般原样传递下去就行
@@ -12,7 +21,7 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
 
@@ -25,15 +34,15 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
 
     # resolve deps
     try:
-        from zh_langchain import construct_vector_store
-        from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-        from .crazy_utils import knowledge_archive_interface
+        # from zh_langchain import construct_vector_store
+        # from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+        from crazy_functions.vector_fns.vector_database import knowledge_archive_interface
     except Exception as e:
-        chatbot.append(["依赖不足", "导入依赖失败。正在尝试自动安装，请查看终端的输出或耐心等待..."])
+        chatbot.append(["依赖不足", f"{str(e)}\n\n导入依赖失败。请用以下命令安装" + install_msg])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        from .crazy_utils import try_install_deps
-        try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
-        yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
+        # from .crazy_utils import try_install_deps
+        # try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
+        # yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
         return
 
     # < --------------------读取文件--------------- >
@@ -42,12 +51,12 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     for sp in spl:
         _, file_manifest_tmp, _ = get_files_from_everything(txt, type=f'.{sp}')
         file_manifest += file_manifest_tmp
-    
+
     if len(file_manifest) == 0:
         chatbot.append(["没有找到任何可读取文件", "当前支持的格式包括: txt, md, docx, pptx, pdf, json等"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
-    
+
     # < -------------------预热文本向量化模组--------------- >
     chatbot.append(['<br/>'.join(file_manifest), "正在预热文本向量化模组, 如果是第一次运行, 将消耗较长时间下载中文向量化模型..."])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -62,30 +71,31 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     print('Establishing knowledge archive ...')
     with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
         kai = knowledge_archive_interface()
-        kai.feed_archive(file_manifest=file_manifest, id=kai_id)
-    kai_files = kai.get_loaded_file()
+        vs_path = get_log_folder(user=get_user(chatbot), plugin_name='vec_store')
+        kai.feed_archive(file_manifest=file_manifest, vs_path=vs_path, id=kai_id)
+    kai_files = kai.get_loaded_file(vs_path=vs_path)
     kai_files = '<br/>'.join(kai_files)
     # chatbot.append(['知识库构建成功', "正在将知识库存储至cookie中"])
     # yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     # chatbot._cookies['langchain_plugin_embedding'] = kai.get_current_archive_id()
-    # chatbot._cookies['lock_plugin'] = 'crazy_functions.Langchain知识库->读取知识库作答'
+    # chatbot._cookies['lock_plugin'] = 'crazy_functions.知识库文件注入->读取知识库作答'
     # chatbot.append(['完成', "“根据知识库作答”函数插件已经接管问答系统, 提问吧! 但注意, 您接下来不能再使用其他插件了，刷新页面即可以退出知识库问答模式。"])
     chatbot.append(['构建完成', f"当前知识库内的有效文件：\n\n---\n\n{kai_files}\n\n---\n\n请切换至“知识库问答”插件进行知识库访问, 或者使用此插件继续上传更多文件。"])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
 @CatchException
-def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port=-1):
+def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request=-1):
     # resolve deps
     try:
-        from zh_langchain import construct_vector_store
-        from langchain.embeddings.huggingface import HuggingFaceEmbeddings
-        from .crazy_utils import knowledge_archive_interface
+        # from zh_langchain import construct_vector_store
+        # from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+        from crazy_functions.vector_fns.vector_database import knowledge_archive_interface
     except Exception as e:
-        chatbot.append(["依赖不足", "导入依赖失败。正在尝试自动安装，请查看终端的输出或耐心等待..."])
+        chatbot.append(["依赖不足", f"{str(e)}\n\n导入依赖失败。请用以下命令安装" + install_msg])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-        from .crazy_utils import try_install_deps
-        try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
-        yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
+        # from .crazy_utils import try_install_deps
+        # try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
+        # yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
         return
 
     # < -------------------  --------------- >
@@ -93,13 +103,14 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
 
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     kai_id = plugin_kwargs.get("advanced_arg", 'default')
-    resp, prompt = kai.answer_with_archive_by_id(txt, kai_id)
+    vs_path = get_log_folder(user=get_user(chatbot), plugin_name='vec_store')
+    resp, prompt = kai.answer_with_archive_by_id(txt, kai_id, vs_path)
 
     chatbot.append((txt, f'[知识库 {kai_id}] ' + prompt))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=prompt, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        inputs=prompt, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
         sys_prompt=system_prompt
     )
     history.extend((prompt, gpt_say))

crazy_functions/联网的ChatGPT.py

@@ -2,7 +2,7 @@ from toolbox import CatchException, update_ui
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
 import requests
 from bs4 import BeautifulSoup
-from request_llm.bridge_all import model_info
+from request_llms.bridge_all import model_info
 
 def google(query, proxies):
     query = query # 在此处替换您要搜索的关键词
@@ -40,10 +40,10 @@ def scrape_text(url, proxies) -> str:
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
         'Content-Type': 'text/plain',
     }
-    try: 
+    try:
         response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
         if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
-    except: 
+    except:
         return "无法连接到该网页"
     soup = BeautifulSoup(response.text, "html.parser")
     for script in soup(["script", "style"]):
@@ -55,7 +55,7 @@ def scrape_text(url, proxies) -> str:
     return text
 
 @CatchException
-def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -63,16 +63,16 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
-    chatbot.append((f"请结合互联网信息回答以下问题：{txt}", 
+    chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
                     "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该模板可以实现ChatGPT联网信息综合。该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板。您若希望分享新的功能模组，请不吝PR！"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
     # ------------- < 第1步：爬取搜索引擎的结果 > -------------
     from toolbox import get_conf
-    proxies, = get_conf('proxies')
+    proxies = get_conf('proxies')
     urls = google(txt, proxies)
     history = []
     if len(urls) == 0:
@@ -91,13 +91,13 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     # ------------- < 第3步：ChatGPT综合 > -------------
     i_say = f"从以上搜索结果中抽取信息，然后回答问题：{txt}"
     i_say, history = input_clipping(    # 裁剪输入，从最长的条目开始裁剪，防止爆token
-        inputs=i_say, 
-        history=history, 
+        inputs=i_say,
+        history=history,
         max_token_limit=model_info[llm_kwargs['llm_model']]['max_token']*3//4
     )
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=i_say, inputs_show_user=i_say, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=i_say, inputs_show_user=i_say,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt="请从给定的若干条搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。"
     )
     chatbot[-1] = (i_say, gpt_say)

crazy_functions/联网的ChatGPT_bing版.py

@@ -2,7 +2,7 @@ from toolbox import CatchException, update_ui
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
 import requests
 from bs4 import BeautifulSoup
-from request_llm.bridge_all import model_info
+from request_llms.bridge_all import model_info
 
 
 def bing_search(query, proxies=None):
@@ -55,7 +55,7 @@ def scrape_text(url, proxies) -> str:
     return text
 
 @CatchException
-def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -63,7 +63,7 @@ def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, histor
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
     chatbot.append((f"请结合互联网信息回答以下问题：{txt}",
@@ -72,7 +72,7 @@ def 连接bing搜索回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, histor
 
     # ------------- < 第1步：爬取搜索引擎的结果 > -------------
     from toolbox import get_conf
-    proxies, = get_conf('proxies')
+    proxies = get_conf('proxies')
     urls = bing_search(txt, proxies)
     history = []
     if len(urls) == 0:

crazy_functions/虚空终端.py

@@ -33,7 +33,7 @@ explain_msg = """
     - 「请调用插件，解析python源代码项目，代码我刚刚打包拖到上传区了」
     - 「请问Transformer网络的结构是怎样的？」
 
-2. 您可以打开插件下拉菜单以了解本项目的各种能力。    
+2. 您可以打开插件下拉菜单以了解本项目的各种能力。
 
 3. 如果您使用「调用插件xxx」、「修改配置xxx」、「请问」等关键词，您的意图可以被识别的更准确。
 
@@ -48,7 +48,7 @@ from pydantic import BaseModel, Field
 from typing import List
 from toolbox import CatchException, update_ui, is_the_upload_folder
 from toolbox import update_ui_lastest_msg, disable_auto_promotion
-from request_llm.bridge_all import predict_no_ui_long_connection
+from request_llms.bridge_all import predict_no_ui_long_connection
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 from crazy_functions.crazy_utils import input_clipping
 from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
@@ -67,7 +67,7 @@ class UserIntention(BaseModel):
 def chat(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=txt, inputs_show_user=txt,
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
         sys_prompt=system_prompt
     )
     chatbot[-1] = [txt, gpt_say]
@@ -104,7 +104,7 @@ def analyze_intention_with_simple_rules(txt):
 
 
 @CatchException
-def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     disable_auto_promotion(chatbot=chatbot)
     # 获取当前虚空终端状态
     state = VoidTerminalState.get_state(chatbot)
@@ -115,13 +115,13 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     if is_the_upload_folder(txt):
         state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False)
         appendix_msg = "\n\n**很好，您已经上传了文件**，现在请您描述您的需求。"
-        
+
     if is_certain or (state.has_provided_explaination):
         # 如果意图明确，跳过提示环节
         state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
         state.unlock_plugin(chatbot=chatbot)
         yield from update_ui(chatbot=chatbot, history=history)
-        yield from 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
+        yield from 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
         return
     else:
         # 如果意图模糊，提示
@@ -133,7 +133,7 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
 
 
 
-def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []
     chatbot.append(("虚空终端状态: ", f"正在执行任务: {txt}"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -152,7 +152,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         analyze_res = run_gpt_fn(inputs, "")
         try:
             user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
-            lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}", 
+            lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
         except JsonStringError as e:
             yield from update_ui_lastest_msg(
                 lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 失败 当前语言模型（{llm_kwargs['llm_model']}）不能理解您的意图", chatbot=chatbot, history=history, delay=0)
@@ -161,7 +161,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         pass
 
     yield from update_ui_lastest_msg(
-        lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}", 
+        lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
         chatbot=chatbot, history=history, delay=0)
 
     # 用户意图: 修改本项目的配置

crazy_functions/解析JupyterNotebook.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 fast_debug = True
 
@@ -13,10 +13,9 @@ class PaperFileGroup():
         self.sp_file_tag = []
 
         # count_token
-        from request_llm.bridge_all import model_info
+        from request_llms.bridge_all import model_info
         enc = model_info["gpt-3.5-turbo"]['tokenizer']
-        def get_token_num(txt): return len(
-            enc.encode(txt, disallowed_special=()))
+        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
         self.get_token_num = get_token_num
 
     def run_file_split(self, max_token_limit=1900):
@@ -29,9 +28,8 @@ class PaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
-                segments = breakdown_txt_to_satisfy_token_limit_for_pdf(
-                    file_content, self.get_token_num, max_token_limit)
+                from crazy_functions.pdf_fns.breakdown_txt import breakdown_text_to_satisfy_token_limit
+                segments = breakdown_text_to_satisfy_token_limit(file_content, max_token_limit)
                 for j, segment in enumerate(segments):
                     self.sp_file_contents.append(segment)
                     self.sp_file_index.append(index)
@@ -62,7 +60,7 @@ def parseNotebook(filename, enable_markdown=1):
         Code += f"This is {idx+1}th code block: \n"
         Code += code+"\n"
 
-    return Code 
+    return Code
 
 
 def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
@@ -117,7 +115,7 @@ def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
 @CatchException
-def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     chatbot.append([
         "函数插件功能？",
         "对IPynb文件进行解析。Contributor: codycjy."])
@@ -131,7 +129,7 @@ def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
     else:
         if txt == "":
             txt = '空空如也的输入栏'
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return
@@ -141,7 +139,7 @@ def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         file_manifest = [f for f in glob.glob(
             f'{project_folder}/**/*.ipynb', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history,
+        report_exception(chatbot, history,
                          a=f"解析项目: {txt}", b=f"找不到任何.ipynb文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return

crazy_functions/解析项目源代码.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui, promote_file_to_downloadzone, disable_auto_promotion
-from toolbox import CatchException, report_execption, write_history_to_file
+from toolbox import CatchException, report_exception, write_history_to_file
 from .crazy_utils import input_clipping
 
 def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
@@ -82,12 +82,13 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             inputs=inputs, inputs_show_user=inputs_show_user, llm_kwargs=llm_kwargs, chatbot=chatbot,
             history=this_iteration_history_feed,   # 迭代之前的分析
             sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
-        
-        summary = "请用一句话概括这些文件的整体功能"
+
+        diagram_code = make_diagram(this_iteration_files, result, this_iteration_history_feed)
+        summary = "请用一句话概括这些文件的整体功能。\n\n" + diagram_code
         summary_result = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=summary, 
-            inputs_show_user=summary, 
-            llm_kwargs=llm_kwargs, 
+            inputs=summary,
+            inputs_show_user=summary,
+            llm_kwargs=llm_kwargs,
             chatbot=chatbot,
             history=[i_say, result],   # 迭代之前的分析
             sys_prompt="你是一个程序架构分析师，正在分析一个项目的源代码。" + sys_prompt_additional)
@@ -104,85 +105,88 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
     chatbot.append(("完成了吗？", res))
     yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
 
+def make_diagram(this_iteration_files, result, this_iteration_history_feed):
+    from crazy_functions.diagram_fns.file_tree import build_file_tree_mermaid_diagram
+    return build_file_tree_mermaid_diagram(this_iteration_history_feed[0::2], this_iteration_history_feed[1::2], "项目示意图")
 
 @CatchException
-def 解析项目本身(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析项目本身(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob
     file_manifest = [f for f in glob.glob('./*.py')] + \
                     [f for f in glob.glob('./*/*.py')]
     project_folder = './'
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
-def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个Python项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.py', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何python文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
-def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个Matlab项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.m', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到任何`.m`源文件: {txt}")
+        report_exception(chatbot, history, a = f"解析Matlab项目: {txt}", b = f"找不到任何`.m`源文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
-def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个C项目的头文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.h', recursive=True)]  + \
                     [f for f in glob.glob(f'{project_folder}/**/*.hpp', recursive=True)] #+ \
                     # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.h头文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.h头文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
-def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.h', recursive=True)]  + \
@@ -190,21 +194,21 @@ def 解析一个C项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system
                     [f for f in glob.glob(f'{project_folder}/**/*.hpp', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.h头文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.h头文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 
 @CatchException
-def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []  # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.java', recursive=True)] + \
@@ -212,21 +216,21 @@ def 解析一个Java项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
                     [f for f in glob.glob(f'{project_folder}/**/*.xml', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.sh', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何java文件: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何java文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 
 @CatchException
-def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []  # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.ts', recursive=True)] + \
@@ -241,21 +245,21 @@ def 解析一个前端项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
                     [f for f in glob.glob(f'{project_folder}/**/*.css', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.jsx', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何前端相关文件: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何前端相关文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 
 @CatchException
-def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []  # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.go', recursive=True)] + \
@@ -263,40 +267,40 @@ def 解析一个Golang项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
                     [f for f in glob.glob(f'{project_folder}/**/go.sum', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/go.work', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何golang文件: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何golang文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
-def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个Rust项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []  # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.rs', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.toml', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.lock', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何golang文件: {txt}")
+        report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何golang文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 @CatchException
-def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.lua', recursive=True)] + \
@@ -304,34 +308,34 @@ def 解析一个Lua项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
                     [f for f in glob.glob(f'{project_folder}/**/*.json', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.toml', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何lua文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何lua文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 
 @CatchException
-def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析一个CSharp项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.cs', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.csproj', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何CSharp文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何CSharp文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
 
 
 @CatchException
-def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     txt_pattern = plugin_kwargs.get("advanced_arg")
     txt_pattern = txt_pattern.replace("，", ",")
     # 将要匹配的模式(例如: *.c, *.cpp, *.py, config.toml)
@@ -341,9 +345,12 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     pattern_except_suffix = [_.lstrip(" ^*.,").rstrip(" ,") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^*.")]
     pattern_except_suffix += ['zip', 'rar', '7z', 'tar', 'gz'] # 避免解析压缩文件
     # 将要忽略匹配的文件名(例如: ^README.md)
-    pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", "\.") for _ in txt_pattern.split(" ") if _ != "" and _.strip().startswith("^") and not _.strip().startswith("^*.")]
+    pattern_except_name = [_.lstrip(" ^*,").rstrip(" ,").replace(".", r"\.") # 移除左边通配符，移除右侧逗号，转义点号
+                           for _ in txt_pattern.split(" ") # 以空格分割
+                           if (_ != "" and _.strip().startswith("^") and not _.strip().startswith("^*."))   # ^开始，但不是^*.开始
+                           ]
     # 生成正则表达式
-    pattern_except = '/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
+    pattern_except = r'/[^/]+\.(' + "|".join(pattern_except_suffix) + ')$'
     pattern_except += '|/(' + "|".join(pattern_except_name) + ')$' if pattern_except_name != [] else ''
 
     history.clear()
@@ -352,7 +359,7 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     # 若上传压缩文件, 先寻找到解压的文件夹路径, 从而避免解析压缩文件
@@ -365,7 +372,7 @@ def 解析任意code项目(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys
     file_manifest = [f for pattern in pattern_include for f in glob.glob(f'{extract_folder_path}/**/{pattern}', recursive=True) if "" != extract_folder_path and \
                       os.path.isfile(f) and (not re.search(pattern_except, f) or pattern.endswith('.' + re.search(pattern_except, f).group().split('.')[-1]))]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/询问多个大语言模型.py

@@ -1,8 +1,8 @@
-from toolbox import CatchException, update_ui
+from toolbox import CatchException, update_ui, get_conf
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 import datetime
 @CatchException
-def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -10,17 +10,18 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
-    chatbot.append((txt, "正在同时咨询ChatGPT和ChatGLM……"))
+    MULTI_QUERY_LLM_MODELS = get_conf('MULTI_QUERY_LLM_MODELS')
+    chatbot.append((txt, "正在同时咨询" + MULTI_QUERY_LLM_MODELS))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
     # llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo&api2d-gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
-    llm_kwargs['llm_model'] = 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
+    llm_kwargs['llm_model'] = MULTI_QUERY_LLM_MODELS # 支持任意数量的llm接口，用&符号分隔
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=txt, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=txt, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt=system_prompt,
         retry_times_at_unknown_error=0
     )
@@ -31,7 +32,7 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
 
 
 @CatchException
-def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -39,7 +40,7 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
 
@@ -51,8 +52,8 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
 
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-        inputs=txt, inputs_show_user=txt, 
-        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history, 
+        inputs=txt, inputs_show_user=txt,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
         sys_prompt=system_prompt,
         retry_times_at_unknown_error=0
     )

crazy_functions/语音助手.py

@@ -1,47 +1,35 @@
 from toolbox import update_ui
 from toolbox import CatchException, get_conf, markdown_convertion
 from crazy_functions.crazy_utils import input_clipping
-from request_llm.bridge_all import predict_no_ui_long_connection
+from crazy_functions.agent_fns.watchdog import WatchDog
+from request_llms.bridge_all import predict_no_ui_long_connection
 import threading, time
 import numpy as np
 from .live_audio.aliyunASR import AliyunASR
 import json
+import re
 
-class WatchDog():
-    def __init__(self, timeout, bark_fn, interval=3, msg="") -> None:
-        self.last_feed = None
-        self.timeout = timeout
-        self.bark_fn = bark_fn
-        self.interval = interval
-        self.msg = msg
-        self.kill_dog = False
-    
-    def watch(self):
-        while True:
-            if self.kill_dog: break
-            if time.time() - self.last_feed > self.timeout:
-                if len(self.msg) > 0: print(self.msg)
-                self.bark_fn()
-                break
-            time.sleep(self.interval)
-
-    def begin_watch(self):
-        self.last_feed = time.time()
-        th = threading.Thread(target=self.watch)
-        th.daemon = True
-        th.start()
-
-    def feed(self):
-        self.last_feed = time.time()
 
 def chatbot2history(chatbot):
     history = []
     for c in chatbot:
         for q in c:
-            if q not in ["[请讲话]", "[等待GPT响应]", "[正在等您说完问题]"]:
+            if q in ["[ 请讲话 ]", "[ 等待GPT响应 ]", "[ 正在等您说完问题 ]"]:
+                continue
+            elif q.startswith("[ 正在等您说完问题 ]"):
+                continue
+            else:
                 history.append(q.strip('<div class="markdown-body">').strip('</div>').strip('<p>').strip('</p>'))
     return history
 
+def visualize_audio(chatbot, audio_shape):
+    if len(chatbot) == 0: chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"])
+    chatbot[-1] = list(chatbot[-1])
+    p1 = '「'
+    p2 = '」'
+    chatbot[-1][-1] = re.sub(p1+r'(.*)'+p2, '', chatbot[-1][-1])
+    chatbot[-1][-1] += (p1+f"`{audio_shape}`"+p2)
+
 class AsyncGptTask():
     def __init__(self) -> None:
         self.observe_future = []
@@ -51,7 +39,7 @@ class AsyncGptTask():
         try:
             MAX_TOKEN_ALLO = 2560
             i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
-            gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt, 
+            gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
                                                             observe_window=observe_window[index], console_slience=True)
         except ConnectionAbortedError as token_exceed_err:
             print('至少一个线程任务Token溢出而失败', e)
@@ -81,8 +69,9 @@ class InterviewAssistant(AliyunASR):
         self.capture_interval = 0.5 # second
         self.stop = False
         self.parsed_text = ""   # 下个句子中已经说完的部分, 由 test_on_result_chg() 写入
-        self.parsed_sentence = ""   # 某段话的整个句子,由 test_on_sentence_end() 写入
+        self.parsed_sentence = ""   # 某段话的整个句子, 由 test_on_sentence_end() 写入
         self.buffered_sentence = ""    #
+        self.audio_shape = ""   # 音频的可视化表现, 由 audio_convertion_thread() 写入
         self.event_on_result_chg = threading.Event()
         self.event_on_entence_end = threading.Event()
         self.event_on_commit_question = threading.Event()
@@ -117,7 +106,7 @@ class InterviewAssistant(AliyunASR):
     def begin(self, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
         # main plugin function
         self.init(chatbot)
-        chatbot.append(["[请讲话]", "[正在等您说完问题]"])
+        chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         self.plugin_wd.begin_watch()
         self.agt = AsyncGptTask()
@@ -131,7 +120,7 @@ class InterviewAssistant(AliyunASR):
             yield from update_ui(chatbot=chatbot, history=history)      # 刷新界面
             self.plugin_wd.feed()
 
-            if self.event_on_result_chg.is_set(): 
+            if self.event_on_result_chg.is_set():
                 # called when some words have finished
                 self.event_on_result_chg.clear()
                 chatbot[-1] = list(chatbot[-1])
@@ -157,14 +146,18 @@ class InterviewAssistant(AliyunASR):
 
                 self.commit_wd.begin_watch()
                 chatbot[-1] = list(chatbot[-1])
-                chatbot[-1] = [self.buffered_sentence, "[等待GPT响应]"]
+                chatbot[-1] = [self.buffered_sentence, "[ 等待GPT响应 ]"]
                 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
                 # add gpt task 创建子线程请求gpt，避免线程阻塞
                 history = chatbot2history(chatbot)
                 self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt)
-                
+
                 self.buffered_sentence = ""
-                chatbot.append(["[请讲话]", "[正在等您说完问题]"])
+                chatbot.append(["[ 请讲话 ]", "[ 正在等您说完问题 ]"])
+                yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+            if not self.event_on_result_chg.is_set() and not self.event_on_entence_end.is_set() and not self.event_on_commit_question.is_set():
+                visualize_audio(chatbot, self.audio_shape)
                 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
         if len(self.stop_msg) != 0:
@@ -173,7 +166,7 @@ class InterviewAssistant(AliyunASR):
 
 
 @CatchException
-def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     # pip install -U openai-whisper
     chatbot.append(["对话助手函数插件：使用时，双手离开鼠标键盘吧", "音频助手, 正在听您讲话（点击“停止”键可终止程序）..."])
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -183,7 +176,7 @@ def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
         import nls
         from scipy import io
     except:
-        chatbot.append(["导入依赖失败", "使用该模块需要额外依赖, 安装方法:```pip install --upgrade aliyun-python-sdk-core==2.13.3 pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git```"])
+        chatbot.append(["导入依赖失败", "使用该模块需要额外依赖, 安装方法:```pip install --upgrade aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git```"])
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 

crazy_functions/读文章写摘要.py

@@ -1,5 +1,5 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption
+from toolbox import CatchException, report_exception
 from toolbox import write_history_to_file, promote_file_to_downloadzone
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 
@@ -44,21 +44,21 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
 
 
 @CatchException
-def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 读文章写摘要(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     history = []    # 清空历史，以免输入溢出
     import glob, os
     if os.path.exists(txt):
         project_folder = txt
     else:
         if txt == "": txt = '空空如也的输入栏'
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] # + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
                     # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
     if len(file_manifest) == 0:
-        report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
+        report_exception(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
     yield from 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)

crazy_functions/谷歌检索小助手.py

@@ -1,5 +1,5 @@
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from toolbox import CatchException, report_execption, promote_file_to_downloadzone
+from toolbox import CatchException, report_exception, promote_file_to_downloadzone
 from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion, write_history_to_file
 import logging
 import requests
@@ -17,16 +17,22 @@ def get_meta_information(url, chatbot, history):
     from urllib.parse import urlparse
     session = requests.session()
 
-    proxies, = get_conf('proxies')
+    proxies = get_conf('proxies')
     headers = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36',
-        'Accept-Encoding': 'gzip, deflate, br', 
+        'Accept-Encoding': 'gzip, deflate, br',
         'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7',
         'Cache-Control':'max-age=0',
-        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', 
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
         'Connection': 'keep-alive'
     }
-    session.proxies.update(proxies)
+    try:
+        session.proxies.update(proxies)
+    except:
+        report_exception(chatbot, history,
+                    a=f"获取代理失败 无代理状态下很可能无法访问OpenAI家族的模型及谷歌学术 建议：检查USE_PROXY选项是否修改。",
+                    b=f"尝试直接连接")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
     session.headers.update(headers)
 
     response = session.get(url)
@@ -89,7 +95,7 @@ def get_meta_information(url, chatbot, history):
         )
         try: paper = next(search.results())
         except: paper = None
-        
+
         is_match = paper is not None and string_similar(title, paper.title) > 0.90
 
         # 如果在Arxiv上匹配失败，检索文章的历史版本的题目
@@ -126,7 +132,7 @@ def get_meta_information(url, chatbot, history):
     return profile
 
 @CatchException
-def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     disable_auto_promotion(chatbot=chatbot)
     # 基本信息：功能、贡献者
     chatbot.append([
@@ -140,8 +146,8 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         import math
         from bs4 import BeautifulSoup
     except:
-        report_execption(chatbot, history, 
-            a = f"解析项目: {txt}", 
+        report_exception(chatbot, history,
+            a = f"解析项目: {txt}",
             b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade beautifulsoup4 arxiv```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
@@ -157,7 +163,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         if len(meta_paper_info_list[:batchsize]) > 0:
             i_say = "下面是一些学术文献的数据，提取出以下内容：" + \
             "1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开（is_paper_in_arxiv）；4、引用数量（cite）；5、中文摘要翻译。" + \
-            f"以下是信息源：{str(meta_paper_info_list[:batchsize])}" 
+            f"以下是信息源：{str(meta_paper_info_list[:batchsize])}"
 
             inputs_show_user = f"请分析此页面中出现的所有文章：{txt}，这是第{batch+1}批"
             gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
@@ -169,11 +175,11 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
             history.extend([ f"第{batch+1}批", gpt_say ])
             meta_paper_info_list = meta_paper_info_list[batchsize:]
 
-    chatbot.append(["状态？", 
+    chatbot.append(["状态？",
         "已经全部完成，您可以试试让AI写一个Related Works，例如您可以继续输入Write a \"Related Works\" section about \"你搜索的研究领域\" for me."])
     msg = '正常'
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
     path = write_history_to_file(history)
     promote_file_to_downloadzone(path, chatbot=chatbot)
-    chatbot.append(("完成了吗？", path)); 
+    chatbot.append(("完成了吗？", path));
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面

crazy_functions/辅助功能.py

@@ -2,13 +2,16 @@
 # @Time   : 2023/4/19
 # @Author : Spike
 # @Descr   :
-from toolbox import update_ui, get_conf
+from toolbox import update_ui, get_conf, get_user
 from toolbox import CatchException
+from toolbox import default_user_name
 from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+import shutil
+import os
 
 
 @CatchException
-def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     if txt:
         show_say = txt
         prompt = txt+'\n回答完问题后，再列出用户可能提出的三个问题。'
@@ -29,14 +32,23 @@ def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
 
 
 @CatchException
-def 清除缓存(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 清除缓存(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     chatbot.append(['清除本地缓存数据', '执行中. 删除数据'])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
 
-    import shutil, os
-    PATH_PRIVATE_UPLOAD, PATH_LOGGING = get_conf('PATH_PRIVATE_UPLOAD', 'PATH_LOGGING')
-    shutil.rmtree(PATH_LOGGING, ignore_errors=True)
-    shutil.rmtree(PATH_PRIVATE_UPLOAD, ignore_errors=True)
+    def _get_log_folder(user=default_user_name):
+        PATH_LOGGING = get_conf('PATH_LOGGING')
+        _dir = os.path.join(PATH_LOGGING, user)
+        if not os.path.exists(_dir): os.makedirs(_dir)
+        return _dir
+
+    def _get_upload_folder(user=default_user_name):
+        PATH_PRIVATE_UPLOAD = get_conf('PATH_PRIVATE_UPLOAD')
+        _dir = os.path.join(PATH_PRIVATE_UPLOAD, user)
+        return _dir
+
+    shutil.rmtree(_get_log_folder(get_user(chatbot)), ignore_errors=True)
+    shutil.rmtree(_get_upload_folder(get_user(chatbot)), ignore_errors=True)
 
     chatbot.append(['清除本地缓存数据', '执行完成'])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面

crazy_functions/高级功能函数模板.py

@@ -1,8 +1,77 @@
 from toolbox import CatchException, update_ui
-from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
 import datetime
+
+高阶功能模板函数示意图 = f"""
+```mermaid
+flowchart TD
+    %% <gpt_academic_hide_mermaid_code> 一个特殊标记，用于在生成mermaid图表时隐藏代码块
+    subgraph 函数调用["函数调用过程"]
+        AA["输入栏用户输入的文本(txt)"] --> BB["gpt模型参数(llm_kwargs)"]
+        BB --> CC["插件模型参数(plugin_kwargs)"]
+        CC --> DD["对话显示框的句柄(chatbot)"]
+        DD --> EE["对话历史(history)"]
+        EE --> FF["系统提示词(system_prompt)"]
+        FF --> GG["当前用户信息(web_port)"]
+
+        A["开始(查询5天历史事件)"]
+        A --> B["获取当前月份和日期"]
+        B --> C["生成历史事件查询提示词"]
+        C --> D["调用大模型"]
+        D --> E["更新界面"]
+        E --> F["记录历史"]
+        F --> |"下一天"| B
+    end
+```
+"""
+
 @CatchException
-def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
+    """
+    # 高阶功能模板函数示意图：https://mermaid.live/edit#pako:eNptk1tvEkEYhv8KmattQpvlvOyFCcdeeaVXuoYssBwie8gyhCIlqVoLhrbbtAWNUpEGUkyMEDW2Fmn_DDOL_8LZHdOwxrnamX3f7_3mmZk6yKhZCfAgV1KrmYKoQ9fDuKC4yChX0nld1Aou1JzjznQ5fWmejh8LYHW6vG2a47YAnlCLNSIRolnenKBXI_zRIBrcuqRT890u7jZx7zMDt-AaMbnW1--5olGiz2sQjwfoQxsZL0hxplSSU0-rop4vrzmKR6O2JxYjHmwcL2Y_HDatVMkXlf86YzHbGY9bO5j8XE7O8Nsbc3iNB3ukL2SMcH-XIQBgWoVOZzxuOxOJOyc63EPGV6ZQLENVrznViYStTiaJ2vw2M2d9bByRnOXkgCnXylCSU5quyto_IcmkbdvctELmJ-j1ASW3uB3g5xOmKqVTmqr_Na3AtuS_dtBFm8H90XJyHkDDT7S9xXWb4HGmRChx64AOL5HRpUm411rM5uh4H78Z4V7fCZzytjZz2seto9XaNPFue07clLaVZF8UNLygJ-VES8lah_n-O-5Ozc7-77NzJ0-K0yr0ZYrmHdqAk50t2RbA4qq9uNohBASw7YpSgaRkLWCCAtxAlnRZLGbJba9bPwUAC5IsCYAnn1kpJ1ZKUACC0iBSsQLVBzUlA3ioVyQ3qGhZEUrxokiehAz4nFgqk1VNVABfB1uAD_g2_AGPl-W8nMcbCvsDblADfNCz4feyobDPy3rYEMtxwYYbPFNVUoHdCPmDHBv2cP4AMfrCbiBli-Q-3afv0X6WdsIjW2-10fgDy1SAig
+
+    txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
+    llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
+    plugin_kwargs   插件模型的参数，用于灵活调整复杂功能的各种参数
+    chatbot         聊天显示框的句柄，用于显示给用户
+    history         聊天历史，前情提要
+    system_prompt   给gpt的静默提醒
+    user_request    当前用户的请求信息（IP地址等）
+    """
+    history = []    # 清空历史，以免输入溢出
+    chatbot.append((
+        "您正在调用插件：历史上的今天",
+        "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板（该函数只有20多行代码）。此外我们也提供可同步处理大量文件的多线程Demo供您参考。您若希望分享新的功能模组，请不吝PR！" + 高阶功能模板函数示意图))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
+    for i in range(5):
+        currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
+        currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
+        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=i_say, inputs_show_user=i_say,
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
+            sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
+        )
+        chatbot[-1] = (i_say, gpt_say)
+        history.append(i_say);history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+
+
+
+PROMPT = """
+请你给出围绕“{subject}”的逻辑关系图，使用mermaid语法，mermaid语法举例：
+```mermaid
+graph TD
+    P(编程) --> L1(Python)
+    P(编程) --> L2(C)
+    P(编程) --> L3(C++)
+    P(编程) --> L4(Javascipt)
+    P(编程) --> L5(PHP)
+```
+"""
+@CatchException
+def 测试图表渲染(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
@@ -10,20 +79,21 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
-    web_port        当前软件运行的端口号
+    user_request    当前用户的请求信息（IP地址等）
     """
     history = []    # 清空历史，以免输入溢出
-    chatbot.append(("这是什么功能？", "[Local Message] 请注意，您正在调用一个[函数插件]的模板，该函数面向希望实现更多有趣功能的开发者，它可以作为创建新功能函数的模板（该函数只有20多行代码）。此外我们也提供可同步处理大量文件的多线程Demo供您参考。您若希望分享新的功能模组，请不吝PR！"))
+    chatbot.append(("这是什么功能？", "一个测试mermaid绘制图表的功能，您可以在输入框中输入一些关键词，然后使用mermaid+llm绘制图表。"))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
-    for i in range(5):
-        currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
-        currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
-        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, inputs_show_user=i_say, 
-            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
-            sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
-        )
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say);history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+
+    if txt == "": txt = "空白的输入栏" # 调皮一下
+
+    i_say_show_user = f'请绘制有关“{txt}”的逻辑关系图。'
+    i_say = PROMPT.format(subject=txt)
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=i_say,
+        inputs_show_user=i_say_show_user,
+        llm_kwargs=llm_kwargs, chatbot=chatbot, history=[],
+        sys_prompt=""
+    )
+    history.append(i_say); history.append(gpt_say)
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新

docker-compose.yml

@@ -1,17 +1,41 @@
-#【请修改完参数后，删除此行】请在以下方案中选择一种，然后删除其他的方案，最后docker-compose up运行 | Please choose from one of these options below, delete other options as well as This Line
+## ===================================================
+#                docker-compose.yml
+## ===================================================
+# 1. 请在以下方案中选择任意一种，然后删除其他的方案
+# 2. 修改你选择的方案中的environment环境变量，详情请见github wiki或者config.py
+# 3. 选择一种暴露服务端口的方法，并对相应的配置做出修改：
+    # 「方法1: 适用于Linux，很方便，可惜windows不支持」与宿主的网络融合为一体，这个是默认配置
+    # network_mode: "host"
+    # 「方法2: 适用于所有系统包括Windows和MacOS」端口映射，把容器的端口映射到宿主的端口（注意您需要先删除network_mode: "host"，再追加以下内容）
+    # ports:
+    #   - "12345:12345"  # 注意！12345必须与WEB_PORT环境变量相互对应
+# 4. 最后`docker-compose up`运行
+# 5. 如果希望使用显卡，请关注 LOCAL_MODEL_DEVICE 和 英伟达显卡运行时 选项
+## ===================================================
+# 1. Please choose one of the following options and delete the others.
+# 2. Modify the environment variables in the selected option, see GitHub wiki or config.py for more details.
+# 3. Choose a method to expose the server port and make the corresponding configuration changes:
+    # [Method 1: Suitable for Linux, convenient, but not supported for Windows] Fusion with the host network, this is the default configuration
+    # network_mode: "host"
+    # [Method 2: Suitable for all systems including Windows and MacOS] Port mapping, mapping the container port to the host port (note that you need to delete network_mode: "host" first, and then add the following content)
+    # ports:
+    # - "12345: 12345" # Note! 12345 must correspond to the WEB_PORT environment variable.
+# 4. Finally, run `docker-compose up`.
+# 5. If you want to use a graphics card, pay attention to the LOCAL_MODEL_DEVICE and Nvidia GPU runtime options.
+## ===================================================
 
 ## ===================================================
-## 【方案零】 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
+## 「方案零」 部署项目的全部能力（这个是包含cuda和latex的大型镜像。如果您网速慢、硬盘小或没有显卡，则不推荐使用这个）
 ## ===================================================
 version: '3'
 services:
   gpt_academic_full_capability:
     image: ghcr.io/binary-husky/gpt_academic_with_all_capacity:master
     environment:
-    # 请查阅 `config.py`或者 github wiki 以查看所有的配置信息
+      # 请查阅 `config.py`或者 github wiki 以查看所有的配置信息
       API_KEY:                  '  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                        '
-    # USE_PROXY:                '  True                                                                       '
-    # proxies:                  '  { "http": "http://localhost:10881", "https": "http://localhost:10881", }   '
+      # USE_PROXY:                '  True                                                                       '
+      # proxies:                  '  { "http": "http://localhost:10881", "https": "http://localhost:10881", }   '
       LLM_MODEL:                '  gpt-3.5-turbo                                                              '
       AVAIL_LLM_MODELS:         '  ["gpt-3.5-turbo", "gpt-4", "qianfan", "sparkv2", "spark", "chatglm"]       '
       BAIDU_CLOUD_API_KEY :     '  bTUtwEAveBrQipEowUvDwYWq                                                   '
@@ -27,7 +51,7 @@ services:
       THEME:                    '  Chuanhu-Small-and-Beautiful                                                '
       ALIYUN_ACCESSKEY:         '  LTAI5t6BrFUzxRXVGUWnekh1                                                   '
       ALIYUN_SECRET:            '  eHmI20SVWIwQZxCiTD2bGQVspP9i68                                             '
-    # LOCAL_MODEL_DEVICE:       '  cuda                                                                       '
+      # LOCAL_MODEL_DEVICE:       '  cuda                                                                       '
 
     # 加载英伟达显卡运行时
     # runtime: nvidia
@@ -39,18 +63,20 @@ services:
     #             count: 1
     #             capabilities: [gpu]
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 「WEB_PORT暴露方法2: 适用于所有系统」端口映射
+    # ports:
+    #   - "12345:12345"  # 12345必须与WEB_PORT相互对应
+
+    # 启动容器后，运行main.py主程序
     command: >
       bash -c "python3 -u main.py"
 
 
-
-
 ## ===================================================
-## 【方案一】 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
+## 「方案一」 如果不需要运行本地模型（仅 chatgpt, azure, 星火, 千帆, claude 等在线大模型服务）
 ## ===================================================
 version: '3'
 services:
@@ -69,16 +95,16 @@ services:
       # DEFAULT_WORKER_NUM:       '    10                                                                                             '
       # AUTHENTICATION:           '    [("username", "passwd"), ("username2", "passwd2")]                                             '
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
 
 
 ### ===================================================
-### 【方案二】 如果需要运行ChatGLM + Qwen + MOSS等本地模型
+### 「方案二」 如果需要运行ChatGLM + Qwen + MOSS等本地模型
 ### ===================================================
 version: '3'
 services:
@@ -101,18 +127,21 @@ services:
     runtime: nvidia
     devices:
       - /dev/nvidia0:/dev/nvidia0
-      
-    # 与宿主的网络融合
+
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
+
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
 
     # P.S. 通过对 command 进行微调，可以便捷地安装额外的依赖
     # command: >
-    #   bash -c "pip install -r request_llm/requirements_qwen.txt && python3 -u main.py"
+    #   bash -c "pip install -r request_llms/requirements_qwen.txt && python3 -u main.py"
+
 
 ### ===================================================
-### 【方案三】 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
+### 「方案三」 如果需要运行ChatGPT + LLAMA + 盘古 + RWKV本地模型
 ### ===================================================
 version: '3'
 services:
@@ -135,17 +164,17 @@ services:
     runtime: nvidia
     devices:
       - /dev/nvidia0:/dev/nvidia0
-      
-    # 与宿主的网络融合
+
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       python3 -u main.py
 
 
 ## ===================================================
-## 【方案四】 ChatGPT + Latex
+## 「方案四」 ChatGPT + Latex
 ## ===================================================
 version: '3'
 services:
@@ -162,16 +191,16 @@ services:
       DEFAULT_WORKER_NUM:       '    10                                                                               '
       WEB_PORT:                 '    12303                                                                            '
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
 
 
 ## ===================================================
-## 【方案五】 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
+## 「方案五」 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
 ## ===================================================
 version: '3'
 services:
@@ -195,10 +224,9 @@ services:
       # (无需填写) ALIYUN_ACCESSKEY:         '    LTAI5q6BrFUzoRXVGUWnekh1                                         '
       # (无需填写) ALIYUN_SECRET:            '    eHmI20AVWIaQZ0CiTD2bGQVsaP9i68                                   '
 
-    # 与宿主的网络融合
+    # 「WEB_PORT暴露方法1: 适用于Linux」与宿主的网络融合
     network_mode: "host"
 
-    # 不使用代理网络拉取最新代码
+    # 启动命令
     command: >
       bash -c "python3 -u main.py"
-

docs/Dockerfile+ChatGLM

@@ -1,2 +1 @@
 # 此Dockerfile不再维护，请前往docs/GithubAction+ChatGLM+Moss
-

docs/Dockerfile+JittorLLM

@@ -1 +1 @@
-# 此Dockerfile不再维护，请前往docs/GithubAction+JittorLLMs
+# 此Dockerfile不再维护，请前往docs/GithubAction+JittorLLMs

docs/GithubAction+AllCapacity

@@ -14,18 +14,18 @@ RUN python3 -m pip install colorama Markdown pygments pymupdf
 RUN python3 -m pip install python-docx moviepy pdfminer
 RUN python3 -m pip install zh_langchain==0.2.1 pypinyin
 RUN python3 -m pip install rarfile py7zr
-RUN python3 -m pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+RUN python3 -m pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
 # 下载分支
 WORKDIR /gpt
 RUN git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
 WORKDIR /gpt/gpt_academic
-RUN git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llm/moss
+RUN git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss
 
 RUN python3 -m pip install -r requirements.txt
-RUN python3 -m pip install -r request_llm/requirements_moss.txt
-RUN python3 -m pip install -r request_llm/requirements_qwen.txt
-RUN python3 -m pip install -r request_llm/requirements_chatglm.txt
-RUN python3 -m pip install -r request_llm/requirements_newbing.txt
+RUN python3 -m pip install -r request_llms/requirements_moss.txt
+RUN python3 -m pip install -r request_llms/requirements_qwen.txt
+RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
+RUN python3 -m pip install -r request_llms/requirements_newbing.txt
 RUN python3 -m pip install nougat-ocr
 
 

docs/GithubAction+AllCapacityBeta

@@ -0,0 +1,53 @@
+# docker build -t gpt-academic-all-capacity -f docs/GithubAction+AllCapacity  --network=host --build-arg http_proxy=http://localhost:10881 --build-arg https_proxy=http://localhost:10881 .
+# docker build -t gpt-academic-all-capacity -f docs/GithubAction+AllCapacityBeta  --network=host .
+# docker run -it --net=host gpt-academic-all-capacity  bash
+
+# 从NVIDIA源，从而支持显卡（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
+FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
+
+# use python3 as the system default python
+WORKDIR /gpt
+RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
+
+# # 非必要步骤，更换pip源 （以下三行，可以删除）
+# RUN echo '[global]' > /etc/pip.conf && \
+#     echo 'index-url = https://mirrors.aliyun.com/pypi/simple/' >> /etc/pip.conf && \
+#     echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
+
+# 下载pytorch
+RUN python3 -m pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu113
+# 准备pip依赖
+RUN python3 -m pip install openai numpy arxiv rich
+RUN python3 -m pip install colorama Markdown pygments pymupdf
+RUN python3 -m pip install python-docx moviepy pdfminer
+RUN python3 -m pip install zh_langchain==0.2.1 pypinyin
+RUN python3 -m pip install rarfile py7zr
+RUN python3 -m pip install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+# 下载分支
+WORKDIR /gpt
+RUN git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+WORKDIR /gpt/gpt_academic
+RUN git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss
+
+RUN python3 -m pip install -r requirements.txt
+RUN python3 -m pip install -r request_llms/requirements_moss.txt
+RUN python3 -m pip install -r request_llms/requirements_qwen.txt
+RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
+RUN python3 -m pip install -r request_llms/requirements_newbing.txt
+RUN python3 -m pip install nougat-ocr
+
+# 预热Tiktoken模块
+RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+
+# 安装知识库插件的额外依赖
+RUN apt-get update && apt-get install libgl1 -y
+RUN pip3 install transformers protobuf langchain sentence-transformers  faiss-cpu nltk beautifulsoup4 bitsandbytes tabulate icetk --upgrade
+RUN pip3 install unstructured[all-docs] --upgrade
+RUN python3  -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
+RUN rm -rf /usr/local/lib/python3.8/dist-packages/tests
+
+
+# COPY .cache /root/.cache
+# COPY config_private.py config_private.py
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/GithubAction+ChatGLM+Moss

@@ -14,12 +14,12 @@ RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/
 WORKDIR /gpt
 RUN git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
 WORKDIR /gpt/gpt_academic
-RUN git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss
+RUN git clone https://github.com/OpenLMLab/MOSS.git request_llms/moss
 RUN python3 -m pip install -r requirements.txt
-RUN python3 -m pip install -r request_llm/requirements_moss.txt
-RUN python3 -m pip install -r request_llm/requirements_qwen.txt
-RUN python3 -m pip install -r request_llm/requirements_chatglm.txt
-RUN python3 -m pip install -r request_llm/requirements_newbing.txt
+RUN python3 -m pip install -r request_llms/requirements_moss.txt
+RUN python3 -m pip install -r request_llms/requirements_qwen.txt
+RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
+RUN python3 -m pip install -r request_llms/requirements_newbing.txt
 
 
 

docs/GithubAction+JittorLLMs

@@ -16,12 +16,12 @@ WORKDIR /gpt
 RUN git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
 WORKDIR /gpt/gpt_academic
 RUN python3 -m pip install -r requirements.txt
-RUN python3 -m pip install -r request_llm/requirements_chatglm.txt
-RUN python3 -m pip install -r request_llm/requirements_newbing.txt
-RUN python3 -m pip install -r request_llm/requirements_jittorllms.txt -i https://pypi.jittor.org/simple -I
+RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
+RUN python3 -m pip install -r request_llms/requirements_newbing.txt
+RUN python3 -m pip install -r request_llms/requirements_jittorllms.txt -i https://pypi.jittor.org/simple -I
 
 # 下载JittorLLMs
-RUN git clone https://github.com/binary-husky/JittorLLMs.git --depth 1 request_llm/jittorllms
+RUN git clone https://github.com/binary-husky/JittorLLMs.git --depth 1 request_llms/jittorllms
 
 # 禁用缓存，确保更新代码
 ADD "https://www.random.org/cgi-bin/randbyte?nbytes=10&format=h" skipcache

docs/GithubAction+NoLocal+AudioAssistant

@@ -13,7 +13,7 @@ COPY . .
 RUN pip3 install -r requirements.txt
 
 # 安装语音插件的额外依赖
-RUN pip3 install pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+RUN pip3 install aliyun-python-sdk-core==2.13.3 pyOpenSSL webrtcvad scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
 
 # 可选步骤，用于预热模块
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'

docs/GithubAction+NoLocal+Latex

@@ -4,16 +4,19 @@
 # - 3 运行 docker run -v /home/fuqingxu/arxiv_cache:/root/arxiv_cache --rm -it --net=host gpt-academic-nolocal-latex
 
 FROM fuqingxu/python311_texlive_ctex:latest
+ENV PATH "$PATH:/usr/local/texlive/2022/bin/x86_64-linux"
+ENV PATH "$PATH:/usr/local/texlive/2023/bin/x86_64-linux"
+ENV PATH "$PATH:/usr/local/texlive/2024/bin/x86_64-linux"
+ENV PATH "$PATH:/usr/local/texlive/2025/bin/x86_64-linux"
+ENV PATH "$PATH:/usr/local/texlive/2026/bin/x86_64-linux"
 
 # 指定路径
 WORKDIR /gpt
 
-RUN pip3 install gradio openai numpy arxiv rich
+RUN pip3 install openai numpy arxiv rich
 RUN pip3 install colorama Markdown pygments pymupdf
-RUN pip3 install python-docx moviepy pdfminer 
-RUN pip3 install zh_langchain==0.2.1
+RUN pip3 install python-docx pdfminer
 RUN pip3 install nougat-ocr
-RUN pip3 install aliyun-python-sdk-core==2.13.3 pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
 
 # 装载项目文件
 COPY . .

docs/GithubAction+NoLocal+Vectordb

@@ -0,0 +1,26 @@
+# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型，请参考 docs/Dockerfile+ChatGLM
+# 如何构建: 先修改 `config.py`， 然后 docker build -t gpt-academic-nolocal-vs -f docs/GithubAction+NoLocal+Vectordb .
+# 如何运行: docker run --rm -it --net=host gpt-academic-nolocal-vs
+FROM python:3.11
+
+# 指定路径
+WORKDIR /gpt
+
+# 装载项目文件
+COPY . .
+
+# 安装依赖
+RUN pip3 install -r requirements.txt
+
+# 安装知识库插件的额外依赖
+RUN apt-get update && apt-get install libgl1 -y
+RUN pip3 install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+RUN pip3 install transformers protobuf langchain sentence-transformers  faiss-cpu nltk beautifulsoup4 bitsandbytes tabulate icetk --upgrade
+RUN pip3 install unstructured[all-docs] --upgrade
+RUN python3  -c 'from check_proxy import warm_up_vectordb; warm_up_vectordb()'
+
+# 可选步骤，用于预热模块
+RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/README.Arabic.md

@@ -0,0 +1,343 @@
+
+
+
+> **ملحوظة**
+>
+> تمت ترجمة هذا الملف README باستخدام GPT (بواسطة المكون الإضافي لهذا المشروع) وقد لا تكون الترجمة 100٪ موثوقة، يُرجى التمييز بعناية بنتائج الترجمة.
+>
+> 2023.11.7: عند تثبيت التبعيات، يُرجى اختيار الإصدار المُحدد في `requirements.txt`. الأمر للتثبيت: `pip install -r requirements.txt`.
+
+# <div align=center><img src="logo.png" width="40"> GPT الأكاديمي</div>
+
+**إذا كنت تحب هذا المشروع، فيُرجى إعطاؤه Star. لترجمة هذا المشروع إلى لغة عشوائية باستخدام GPT، قم بقراءة وتشغيل [`multi_language.py`](multi_language.py) (تجريبي).
+
+> **ملحوظة**
+>
+> 1. يُرجى ملاحظة أنها الإضافات (الأزرار) المميزة فقط التي تدعم قراءة الملفات، وبعض الإضافات توجد في قائمة منسدلة في منطقة الإضافات. بالإضافة إلى ذلك، نرحب بأي Pull Request جديد بأعلى أولوية لأي إضافة جديدة.
+>
+> 2. تُوضّح كل من الملفات في هذا المشروع وظيفتها بالتفصيل في [تقرير الفهم الذاتي `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告). يمكنك في أي وقت أن تنقر على إضافة وظيفة ذات صلة لاستدعاء GPT وإعادة إنشاء تقرير الفهم الذاتي للمشروع. للأسئلة الشائعة [`الويكي`](https://github.com/binary-husky/gpt_academic/wiki). [طرق التثبيت العادية](#installation) |  [نصب بنقرة واحدة](https://github.com/binary-husky/gpt_academic/releases) | [تعليمات التكوين](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+>
+> 3. يتم توافق هذا المشروع مع ودعم توصيات اللغة البيجائية الأكبر شمولًا وشجاعة لمثل ChatGLM. يمكنك توفير العديد من مفاتيح Api المشتركة في تكوين الملف، مثل `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`. عند تبديل مؤقت لـ `API_KEY`، قم بإدخال `API_KEY` المؤقت في منطقة الإدخال ثم اضغط على زر "إدخال" لجعله ساري المفعول.
+
+
+
+<div align="center">
+
+الوظائف (⭐= وظائف مُضافة حديثًا) | الوصف
+--- | ---
+⭐[التوصل لنموذج جديد](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)! | بحث بيدو[تشيان فان](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu) ووينسين[جينرال](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)، مختبرات شنغهاي للذكاء الصناعي[شو شينغ](https://github.com/InternLM/InternLM)، إكسنفلام[زينغهو]https://xinghuo.xfyun.cn/)، [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)، واجهة بيانية ذكية و3 خدمات إضافية [DALLE3]
+الجودة الفائقة، الترجمة، شرح الكود | الإصلاح الفوري للاخطاء النحوية في الأبحاث وترجمة وتحسين التصريف اللغوي للأكواد
+[اختصارات مخصصة](https://www.bilibili.com/video/BV14s4y1E7jN) | دعم الاختصارات المخصصة
+تصميم قابل للتوسيع | دعم الإضافات القوية المخصصة (الوظائف)، الإضافات قابلة للتحديث بشكل فوري
+[تحليل البرنامج](https://www.bilibili.com/video/BV1cj411A7VW) | [وظائف] التحليل الشجري بناءً على البرنامج من Python/C/C++/Java/Lua/..., أو [التحليل الذاتي](https://www.bilibili.com/video/BV1cj411A7VW)
+قراءة وترجمة الأبحاث | [وظائف] فك تشفير كامل لأوراق البحث بتنسيق LaTeX/PDF وإنشاء مستخلص
+ترجمة وتحسين أوراق اللاتكس | [وظائف] ترجمة أو تحسين الأوراق المكتوبة بلاتكس
+إنشاء تعليقات الدوال دفعة واحدة | [وظائف] إنشاء تعليقات الدوال بدفعة واحدة
+ترجمة Markdown بين اللغتين العربية والإنجليزية | [وظائف] هل رأيت الـ 5 لغات المستخدمة في منشور [README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md) ؟
+إنشاء تقرير تحليل الدردشة | [وظائف] إنشاء تقرير ملخص بعد تشغيله
+ترجمة كاملة لأوراق PDF | [وظائف] تحليل الأوراق بتنسيق PDF لتحديد العنوان وملخصها وترجمتها (متعدد الخيوط)
+مساعدة Arxiv | [وظائف] قم بإدخال رابط مقال Arxiv لترجمة الملخص وتحميل ملف PDF
+تصحيح لاتكس بضغطة زر واحدة | [وظائف] إكمال تصحيح لاتكس بناءً على التركيبة النحوية، إخراج همز المقابل للمقارنة PDF
+مساعد بحث Google بنسخة محلية | [وظائف] قم بتقديم رابط لصفحة بحث Google Scholar العشوائي حتى يساعدك GPT في كتابة [الأبحاث المتعلقة](https://www.bilibili.com/video/BV1GP411U7Az/)
+تجميع معلومات الويب + GPT | [وظائف] جمع المعلومات من الويب بشكل سهل للرد على الأسئلة لجعل المعلومات محدثة باستمرار
+⭐ترجمة دقيقة لأوراق Arxiv ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [وظائف] ترجمة مقالات Arxiv عالية الجودة بنقرة واحدة، أفضل أداة حاليا للترجمة
+⭐[إدخال الصوت الفوري](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [وظائف] (غير متزامن) استماع الصوت وقطعه تلقائيًا وتحديد وقت الإجابة تلقائيًا
+عرض الصيغ/الصور/الجداول | يمكن عرض الصيغ بشكل [TEX](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png) وأيضًا بتنسيق رسومي، يدعم عرض الصيغ وإبراز الكود
+⭐إضغط على وكيل "شارلوت الذكي" | [وظائف] استكمال الذكاء للكأس الأول للذكاء المكتسب من مايكروسوفت، اكتشاف وتطوير عالمي العميل
+تبديل الواجهة المُظلمة | يمكنك التبديل إلى الواجهة المظلمة بإضافة ```/?__theme=dark``` إلى نهاية عنوان URL في المتصفح
+دعم المزيد من نماذج LLM | دعم لجميع GPT3.5 وGPT4 و[ChatGLM2 في جامعة ثوه في لين](https://github.com/THUDM/ChatGLM2-6B) و[MOSS في جامعة فودان](https://github.com/OpenLMLab/MOSS)
+⭐تحوي انطباعة "ChatGLM2" | يدعم استيراد "ChatGLM2" ويوفر إضافة المساعدة في تعديله
+دعم المزيد من نماذج "LLM"، دعم [نشر الحديس](https://huggingface.co/spaces/qingxu98/gpt-academic) | انضم إلى واجهة "Newbing" (Bing الجديدة)،نقدم نماذج Jittorllms الجديدة تؤيدهم [LLaMA](https://github.com/facebookresearch/llama) و   [盘古α](https://openi.org.cn/pangu/)
+⭐حزمة "void-terminal" للشبكة (pip) | قم بطلب كافة وظائف إضافة هذا المشروع في python بدون واجهة رسومية (قيد التطوير)
+⭐PCI-Express لإعلام (PCI) | [وظائف] باللغة الطبيعية، قم بتنفيذ المِهام الأخرى في المشروع
+المزيد من العروض (إنشاء الصور وغيرها)……| شاهد أكثر في نهاية هذا المستند ...
+</div>
+
+
+- شكل جديد (عن طريق تعديل الخيار LAYOUT في `config.py` لقانون التوزيع "اليمين أو اليسار" أو "الأعلى أو الأسفل")
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- جميع الأزرار يتم إنشاؤها ديناميكيًا من خلال قراءة functional.py ويمكن إضافة وظائف مخصصة بحرية وتحرير الحافظة
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- التجميل / التحوير
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- إذا تضمّن الإخراج معادلات، فسيتم عرضها بشكلٍ يمكّن من النسخ والقراءة على النحوين: TEX ورسومية.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- هل تشعر بالكسل من قراءة كود المشروع؟ قم بمدها مباشرةً إلى ChatGPT
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- دمج نماذج اللغات الكبيرة المختلفة (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Installation
+### طريقة التثبيت الأولى: التشغيل المباشر (Windows، Linux أو MacOS)
+
+1. قم بتنزيل المشروع
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. قم بتكوين لغة البرمجة Python
+
+في ملف `config.py`، قم بتكوين مفتاح الواجهة API والإعدادات الأخرى، [انقر هنا للاطلاع على طريقة تكوين الإعدادات في بيئة شبكة خاصة](https://github.com/binary-husky/gpt_academic/issues/1). [انقر هنا لزيارة صفحة الويكي](https://github.com/binary-husky/gpt_academic/wiki/توضيحات-تكوين-المشروع).
+
+" ستقوم البرنامج بفحص وجود ملف تكوين خاص يسمى `config_private.py` بأولوية، وسيستخدم التكوينات الموجودة فيه لتجاوز التكوينات ذات الأسماء المطابقة في `config.py`. إذا كنت تفهم هذه الطريقة ونظام القراءة، فإننا نوصي بشدة بإنشاء ملف تكوين جديد يسمى `config_private.py` بجوار `config.py` ونقل (نسخ) التكوينات الموجودة في `config.py` إلى `config_private.py` (يجب نسخ العناصر التي قمت بتعديلها فقط). "
+
+" يدعم المشروع التكوين من خلال `المتغيرات المحيطية`، ويمكن تحديد تنسيق كتابة المتغيرات المحيطية من خلال ملف `docker-compose.yml` أو صفحة الويكي الخاصة بنا. تعتمد أولوية القراءة على التكوينات على التالي: `المتغيرات المحيطية` > `config_private.py` > `config.py`. "
+
+3. قم بتثبيت التبعيات
+```sh
+# (الخيار الأول: إذا كنت تعرف Python، python>=3.9) الملحوظة: استخدم مستودع pip الرسمي أو مستودع pip آلي بباي، يمكن تغيير المستودع المؤقت بواسطة الأمر: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (الخيار الثاني: باستخدام Anaconda) الخطوات مشابهة (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # إنشاء بيئة Anaconda
+conda activate gptac_venv                 # تنشيط بيئة Anaconda
+python -m pip install -r requirements.txt # هذه الخطوة مطابقة لخطوة تثبيت pip
+```
+
+
+<details><summary>إذا كنت بحاجة إلى دعم ChatGLM2 من الجامعة الصينية للاقتصاد وإدارة الأعمال وموس من جامعة فودان كخادم وجودة عالية لطرح الأسئلة، انقر هنا للعرض</summary>
+<p>
+
+【خطوات اختيارية】إذا كنت بحاجة إلى دعم جودة عالية لتشات جامعة تسينهوا (ChatGLM2) الصينية وجامعة فودان (MOSS)، يتعين عليك تثبيت تبعيات إضافية (شرط مسبق: التعامل مع Python واستخدام Pytorch وتوفر الحاسوب الشخصي بمواصفات قوية):
+```sh
+# 【خطوات اختيارية 1】دعم جودة عالية لتشات جامعة تسينهوا (ChatGLM2)
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# 【خطوات اختيارية 2】دعم جودة عالية لتشات جامعة فودان (MOSS)
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # عند تنفيذ هذا الأمر، يجب أن تكون في مسار المشروع الرئيسي
+
+# 【خطوات اختيارية 3】دعم RWKV Runner
+راجع الويكي: https://github.com/binary-husky/gpt_academic/wiki/دليل-تكوين-RWKV
+
+# 【خطوات اختيارية 4】تأكد من أن ملف التكوين config.py يحتوي على النماذج المرجوة، وهناك النماذج المدعومة حاليًا التالية (توجد خطط لتشغيل "jittorllms" في docker فقط):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+4. تشغيل البرنامج
+```sh
+python main.py
+```
+
+### طريقة التثبيت الثانية: استخدام Docker
+
+0. نصب القدرات الكاملة للمشروع (هذا هو الصورة الكبيرة التي تحتوي على CUDA و LaTeX. ولكن إذا كانت سرعة الإنترنت بطيئة أو القرص الصلب صغير، فإننا لا نوصي باستخدام هذا الخيار)
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+``` sh
+# قم بتعديل ملف docker-compose.yml للحفاظ على الخطة رقم 0 وحذف الخطط الأخرى. ثم أشغل:
+docker-compose up
+```
+
+1. تشغيل نموذج ChatGPT فقط + 文心一言 (Wenxin YIYan) + Spark عبر الإنترنت (يُوصى بهذا الخيار للمعظم)
+
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+``` sh
+# قم بتعديل ملف docker-compose.yml للحفاظ على الخطة رقم 1 وحذف الخطط الأخرى. ثم أشغل:
+docker-compose up
+```
+
+P.S. للاستفادة من إمكانية اللافتكس الإضافية، يرجى الرجوع إلى الويكي. بالإضافة إلى ذلك، يمكنك استخدام الخطة 4 أو الخطة 0 مباشرة للحصول على إمكانية اللافتكس.
+
+2. تشغيل نموذج ChatGPT + نموذج ChatGLM2 + نموذج MOSS + نموذج LLAMA2 + تون يي تشين ون (QiChaYiWen) (يتطلب معرفة بتشغيل نيفيديا دوكر (Nvidia Docker))
+
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+``` sh
+# قم بتعديل ملف docker-compose.yml للحفاظ على الخطة رقم 2 وحذف الخطط الأخرى. ثم أشغل:
+docker-compose up
+```
+
+### طريقة التثبيت الثالثة: طرائق نشر أخرى
+1. **نصوص بنقرة واحدة لأنظمة Windows**.
+يمكن لمستخدمي Windows الذين لا يعرفون بيئة Python تنزيل سكربت التشغيل بنقرة واحدة من [الإصدارات](https://github.com/binary-husky/gpt_academic/releases) المنشورة لتثبيت الإصدار الذي لا يحتوي على نماذج محلية.
+المساهمة في السكربت تعود لـ[oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. استخدام واجهة برمجة تطبيقات (API) مطراف ثالثة، Microsoft Azure، ونشوة النص، وغيرها، يرجى الرجوع إلى [صفحة الويكي](https://github.com/binary-husky/gpt_academic/wiki/إعدادات-التكوين-للمشروع) الخاصة بنا
+
+3. دليل تجنب المشاكل عند نشر المشروع في خوادم السحابة.
+يرجى زيارة صفحة [دليل نشر خوادم السحابة في المحيط](https://github.com/binary-husky/gpt_academic/wiki/دليل-نشر-خوادم-السحابة)
+
+4. طرائق نشر المشروع بأحدث الأساليب
+    - استخدام Sealos للنشر السريع [بنقرة واحدة](https://github.com/binary-husky/gpt_academic/issues/993).
+    - استخدم WSL2 (Windows Subsystem for Linux). يُرجى زيارة صفحة الويكي [لدليل التثبيت-2](https://github.com/binary-husky/gpt_academic/wiki/دليل-تشغيل-WSL2-(Windows-Subsystem-for-Linux)
+    - كيفية تشغيل البرنامج تحت عنوان فرعي (على سبيل المثال: `http://localhost/subpath`). يُرجى زيارة [إرشادات FastAPI](docs/WithFastapi.md)
+
+
+
+# الاستخدام المتقدم
+### I: إنشاء أزرار مخصصة (اختصارات أكاديمية)
+افتح أي محرر نصوص وافتح `core_functional.py` وأضف الإدخالات التالية ثم أعد تشغيل البرنامج. (إذا كانت الأزرار موجودة بالفعل، بإمكانك تعديل البادئة واللاحقة حراريًا دون الحاجة لإعادة تشغيل البرنامج)
+على سبيل المثال:
+```
+"ترجمة سوبر الإنجليزية إلى العربية": {
+    # البادئة، ستتم إضافتها قبل إدخالاتك. مثلاً، لوصف ما تريده مثل ترجمة أو شرح كود أو تلوين وهلم جرا
+    "بادئة": "يرجى ترجمة النص التالي إلى العربية ثم استخدم جدول Markdown لشرح المصطلحات المختصة المذكورة في النص:\n\n",
+
+    # اللاحقة، سيتم إضافتها بعد إدخالاتك. يمكن استخدامها لوضع علامات اقتباس حول إدخالك.
+    "لاحقة": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: إنشاء مكونات وظيفية مخصصة
+قم بكتابة مكونات وظيفية قوية لتنفيذ أي مهمة ترغب في الحصول عليها وحتى تلك التي لم تخطر لك على بال.
+إن إنشاء وتصحيح المكونات في هذا المشروع سهل للغاية، فما عليك سوى أن تمتلك بعض المعرفة الأساسية في لغة البرمجة بايثون وتستند على القالب الذي نقدمه.
+للمزيد من التفاصيل، يُرجى الاطلاع على [دليل المكونات الوظيفية](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97).
+
+
+# التحديثات
+### I: تحديثات
+
+1. ميزة حفظ الدردشة: يمكن حفظ الدردشة الحالية كملف HTML قابل للقراءة والاسترداد ببساطة عند استدعاء الوظيفة في منطقة المكونات `حفظ الدردشة الحالية` ، ويمكن استرجاع المحادثة السابقة ببساطة عند استدعاء الوظيفة في منطقة المكونات (القائمة المنسدلة) `تحميل سجل الدردشة` .
+نصيحة: يمكنك النقر المباشر على `تحميل سجل الدردشة` بدون تحديد ملف لعرض ذاكرة التخزين المؤقت لسجلات HTML.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ميزة ترجمة المقالات العلمية بواسطة Latex/Arxiv
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. محطة فراغ (فهم نغمة المستخدم من داخل اللغة الطبيعية واستدعاء وظائف أخرى تلقائيًا)
+
+- الخطوة 1: اكتب "بالرجاء استدعاء وظيفة ترجمة المقالة الأكاديمية من PDF وعنوان المقال هو https://openreview.net/pdf?id=rJl0r3R9KX".
+- الخطوة 2: انقر فوق "محطة الفراغ".
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. تصميم الوظائف المتعددة القادرة على توفير وظائف قوية بواجهات بسيطة
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. ترجمة وإلغاء ترجمة المشاريع الأخرى مفتوحة المصدر
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. ميزة تزيين [live2d](https://github.com/fghrsh/live2d_demo) (مغلقة بشكل افتراضي، يتطلب تعديل `config.py`)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. إنتاج الصور من OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. تحليل وإجماع الصوت من OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. إصلاح أخطاء اللغة الطبيعة في Latex
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. تغيير اللغة والموضوع
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II: الإصدارات:
+- الإصدار 3.70 (قريبًا): تحسينات لوظائف AutoGen وتصميم سلسلة من المكونات المشتقة
+- الإصدار 3.60: إدخال AutoGen كأساس لوظائف الجيل الجديد
+- الإصدار 3.57: دعم GLM3، نار النجوم v3، وشجرة الكلمات v4، وإصلاح خطأ الازدحام في النماذج المحلية
+- الإصدار 3.56: الدعم لإضافة مزامنة الأزرار الأساسية حسب الطلب، وصفحة تجميع تقارير البيانات في ملف PDF
+- الإصدار 3.55: إعادة هيكلة واجهة المستخدم الأمامية، وإضافة نافذة عائمة وشريط قائمة
+- الإصدار 3.54: إضافة مترجم الكود المباشر (Code Interpreter) (قيد الانجاز)
+- الإصدار 3.53: دعم اختيار موضوعات واجهة مختلفة، وزيادة الاستقرار وحل مشاكل التعارض بين المستخدمين المتعدد
+- الإصدار 3.50: استخدام اللغة الطبيعية لاستدعاء جميع وظائف المشروع هذا (محطة فراغ)، ودعم تصنيف الوظائف وتحسين واجهة المستخدم وتصميم مواضيع جديدة
+- الإصدار 3.49: دعم المنصات البحثية في بيدو كونفان وشجرة الكلمات
+- الإصدار 3.48: دعم علي بابا, بوكما رش حتكيا, إكسونامبلومانت النار
+- الإصدار 3.46: دعم محادثة نصية في الوقت الحقيقي غير مراقبة
+- الإصدار 3.45: دعم تخصيص LatexChatglm النموذج التعديل
+- الإصدار 3.44: دعم Azure رسميًا، وتحسين سهولة الاستخدام للواجهات الأمامية
+- الإصدار 3.4: +ترجمة النصوص الكاملة للمقالات من خلال ملف PDF، +اختيار موضع المنطقة النصية، +خيار التخطيط الرأسي، +تحسينات في وظائف التداخل العديدة
+- الإصدار 3.3: +وظائف متكاملة للمعلومات عبر الإنترنت
+- الإصدار 3.2: دعم وظائف المكونات التي تحتوي معلمات أكثر (حفظ النص، فهم أي لغة برمجة، طلب أي تركيبة LLM في وقت واحد)
+- الإصدار 3.1: دعم السؤال نحو نماذج GPT المتعددة! دعم واجهة api2d، دعم توازن الأحمال بين المفاتيح الخاصة المتعددة
+- الإصدار 3.0: دعم لنماذج جات، واحدة منها لشتلس الصغيرة
+- الإصدار 2.6: إعادة تصميم بنية الوظائف، وتحسين التفاعل وإضافة مزيد من الوظائف
+- الإصدار 2.5: التحديث التلقائي، وحل مشكلة النص الطويل عند ملخص المشاريع الضخمة وتجاوز النصوص.
+- الإصدار 2.4: (١) إضافة ميزة ترجمة المقالات الدورية. (٢) إضافة ميزة لتحويل مكان منطقة الإدخال. (٣) إضافة خيار التخطيط العمودي (vertical layout). (٤) تحسين وظائف المكونات متعددة الخيوط.
+- الإصدار 2.3: تحسين التفاعل مع مواضيع متعددة
+- الإصدار 2.2: دعم إعادة تحميل الوظائف المكونة حراريًا
+- الإصدار 2.1: تصميم قابل للطي
+- الإصدار 2.0: إدخال وحدات الوظائف المكونة
+- الإصدار 1.0: الوظائف الأساسية
+
+مجموعة المطورين GPT Academic QQ: `610599535`
+
+- مشكلات معروفة
+    - بعض ملحقات متصفح الترجمة تتداخل مع تشغيل الواجهة الأمامية لهذا البرنامج
+    - يحتوي Gradio الرسمي حاليًا على عدد كبير من مشاكل التوافق. يُرجى استخدام `requirement.txt` لتثبيت Gradio.
+
+### III: الأنساق
+يمكن تغيير الأنساق بتعديل خيار `THEME` (config.py)
+1. `Chuanhu-Small-and-Beautiful` [الرابط](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV: فروع تطوير هذا المشروع
+
+1. الفرع `master`: الفرع الرئيسي، إصدار مستقر
+2. الفرع `frontier`: الفرع التطويري، إصدار تجريبي
+
+
+### V: المراجع والفروض التعليمية
+
+```
+استخدمت العديد من التصاميم الموجودة في مشاريع ممتازة أخرى في الأكواد التالية، للمراجع عشوائية:
+
+# ViewGradio:
+https://github.com/THUD
+
+
+
+# مُثبّت بضغطة واحدة Oobabooga:
+https://github.com/oobabooga/one-click-installers
+
+# المزيد:
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.English.md

@@ -0,0 +1,357 @@
+
+
+
+> **Note**
+>
+> This README was translated by GPT (implemented by the plugin of this project) and may not be 100% reliable. Please carefully check the translation results.
+>
+> 2023.11.7: When installing dependencies, please select the **specified versions** in the `requirements.txt` file. Installation command: `pip install -r requirements.txt`.
+
+
+# <div align=center><img src="logo.png" width="40"> GPT Academic Optimization</div>
+
+**If you like this project, please give it a Star.**
+To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
+
+> **Note**
+>
+> 1.Please note that only plugins (buttons) highlighted in **bold** support reading files, and some plugins are located in the **dropdown menu** in the plugin area. Additionally, we welcome and process any new plugins with the **highest priority** through PRs.
+>
+> 2.The functionalities of each file in this project are described in detail in the [self-analysis report `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告). As the version iterates, you can also click on the relevant function plugin at any time to call GPT to regenerate the project's self-analysis report. Common questions are in the [`wiki`](https://github.com/binary-husky/gpt_academic/wiki). [Regular installation method](#installation) | [One-click installation script](https://github.com/binary-husky/gpt_academic/releases) | [Configuration instructions](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+>
+> 3.This project is compatible with and encourages the use of domestic large-scale language models such as ChatGLM. Multiple api-keys can be used together. You can fill in the configuration file with `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"` to temporarily switch `API_KEY` during input, enter the temporary `API_KEY`, and then press enter to apply it.
+
+
+
+
+<div align="center">
+
+Feature (⭐ = Recently Added) | Description
+--- | ---
+⭐[Integrate New Models](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B) | Baidu [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu) and Wenxin Yiyu, [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), Shanghai AI-Lab [Shusheng](https://github.com/InternLM/InternLM), Xunfei [Xinghuo](https://xinghuo.xfyun.cn/), [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Zhifu API, DALLE3
+Proofreading, Translation, Code Explanation | One-click proofreading, translation, searching for grammar errors in papers, explaining code
+[Custom Shortcuts](https://www.bilibili.com/video/BV14s4y1E7jN) | Support for custom shortcuts
+Modular Design | Support for powerful [plugins](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions), plugins support [hot updates](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[Program Profiling](https://www.bilibili.com/video/BV1cj411A7VW) | [Plugin] One-click to profile Python/C/C++/Java/Lua/... project trees or [self-profiling](https://www.bilibili.com/video/BV1cj411A7VW)
+Read Papers, [Translate](https://www.bilibili.com/video/BV1KT411x7Wn) Papers | [Plugin] One-click to interpret full-text latex/pdf papers and generate abstracts
+Full-text Latex [Translation](https://www.bilibili.com/video/BV1nk4y1Y7Js/), [Proofreading](https://www.bilibili.com/video/BV1FT411H7c5/) | [Plugin] One-click translation or proofreading of latex papers
+Batch Comment Generation | [Plugin] One-click batch generation of function comments
+Markdown [Translation](https://www.bilibili.com/video/BV1yo4y157jV/) | [Plugin] Did you see the [README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md) in the top five languages?
+Chat Analysis Report Generation | [Plugin] Automatically generates summary reports after running
+[PDF Paper Full-text Translation](https://www.bilibili.com/video/BV1KT411x7Wn) | [Plugin] Extract title & abstract of PDF papers + translate full-text (multi-threaded)
+[Arxiv Helper](https://www.bilibili.com/video/BV1LM4y1279X) | [Plugin] Enter the arxiv article URL to translate the abstract + download PDF with one click
+One-click Proofreading of Latex Papers | [Plugin] Syntax and spelling correction of Latex papers similar to Grammarly + output side-by-side PDF
+[Google Scholar Integration Helper](https://www.bilibili.com/video/BV19L411U7ia) | [Plugin] Given any Google Scholar search page URL, let GPT help you [write related works](https://www.bilibili.com/video/BV1GP411U7Az/)
+Internet Information Aggregation + GPT | [Plugin] One-click to let GPT retrieve information from the Internet to answer questions and keep the information up to date
+⭐Arxiv Paper Fine Translation ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [Plugin] One-click [high-quality translation of arxiv papers](https://www.bilibili.com/video/BV1dz4y1v77A/), the best paper translation tool at present
+⭐[Real-time Speech Input](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [Plugin] Asynchronously [listen to audio](https://www.bilibili.com/video/BV1AV4y187Uy/), automatically segment sentences, and automatically find the best time to answer
+Formula/Image/Table Display | Can simultaneously display formulas in [TeX form and rendered form](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png), support formula and code highlighting
+⭐AutoGen Multi-Agent Plugin | [Plugin] Explore the emergence of multi-agent intelligence with Microsoft AutoGen!
+Start Dark [Theme](https://github.com/binary-husky/gpt_academic/issues/173) | Add ```/?__theme=dark``` to the end of the browser URL to switch to the dark theme
+[More LLM Model Support](https://www.bilibili.com/video/BV1wT411p7yf) | It must be great to be served by GPT3.5, GPT4, [THU ChatGLM2](https://github.com/THUDM/ChatGLM2-6B), and [Fudan MOSS](https://github.com/OpenLMLab/MOSS) at the same time, right?
+⭐ChatGLM2 Fine-tuning Model | Support for loading ChatGLM2 fine-tuning models and providing ChatGLM2 fine-tuning assistant plugins
+More LLM Model Access, support for [huggingface deployment](https://huggingface.co/spaces/qingxu98/gpt-academic) | Join NewBing interface (New Bing), introduce Tsinghua [JittorLLMs](https://github.com/Jittor/JittorLLMs) to support [LLaMA](https://github.com/facebookresearch/llama) and [Pangu](https://openi.org.cn/pangu/)
+⭐[void-terminal](https://github.com/binary-husky/void-terminal) pip package | Use this project's all function plugins directly in Python without GUI (under development)
+⭐Void Terminal Plugin | [Plugin] Schedule other plugins of this project directly in natural language
+More New Feature Demonstrations (Image Generation, etc.)...... | See the end of this document ........
+</div>
+
+
+- New interface (modify the LAYOUT option in `config.py` to switch between "left-right layout" and "top-bottom layout")
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- All buttons are dynamically generated by reading `functional.py` and can be added with custom functions to free up the clipboard
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- Proofreading/Correction
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- If the output contains formulas, they will be displayed in both tex format and rendered format for easy copying and reading.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- Too lazy to look at the project code? Show off the whole project directly in chatgpt's mouth
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- Multiple large language models mixed calling (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Installation
+### Installation Method I: Run directly (Windows, Linux or MacOS)
+
+1. Download the project
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. Configure API_KEY
+
+In `config.py`, configure API KEY and other settings, [click here to see special network environment configuration methods](https://github.com/binary-husky/gpt_academic/issues/1). [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。
+
+「 The program will first check if a secret configuration file named `config_private.py` exists and use the configurations from that file to override the ones in `config.py` with the same names. If you understand this logic, we strongly recommend that you create a new configuration file named `config_private.py` next to `config.py` and move (copy) the configurations from `config.py` to `config_private.py` (only copy the configuration items you have modified). 」
+
+「 Project configuration can be done via `environment variables`. The format of the environment variables can be found in the `docker-compose.yml` file or our [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明). Configuration priority: `environment variables` > `config_private.py` > `config.py`. 」
+
+
+3. Install dependencies
+```sh
+# (Option I: If you are familiar with python, python>=3.9) Note: Use the official pip source or the Aliyun pip source. Temporary method for switching the source: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (Option II: Using Anaconda) The steps are similar (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # Create the anaconda environment
+conda activate gptac_venv                 # Activate the anaconda environment
+python -m pip install -r requirements.txt # This step is the same as the pip installation process
+```
+
+
+<details><summary>If you need to support THU ChatGLM2, Fudan MOSS, or RWKV Runner as backends, click here to expand</summary>
+<p>
+
+【Optional Step】If you need to support THU ChatGLM2 or Fudan MOSS as backends, you need to install additional dependencies (Prerequisites: Familiar with Python + Familiar with Pytorch + Sufficient computer configuration):
+```sh
+# 【Optional Step I】Support THU ChatGLM2. Note: If you encounter the "Call ChatGLM fail unable to load ChatGLM parameters" error, refer to the following: 1. The default installation above is for torch+cpu version. To use cuda, uninstall torch and reinstall torch+cuda; 2. If the model cannot be loaded due to insufficient local configuration, you can modify the model accuracy in request_llm/bridge_chatglm.py. Change AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) to AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# 【Optional Step II】Support Fudan MOSS
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # When executing this line of code, make sure you are in the root directory of the project
+
+# 【Optional Step III】Support RWKV Runner
+Refer to wiki: https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
+
+# 【Optional Step IV】Make sure that the AVAIL_LLM_MODELS in the config.py configuration file includes the expected models. The currently supported models are as follows (jittorllms series currently only supports the docker solution):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+
+4. Run
+```sh
+python main.py
+```
+
+### Installation Method II: Use Docker
+
+0. Deploy all capabilities of the project (this is a large image that includes cuda and latex. Not recommended if you have slow internet speed or small hard drive)
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+``` sh
+# Modify docker-compose.yml, keep scheme 0 and delete other schemes. Then run:
+docker-compose up
+```
+
+1. ChatGPT + Wenxin + Spark online models only (recommended for most people)
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+``` sh
+# Modify docker-compose.yml, keep scheme 1 and delete other schemes. Then run:
+docker-compose up
+```
+
+P.S. If you need the latex plugin functionality, please see the Wiki. Also, you can directly use scheme 4 or scheme 0 to get the Latex functionality.
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + Intelligent Questions (requires familiarity with [Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian) runtime)
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+``` sh
+# Modify docker-compose.yml, keep scheme 2 and delete other schemes. Then run:
+docker-compose up
+```
+
+
+### Installation Method III: Other deployment methods
+1. **Windows one-click running script**.
+Windows users who are completely unfamiliar with the python environment can download the one-click running script from the [Release](https://github.com/binary-husky/gpt_academic/releases) to install the version without local models.
+The script is contributed by [oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. Use third-party APIs, Azure, Wenxin, Xinghuo, etc., see [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)
+
+3. Pitfall guide for deploying on cloud servers.
+Please visit [Cloud Server Remote Deployment Wiki](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
+
+4. Some new deployment platforms or methods
+    - Use Sealos [to deploy with one click](https://github.com/binary-husky/gpt_academic/issues/993).
+    - Use WSL2 (Windows Subsystem for Linux). Please refer to [Deployment Wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
+    - How to run under a subpath (such as `http://localhost/subpath`). Please visit [FastAPI Run Instructions](docs/WithFastapi.md)
+
+
+
+# Advanced Usage
+### I: Customizing new convenient buttons (academic shortcuts)
+Open `core_functional.py` with any text editor, add the following entry, and then restart the program. (If the button already exists, both the prefix and suffix can be modified on-the-fly without restarting the program.)
+For example:
+```
+"Super Translation": {
+    # Prefix: will be added before your input. For example, used to describe your request, such as translation, code explanation, proofreading, etc.
+    "Prefix": "Please translate the following paragraph into Chinese and then explain each proprietary term in the text using a markdown table:\n\n",
+
+    # Suffix: will be added after your input. For example, used to wrap your input in quotation marks along with the prefix.
+    "Suffix": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: Custom function plugins
+Write powerful function plugins to perform any task you desire and can't imagine.
+The difficulty of writing and debugging plugins in this project is very low. As long as you have a certain knowledge of Python, you can implement your own plugin functionality by following the template we provide.
+For more details, please refer to the [Function Plugin Guide](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97).
+
+# Updates
+### I: Dynamics
+
+1. Conversation-saving feature. Call `Save the current conversation` in the function plugin area to save the current conversation as a readable and restorable HTML file. Additionally, call `Load conversation history archive` in the function plugin area (drop-down menu) to restore previous sessions.
+Tip: Clicking `Load conversation history archive` without specifying a file allows you to view the cached historical HTML archive.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐Latex/Arxiv paper translation feature⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. Void Terminal (understanding user intent from natural language input and automatically calling other plugins)
+
+- Step 1: Enter " Please call the plugin to translate the PDF paper, the address is https://openreview.net/pdf?id=rJl0r3R9KX"
+- Step 2: Click "Void Terminal"
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. Modular function design, simple interface supporting powerful functionality
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. Translate and interpret other open-source projects
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. Added small features that decorate [live2d](https://github.com/fghrsh/live2d_demo) (disabled by default, needs modification in `config.py`)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. OpenAI image generation
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. OpenAI audio parsing and summarization
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Latex full-text proofreading and correction
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. Language and theme switching
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II: Versions:
+- version 3.70 (todo): Optimize the AutoGen plugin theme and design a series of derivative plugins
+- version 3.60: Introduce AutoGen as the cornerstone of the new generation of plugins
+- version 3.57: Support GLM3, Spark v3, Wenxin Quote v4, and fix concurrency bugs in local models
+- version 3.56: Support dynamically adding basic functional buttons and a new summary PDF page
+- version 3.55: Refactor the frontend interface and introduce floating windows and a menu bar
+- version 3.54: Add a dynamic code interpreter (Code Interpreter) (to be improved)
+- version 3.53: Support dynamically choosing different interface themes, improve stability, and resolve conflicts between multiple users
+- version 3.50: Use natural language to call all function plugins of this project (Void Terminal), support plugin classification, improve UI, and design new themes
+- version 3.49: Support Baidu Qianfan Platform and Wenxin Quote
+- version 3.48: Support Ali Dharma Academy Tongyi Qianwen, Shanghai AI-Lab Shusheng, and Xunfei Spark
+- version 3.46: Support fully hands-off real-time voice conversation
+- version 3.45: Support customizing ChatGLM2 fine-tuned models
+- version 3.44: Officially support Azure, optimize interface usability
+- version 3.4: + Arxiv paper translation, latex paper correction functionality
+- version 3.3: + Internet information integration functionality
+- version 3.2: Function plugins support more parameter interfaces (conversation saving functionality, interpreting any code language + asking any combination of LLMs simultaneously)
+- version 3.1: Support querying multiple GPT models simultaneously! Support API2D, support load balancing for multiple API keys
+- version 3.0: Support chatglm and other small-scale LLMs
+- version 2.6: Refactored plugin structure, improved interactivity, added more plugins
+- version 2.5: Self-updating, fix the problem of text being too long and token overflowing when summarizing large code projects
+- version 2.4: (1) Add PDF full-text translation functionality; (2) Add functionality to switch the position of the input area; (3) Add vertical layout option; (4) Optimize multi-threaded function plugins.
+- version 2.3: Enhance multi-threaded interactivity
+- version 2.2: Function plugin hot-reloading support
+- version 2.1: Collapsible layout
+- version 2.0: Introduce modular function plugins
+- version 1.0: Basic functionality
+
+GPT Academic Developer QQ Group: `610599535`
+
+- Known Issues
+    - Some browser translation plugins interfere with the frontend operation of this software
+    - Official Gradio currently has many compatibility bugs, please make sure to install Gradio using `requirement.txt`
+
+### III: Themes
+You can change the theme by modifying the `THEME` option (config.py).
+1. `Chuanhu-Small-and-Beautiful` [Website](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+### IV: Development Branches of This Project
+
+1. `master` branch: Main branch, stable version
+2. `frontier` branch: Development branch, test version
+
+***
+
+### V: References and Learning
+
+
+The code references the designs of many other excellent projects, in no particular order:
+
+[THU ChatGLM2-6B](https://github.com/THUDM/ChatGLM2-6B)
+
+
+[THU JittorLLMs](https://github.com/Jittor/JittorLLMs)
+
+
+[ChatPaper](https://github.com/kaixindelele/ChatPaper)
+
+
+[Edge-GPT](https://github.com/acheong08/EdgeGPT)
+
+
+[ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT)
+
+
+
+# Oobabooga one-click installer:
+https://github.com/oobabooga/one-click-installers
+
+# More:
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.French.md

@@ -0,0 +1,356 @@
+
+
+
+> **Remarque**
+>
+> Ce README a été traduit par GPT (implémenté par le plugin de ce projet) et n'est pas fiable à 100 %. Veuillez examiner attentivement les résultats de la traduction.
+>
+> 7 novembre 2023 : Lors de l'installation des dépendances, veuillez choisir les versions **spécifiées** dans le fichier `requirements.txt`. Commande d'installation : `pip install -r requirements.txt`.
+
+
+# <div align=center><img src="logo.png" width="40"> Optimisation académique GPT (GPT Academic)</div>
+
+**Si vous aimez ce projet, merci de lui donner une étoile ; si vous avez inventé des raccourcis ou des plugins utiles, n'hésitez pas à envoyer des demandes d'extraction !**
+
+Si vous aimez ce projet, veuillez lui donner une étoile.
+Pour traduire ce projet dans une langue arbitraire avec GPT, lisez et exécutez [`multi_language.py`](multi_language.py) (expérimental).
+
+> **Remarque**
+>
+> 1. Veuillez noter que seuls les plugins (boutons) marqués en **surbrillance** prennent en charge la lecture de fichiers, et certains plugins se trouvent dans le **menu déroulant** de la zone des plugins. De plus, nous accueillons avec la plus haute priorité les nouvelles demandes d'extraction de plugins.
+>
+> 2. Les fonctionnalités de chaque fichier de ce projet sont spécifiées en détail dans [le rapport d'auto-analyse `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic个项目自译解报告). Vous pouvez également cliquer à tout moment sur les plugins de fonctions correspondants pour appeler GPT et générer un rapport d'auto-analyse du projet. Questions fréquemment posées [wiki](https://github.com/binary-husky/gpt_academic/wiki). [Méthode d'installation standard](#installation) | [Script d'installation en un clic](https://github.com/binary-husky/gpt_academic/releases) | [Instructions de configuration](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)..
+>
+> 3. Ce projet est compatible avec et recommande l'expérimentation de grands modèles de langage chinois tels que ChatGLM, etc. Prend en charge plusieurs clés API, vous pouvez les remplir dans le fichier de configuration comme `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`. Pour changer temporairement la clé API, entrez la clé API temporaire dans la zone de saisie, puis appuyez sur Entrée pour soumettre et activer celle-ci.
+
+
+<div align="center">
+
+Fonctionnalités (⭐ = fonctionnalité récemment ajoutée) | Description
+--- | ---
+⭐[Modèles acquis](https://github.com/binary-husky/gpt_academic/wiki/如何切换模型)！ | Baidu [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu) et Wenxin Yiyuan, [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), Shanghai AI-Lab [Shusheng](https://github.com/InternLM/InternLM), Xunfei [Xinghuo](https://xinghuo.xfyun.cn/), [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Zhifu API, DALLE3
+Amélioration, traduction, explication du code | Correction, traduction, recherche d'erreurs de syntaxe dans les articles, explication du code
+[Raccourcis personnalisés](https://www.bilibili.com/video/BV14s4y1E7jN) | Prise en charge de raccourcis personnalisés
+Conception modulaire | Prise en charge de plugins puissants personnalisables, prise en charge de la [mise à jour à chaud](https://github.com/binary-husky/gpt_academic/wiki/函数插件指南) des plugins
+[Analyse de programme](https://www.bilibili.com/video/BV1cj411A7VW) | [Plugin] Analyse en profondeur d'un arbre de projets Python/C/C++/Java/Lua/... d'un simple clic ou [auto-analyse](https://www.bilibili.com/video/BV1cj411A7VW)
+Lecture d'articles, traduction d'articles | [Plugin] Lecture automatique des articles LaTeX/PDF et génération du résumé
+Traduction complète de [LaTeX](https://www.bilibili.com/video/BV1nk4y1Y7Js/) ou amélioration de leur qualité | [Plugin] Traduction ou amélioration rapide des articles LaTeX
+Génération de commentaires en masse | [Plugin] Génération facile de commentaires de fonctions
+Traduction [chinois-anglais](https://www.bilibili.com/video/BV1yo4y157jV/) du Markdown | [Plugin] Avez-vous vu le [README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md) dans les cinq langues ci-dessus ?
+Génération de rapports d'analyse du chat | [Plugin] Génération automatique d'un rapport récapitulatif après l'exécution du chat
+[Fonction de traduction complète des articles PDF](https://www.bilibili.com/video/BV1KT411x7Wn) | [Plugin] Extraction du titre et du résumé d'un article PDF, ainsi que traduction intégrale (multithreading)
+Assistant Arxiv | [Plugin] Saisissez l'URL d'un article Arxiv pour traduire automatiquement le résumé et télécharger le PDF
+Correction automatique d'articles LaTeX | [Plugin] Correction de la grammaire, de l'orthographe et comparaison avec le PDF correspondant, à la manière de Grammarly
+Assistant Google Scholar | [Plugin] Donner l'URL d'une page de recherche Google Scholar pour obtenir de l'aide sur l'écriture des références
+Agrégation d'informations sur Internet + GPT | [Plugin] Obtenez les informations de l'Internet pour répondre aux questions à l'aide de GPT, afin que les informations ne soient jamais obsolètes
+⭐Traduction détaillée des articles Arxiv ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [Plugin] Traduction de haute qualité d'articles Arxiv en un clic, le meilleur outil de traduction d'articles à ce jour
+⭐[Saisie orale en temps réel](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [Plugin] Écoute asynchrone de l'audio, découpage automatique et recherche automatique du meilleur moment pour répondre
+Affichage des formules, images, tableaux | Affichage simultané de la forme [TeX et rendue](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png) des formules, prise en charge de la mise en évidence des formules et du code
+⭐Plugin AutoGen multi-agents | [Plugin] Explorez les émergences intelligentes à plusieurs agents avec Microsoft AutoGen !
+Activation du [thème sombre](https://github.com/binary-husky/gpt_academic/issues/173) | Ajouter ```/?__theme=dark``` à l'URL du navigateur pour basculer vers le thème sombre
+Prise en charge de plusieurs modèles LLM | Expérimentez avec GPT 3.5, GPT4, [ChatGLM2 de Tsinghua](https://github.com/THUDM/ChatGLM2-6B), [MOSS de Fudan](https://github.com/OpenLMLab/MOSS) simultanément !
+⭐Modèle ChatGLM2 fine-tuned | Chargez et utilisez un modèle fine-tuned de ChatGLM2, disponible avec un plugin d'assistance
+Prise en charge de plus de modèles LLM, déploiement sur [Huggingface](https://huggingface.co/spaces/qingxu98/gpt-academic) | Ajout de l'interface de connaissance-API, support de [LLaMA](https://github.com/facebookresearch/llama) et [PanGuα](https://openi.org.cn/pangu/)
+⭐Paquet pip [void-terminal](https://github.com/binary-husky/void-terminal) | Accédez à toutes les fonctions et plugins de ce projet directement depuis Python (en cours de développement)
+⭐Plugin terminal du vide | [Plugin] Utilisez un langage naturel pour interagir avec les autres plugins du projet
+Affichage de nouvelles fonctionnalités (génération d'images, etc.) …… | Voir à la fin de ce document ……
+</div>
+
+
+- Nouvelle interface (modifiez l'option LAYOUT dans `config.py` pour basculer entre la disposition "gauche-droite" et "haut-bas")
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- Tous les boutons sont générés dynamiquement en lisant `functional.py`, vous pouvez donc ajouter de nouvelles fonctionnalités personnalisées et libérer le presse-papiers.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- Retouche/correction
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- If the output contains formulas, they will be displayed in both tex and rendered forms for easy copying and reading.
+
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- Don't feel like looking at the project code? Just give it to ChatGPT to show off.
+
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- Multiple large language models are mixed and used together (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4).
+
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Installation
+### Method I: Run directly (Windows, Linux, or MacOS)
+
+1. Download the project
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. Configure API_KEY
+
+In `config.py`, configure the API KEY and other settings. [Click here to see methods for special network environment configurations](https://github.com/binary-husky/gpt_academic/issues/1). [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+
+「 The program will first check if there is a confidential configuration file named `config_private.py`, and use the configurations in that file to override the corresponding configurations in `config.py`. If you understand this logic, we strongly recommend creating a new configuration file named `config_private.py` right next to `config.py`, and move (copy) the configurations from `config.py` to `config_private.py` (only copy the configurations that you have modified). 」
+
+「 You can also configure the project using `environment variables`. The format of the environment variables can be found in the `docker-compose.yml` file or on our [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明). The priority of configuration reading is: `environment variables` > `config_private.py` > `config.py`. 」
+
+3. Install dependencies
+```sh
+# (Option I: If you are familiar with Python, python>=3.9) Note: Use the official pip source or the Ali pip source. Temporary change of source method: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (Option II: Use Anaconda) The steps are similar (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # Create an anaconda environment
+conda activate gptac_venv                 # Activate the anaconda environment
+python -m pip install -r requirements.txt # This step is the same as the pip installation step
+```
+
+
+<details><summary>If you need to support Tsinghua ChatGLM2/Fudan MOSS/RWKV as backends, click here to expand</summary>
+<p>
+
+[Optional Steps] If you need to support Tsinghua ChatGLM2/Fudan MOSS as backends, you need to install additional dependencies (Prerequisites: Familiar with Python + Have used PyTorch + Sufficient computer configuration):
+```sh
+# [Optional Step I] Support Tsinghua ChatGLM2. Comment on this note: If you encounter the error "Call ChatGLM generated an error and cannot load the parameters of ChatGLM", refer to the following: 1: The default installation is the torch+cpu version. To use cuda, you need to uninstall torch and reinstall torch+cuda; 2: If the model cannot be loaded due to insufficient computer configuration, you can modify the model precision in request_llm/bridge_chatglm.py. Change AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) to AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True).
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# [Optional Step II] Support Fudan MOSS
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # Note: You need to be at the root directory of the project when executing this line of code
+
+# [Optional Step III] Support RWKV Runner
+Refer to the wiki: https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
+
+# [Optional Step IV] Make sure that the AVAIL_LLM_MODELS in the config.py configuration file contains the expected models. The currently supported models are as follows (jittorllms series currently only support the docker solution):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+4. Run
+```sh
+python main.py
+```
+
+### Method II: Use Docker
+
+0. Deploy all capabilities of the project (this is a large image that includes cuda and latex. But if you have a slow internet speed or a small hard drive, it is not recommended to use this)
+
+``` sh
+# Modify the docker-compose.yml file, keep scheme 0 and delete the other schemes. Then run:
+docker-compose up
+```
+
+1. ChatGPT + Wenxin Yiyu + Spark and other online models (recommended for most people)
+
+``` sh
+# Modify the docker-compose.yml file, keep scheme 1 and delete the other schemes. Then run:
+docker-compose up
+```
+
+NOTE: If you need Latex plugin functionality, please refer to the Wiki. Additionally, you can also use scheme 4 or scheme 0 directly to obtain Latex functionality.
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + Tongyi Qianwen (requires familiarity with [Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian) runtime)
+
+``` sh
+# Modify the docker-compose.yml file, keep scheme 2 and delete the other schemes. Then run:
+docker-compose up
+```
+
+
+### Method III: Other deployment methods
+1. **One-click run script for Windows**.
+Windows users who are completely unfamiliar with the Python environment can download the one-click run script without local models from the [Release](https://github.com/binary-husky/gpt_academic/releases) section.
+The script was contributed by [oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. Use third-party APIs, Azure, Wenxin Yiyu, Xinghuo, etc., see the [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+
+3. Pitfall guide for deploying on cloud servers.
+Please visit the [cloud server remote deployment wiki](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97).
+
+4. Some new deployment platforms or methods
+    - Use Sealos [one-click deployment](https://github.com/binary-husky/gpt_academic/issues/993).
+    - Use WSL2 (Windows Subsystem for Linux). Please visit the [deployment wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
+    - How to run under a subpath (such as `http://localhost/subpath`). Please see [FastAPI running instructions](docs/WithFastapi.md)
+
+
+
+# Utilisation avancée
+### I: Personnalisation des nouveaux boutons d'accès rapide (raccourcis académiques)
+Ouvrez `core_functional.py` avec n'importe quel éditeur de texte, ajoutez les entrées suivantes, puis redémarrez le programme. (Si le bouton existe déjà, le préfixe et le suffixe peuvent être modifiés à chaud sans redémarrer le programme).
+Par exemple:
+```
+"Traduction avancée de l'anglais vers le français": {
+    # Préfixe, ajouté avant votre saisie. Par exemple, utilisez-le pour décrire votre demande, telle que la traduction, l'explication du code, l'amélioration, etc.
+    "Prefix": "Veuillez traduire le contenu suivant en français, puis expliquer chaque terme propre à la langue anglaise utilisé dans le texte à l'aide d'un tableau markdown : \n\n",
+
+    # Suffixe, ajouté après votre saisie. Par exemple, en utilisant le préfixe, vous pouvez entourer votre contenu par des guillemets.
+    "Suffix": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: Personnalisation des plugins de fonction
+Écrivez de puissants plugins de fonction pour accomplir toutes les tâches que vous souhaitez ou ne pouvez pas imaginer.
+Le développement et le débogage de ces plugins dans ce projet sont très faciles. Tant que vous avez des connaissances de base en python, vous pouvez implémenter vos propres fonctionnalités grâce à notre modèle fourni.
+Veuillez consulter le [Guide des plugins de fonction](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97) pour plus de détails.
+
+
+# Mises à jour
+### I: Dynamique
+
+1. Fonction de sauvegarde de conversation. Appelez `Enregistrer la conversation en cours` dans la zone des plugins fonctionnels pour enregistrer la conversation en cours sous la forme d'un fichier HTML lisible et récupérable. En outre, appelez `Charger les archives de conversation` dans la zone des plugins fonctionnels (menu déroulant) pour restaurer les conversations précédentes.
+Astuce: Si aucun fichier n'est spécifié, cliquez directement sur `Charger les archives de conversation` pour afficher le cache des archives HTML.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐ Fonction de traduction des articles Latex/Arxiv ⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. Terminal du néant (comprendre l'intention de l'utilisateur à partir de la saisie en langage naturel et appeler automatiquement d'autres plugins)
+
+- Étape 1: Saisissez "Veuillez appeler le plugin de traduction pour le document PDF, l'URL est https://openreview.net/pdf?id=rJl0r3R9KX".
+- Étape 2 : Cliquez sur "Terminal du néant".
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. Conception de fonctionnalités modulaires, une interface simple peut prendre en charge des fonctionnalités puissantes
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. Traduction et interprétation d'autres projets open-source
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. Fonctionnalités supplémentaires intégrant [live2d](https://github.com/fghrsh/live2d_demo) (désactivé par défaut, nécessite des modifications dans `config.py`)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. Génération d'images par OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. Analyse et résumé audio par OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Vérification et correction orthographique complète du document en Latex
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. Changement de langue et de thème
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II: Versions:
+- version 3.70(tâche à accomplir) : Optimisation de la fonction AutoGen et création d'une série de plugins dérivés
+- version 3.60 : Introduction d'AutoGen comme base des nouveaux plugins
+- version 3.57 : Prise en charge de GLM3, Starlight v3, Zen v4 et correction de l'incompatibilité des modèles locaux
+- version 3.56 : Possibilité d'ajouter dynamiquement des boutons de fonction de base et nouvelle page de synthèse des PDF
+- version 3.55: Refonte de l'interface utilisateur avec fenêtres flottantes et barre de menu
+- version 3.54 : Nouvel interpréteur de code dynamique (Code Interpreter) (à améliorer)
+- version 3.53 : Possibilité de choisir dynamiquement différents thèmes d'interface, amélioration de la stabilité et résolution des problèmes de conflit entre utilisateurs multiples
+- version 3.50 : Utiliser le langage naturel pour appeler toutes les fonctions du projet (Terminal du néant), prise en charge de la classification des plugins, amélioration de l'interface utilisateur, conception de nouveaux thèmes
+- version 3.49 : Prise en charge de Baidu Qianfan et Xiaomi-Wenyiyan
+- version 3.48 : Prise en charge d'Ali-DA, Shanghai AI-Lab-Shusheng et Xunfei Xinghuo
+- version 3.46 : Prise en charge de la conversation audio temps réel sans intervention
+- version 3.45 : Prise en charge de la personnalisation du modèle ChatGLM2
+- version 3.44 : Prise en charge officielle d'Azure, amélioration de l'utilisabilité de l'interface
+- version 3.4 : +traduction complète des articles Arxiv, +correction des articles Latex
+- version 3.3 : +fonction d'intégration d'informations Internet
+- version 3.2 : Les plugins de fonction prennent en charge plus de paramètres (fonction d'enregistrement de conversation, débogage de code de n'importe quel langage + demandes d'LLM arbitraires)
+- version 3.1 : Prise en charge de l'interrogation simultanée de plusieurs modèles gpt ! Prise en charge de l'API2D, répartition de charge entre plusieurs clés API
+- version 3.0 : Prise en charge de chatglm et d'autres petits llm
+- version 2.6 : Refonte de la structure des plugins, amélioration de l'interactivité, ajout de nouveaux plugins
+- version 2.5 : Auto-mise à jour, résolution des problèmes de dépassement de longueur de texte et de jeton pendant la consolidation de grands projets de codes sources
+- version 2.4 : (1) Nouvelle fonctionnalité de traduction complète des documents PDF ; (2) Nouvelle fonctionnalité de changement de position de la zone de saisie ; (3) Nouvelle option de disposition verticale ; (4) Optimisation des plugins de fonction multithreads.
+- version 2.3 : Amélioration de l'interactivité multi-threads
+- version 2.2 : Prise en charge du rechargement à chaud des plugins de fonction
+- version 2.1 : Mise en page pliable
+- version 2.0 : Introduction de plugins de fonction modulaires
+- version 1.0: Fonctionnalités de base
+
+Groupe QQ des développeurs de GPT Academic: `610599535`
+
+- Problèmes connus
+    - Certains plugins de traduction de navigateurs peuvent nuire au fonctionnement de l'interface utilisateur de ce logiciel.
+    - Gradio officiel a actuellement de nombreux bugs de compatibilité. Veuillez utiliser `requirement.txt` pour installer Gradio.
+
+### III: Thèmes
+Vous pouvez modifier le thème en modifiant l'option `THEME` (config.py).
+
+1. `Chuanhu-Small-and-Beautiful` [Lien](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV: Branches de développement de ce projet
+
+1. Branche `master` : Branche principale, version stable
+2. Branche `frontier` : Branche de développement, version de test
+
+
+### V: Références et apprentissage
+
+```
+De nombreux designs de codes de projets exceptionnels ont été référencés dans le développement de ce projet, sans ordre spécifique :
+
+# ChatGLM2-6B de l'Université Tsinghua:
+https://github.com/THUDM/ChatGLM2-6B
+
+# JittorLLMs de l'Université Tsinghua:
+https://github.com/Jittor/JittorLLMs
+
+# ChatPaper :
+https://github.com/kaixindelele/ChatPaper
+
+# Edge-GPT :
+https://github.com/acheong08/EdgeGPT
+
+# ChuanhuChatGPT :
+https://github.com/GaiZhenbiao/ChuanhuChatGPT
+
+
+
+# Oobabooga installeur en un clic :
+https://github.com/oobabooga/one-click-installers
+
+# Plus：
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.German.md

@@ -0,0 +1,363 @@
+
+
+
+> **Hinweis**
+>
+> Dieses README wurde mithilfe der GPT-Übersetzung (durch das Plugin dieses Projekts) erstellt und ist nicht zu 100 % zuverlässig. Bitte überprüfen Sie die Übersetzungsergebnisse sorgfältig.
+>
+> 7. November 2023: Beim Installieren der Abhängigkeiten bitte nur die in der `requirements.txt` **angegebenen Versionen** auswählen. Installationsbefehl: `pip install -r requirements.txt`.
+
+
+# <div align=center><img src="logo.png" width="40"> GPT Academic (GPT Akademisch)</div>
+
+**Wenn Ihnen dieses Projekt gefällt, geben Sie ihm bitte einen Star. Wenn Sie praktische Tastenkombinationen oder Plugins entwickelt haben, sind Pull-Anfragen willkommen!**
+
+Wenn Ihnen dieses Projekt gefällt, geben Sie ihm bitte einen Star.
+Um dieses Projekt mit GPT in eine beliebige Sprache zu übersetzen, lesen Sie [`multi_language.py`](multi_language.py) (experimentell).
+
+> **Hinweis**
+>
+> 1. Beachten Sie bitte, dass nur die mit **hervorgehobenen** Plugins (Schaltflächen) Dateien lesen können. Einige Plugins befinden sich im **Drop-down-Menü** des Plugin-Bereichs. Außerdem freuen wir uns über jede neue Plugin-PR mit **höchster Priorität**.
+>
+> 2. Die Funktionen jeder Datei in diesem Projekt sind im [Selbstanalysebericht `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT-Academic-Selbstanalysebericht) ausführlich erläutert. Sie können jederzeit auf die relevanten Funktions-Plugins klicken und GPT aufrufen, um den Selbstanalysebericht des Projekts neu zu generieren. Häufig gestellte Fragen finden Sie im [`Wiki`](https://github.com/binary-husky/gpt_academic/wiki). [Standardinstallationsmethode](#installation) | [Ein-Klick-Installationsskript](https://github.com/binary-husky/gpt_academic/releases) | [Konfigurationsanleitung](https://github.com/binary-husky/gpt_academic/wiki/Projekt-Konfigurationsanleitung).
+>
+> 3. Dieses Projekt ist kompatibel mit und unterstützt auch die Verwendung von inländischen Sprachmodellen wie ChatGLM. Die gleichzeitige Verwendung mehrerer API-Schlüssel ist möglich, indem Sie sie in der Konfigurationsdatei wie folgt angeben: `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`. Wenn Sie den `API_KEY` vorübergehend ändern möchten, geben Sie vorübergehend den temporären `API_KEY` im Eingabebereich ein und drücken Sie die Eingabetaste, um die Änderung wirksam werden zu lassen.
+
+
+
+
+<div align="center">
+
+Funktionen (⭐= Kürzlich hinzugefügte Funktion) | Beschreibung
+--- | ---
+⭐[Neues Modell integrieren](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)! | Baidu [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu) und Wenxin Yanyi, [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), Shanghai AI-Lab [Shusheng](https://github.com/InternLM/InternLM), Xunfei [Xinghuo](https://xinghuo.xfyun.cn/), [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Cognitive Graph API, DALLE3
+Verfeinern, Übersetzen, Codierung erläutern | Ein-Klick-Verfeinerung, Übersetzung, Suche nach grammatikalischen Fehlern in wissenschaftlichen Arbeiten, Erklärung von Code
+[Eigene Tastenkombinationen](https://www.bilibili.com/video/BV14s4y1E7jN) definieren | Eigene Tastenkombinationen definieren
+Modulare Gestaltung | Ermöglicht die Verwendung benutzerdefinierter leistungsstarker [Plugins](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions), Plugins unterstützen [Hot-Reload](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[Programmanalyse](https://www.bilibili.com/video/BV1cj411A7VW) | [Plugin] Ermöglicht die Erstellung einer Projekthierarchie für Python/C/C++/Java/Lua/... mit nur einem Klick oder [Selbstanalyse](https://www.bilibili.com/video/BV1cj411A7VW)
+Lesen von Forschungsarbeiten, Übersetzen von Forschungsarbeiten | [Plugin] Ermöglicht eine Umwandlung des gesamten Latex-/PDF-Forschungspapiers mit nur einem Klick und generiert eine Zusammenfassung
+Latex-Übersetzung des vollständigen Textes, Ausbesserung | [Plugin] Ermöglicht eine Übersetzung oder Verbesserung der Latex-Forschungsarbeit mit nur einem Klick
+Erzeugen von Batch-Anmerkungen | [Plugin] Erzeugt Funktionserläuterungen in Stapeln
+Markdown- [En-De-Übersetzung](https://www.bilibili.com/video/BV1yo4y157jV/) | [Plugin] Haben Sie die [README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md) in den oben genannten 5 Sprachen gesehen?
+Erzeugen eines Chat-Analyseberichts | [Plugin] Generiert einen zusammenfassenden Bericht nach der Ausführung
+PDF-Textübersetzungsmerkmal | [Plugin] Extrahiert Titel und Zusammenfassung des PDF-Dokuments und übersetzt den vollständigen Text (mehrfädig)
+Arxiv-Assistent | [Plugin] Geben Sie die URL eines Arxiv-Artikels ein, um eine Zusammenfassung zu übersetzen und die PDF-Datei herunterzuladen
+Automatische Überprüfung von Latex-Artikeln | [Plugin] Überprüft die Grammatik und Rechtschreibung von Latex-Artikeln nach dem Vorbild von Grammarly und generiert eine PDF-Vergleichsdatei
+Google Scholar Integration Assistant | [Plugin] Geben Sie eine beliebige URL der Google Scholar-Suchseite ein und lassen Sie GPT Ihre [Verwandten Arbeiten](https://www.bilibili.com/video/BV1GP411U7Az/) schreiben
+Internetinformationsaggregation + GPT | [Plugin] Ermöglicht es GPT, Fragen durch das Durchsuchen des Internets zu beantworten und Informationen immer auf dem neuesten Stand zu halten
+⭐Feine Übersetzung von Arxiv-Artikeln ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [Plugin] Übersetzt Arxiv-Artikel [mit hoher Qualität](https://www.bilibili.com/video/BV1dz4y1v77A/) mit einem Klick - das beste Übersetzungstool für wissenschaftliche Artikel
+⭐[Echtzeit-Spracheingabe](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [Plugin] [Asynchrones Lauschen auf Audio-Eingabe](https://www.bilibili.com/video/BV1AV4y187Uy/), automatisches Zerschneiden des Textes, automatische Suche nach dem richtigen Zeitpunkt zur Beantwortung
+Darstellen von Formeln/Bildern/Tabellen | Zeigt Formeln sowohl in [TEX-](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)- als auch in gerenderten Formen an, unterstützt Formeln und Code-Hervorhebung
+⭐AutoGen Multi-Agent Plugin | [Plugin] Erforscht die Möglichkeiten des emergenten Verhaltens von Multi-Agent-Systemen mit Microsoft AutoGen!
+Start im Dark-Theme | Um das Dark-Theme zu aktivieren, fügen Sie ```/?__theme=dark``` am Ende der URL im Browser hinzu
+[Mehrsprachige LLM-Modelle](https://www.bilibili.com/video/BV1wT411p7yf) unterstützt | Es ist sicherlich beeindruckend, von GPT3.5, GPT4, [ChatGLM2 der Tsinghua University](https://github.com/THUDM/ChatGLM2-6B), [MOSS der Fudan University](https://github.com/OpenLMLab/MOSS) bedient zu werden, oder?
+⭐ChatGLM2 Feinabstimmungsmodell | Unterstützt das Laden von ChatGLM2-Feinabstimmungsmodellen und bietet Unterstützung für ChatGLM2-Feinabstimmungsassistenten
+Integration weiterer LLM-Modelle, Unterstützung von [Huggingface-Deployment](https://huggingface.co/spaces/qingxu98/gpt-academic) | Hinzufügen der Newbing-Schnittstelle (neues Bing), Einführung der [Jittorllms der Tsinghua University](https://github.com/Jittor/JittorLLMs) zur Unterstützung von LLaMA und PanGu Alpha
+⭐[void-terminal](https://github.com/binary-husky/void-terminal) Pip-Paket | Verwenden Sie das Projekt in Python direkt, indem Sie das gesamte Funktionsplugin verwenden (in Entwicklung)
+⭐Void-Terminal-Plugin | [Plugin] Verwenden Sie natürliche Sprache, um andere Funktionen dieses Projekts direkt zu steuern
+Weitere Funktionen anzeigen (z. B. Bildgenerierung) …… | Siehe das Ende dieses Dokuments ……
+</div>
+
+
+- Neues Interface (Ändern Sie die LAYOUT-Option in der `config.py`, um zwischen "Links-Rechts-Layout" und "Oben-Unten-Layout" zu wechseln)
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- Alle Schaltflächen werden dynamisch aus der `functional.py` generiert und ermöglichen das beliebige Hinzufügen benutzerdefinierter Funktionen zur Befreiung der Zwischenablage.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- Überarbeiten/Korrigieren
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- If the output contains formulas, they will be displayed in both tex format and rendering format for easy copying and reading.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- Don't want to look at the project code? Show off the whole project directly in chatgpt's mouth.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- Multiple large language models mixed calling (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Installation
+### Installation Method I: Run directly (Windows, Linux or MacOS)
+
+1. Download the project
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. Configure API_KEY
+
+In `config.py`, configure API KEY and other settings, [click to view special network environment configuration methods](https://github.com/binary-husky/gpt_academic/issues/1). [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/Project-Configuration-Instructions).
+
+「 The program will first check if there is a confidential configuration file named `config_private.py` and use its configuration to override the configuration with the same name in `config.py`. If you understand this reading logic, we strongly recommend that you create a new configuration file named `config_private.py` next to `config.py` and move (copy) the configuration in `config.py` to `config_private.py` (only copy the configuration items that you have modified). 」
+
+「 You can configure the project through `environment variables`. The format of environment variables can refer to the `docker-compose.yml` file or our [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/Project-Configuration-Instructions). The priority of configuration reading is: `environment variables` > `config_private.py` > `config.py`. 」
+
+
+3. Install dependencies
+```sh
+# (Option I: if you are familiar with python, python>=3.9) Note: Use the official pip source or Ali pip source, temporary method to change the source: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (Option II: Using Anaconda) The steps are similar (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # Create an anaconda environment
+conda activate gptac_venv                 # Activate the anaconda environment
+python -m pip install -r requirements.txt # This step is the same as installing with pip
+```
+
+
+<details><summary>If you need support for Tsinghua ChatGLM2/Fudan MOSS/RWKV as backend, please click to expand.</summary>
+<p>
+
+[Optional] If you need to support Tsinghua ChatGLM2/Fudan MOSS as the backend, you need to install additional dependencies (Prerequisites: Familiar with Python + Have used PyTorch + Strong computer configuration):
+```sh
+# [Optional Step I] Support Tsinghua ChatGLM2. Tsinghua ChatGLM note: If you encounter the error "Call ChatGLM fail cannot load ChatGLM parameters normally", refer to the following: 1: The default installation above is torch+cpu version. To use cuda, you need to uninstall torch and reinstall torch+cuda; 2: If you cannot load the model due to insufficient computer configuration, you can modify the model accuracy in request_llm/bridge_chatglm.py. Change AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) to AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# [Optional Step II] Support Fudan MOSS
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # When executing this line of code, you must be in the root path of the project
+
+# [Optional Step III] Support RWKV Runner
+Refer to the wiki: https://github.com/binary-husky/gpt_academic/wiki/Support-RWKV-Runner
+
+# [Optional Step IV] Make sure the AVAIL_LLM_MODELS in config.py includes the expected models. The currently supported models are as follows (the jittorllms series only supports the docker solution at present):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+
+4. Run
+```sh
+python main.py
+```
+
+### Installation Method II: Use Docker
+
+0. Deploy all capabilities of the project (this is a large image that includes cuda and latex. But if you have a slow internet speed or a small hard drive, it is not recommended to use this)
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+``` sh
+# Modify docker-compose.yml, keep solution 0 and delete other solutions. Then run:
+docker-compose up
+```
+
+1. ChatGPT + Wenxin's words + spark and other online models (recommended for most people)
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+``` sh
+# Modify docker-compose.yml, keep solution 1 and delete other solutions. Then run:
+docker-compose up
+```
+
+P.S. If you need the Latex plugin functionality, please refer to the Wiki. Also, you can directly use solution 4 or 0 to get the Latex functionality.
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + Thousand Questions (Requires familiarity with [Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian) runtime)
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+``` sh
+# Modify docker-compose.yml, keep solution 2 and delete other solutions. Then run:
+docker-compose up
+```
+
+
+### Installation Method III: Other Deployment Methods
+1. **Windows One-Click Script**.
+Windows users who are completely unfamiliar with the python environment can download the one-click script for installation without local models in the published [Release](https://github.com/binary-husky/gpt_academic/releases).
+The script is contributed by [oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. Use third-party APIs, Azure, Wenxin's words, Spark, etc., see [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/Project-Configuration-Instructions)
+
+3. Pit avoidance guide for cloud server remote deployment.
+Please visit the [Cloud Server Remote Deployment Wiki](https://github.com/binary-husky/gpt_academic/wiki/Cloud-Server-Remote-Deployment-Guide)
+
+4. Some new deployment platforms or methods
+    - Use Sealos [one-click deployment](https://github.com/binary-husky/gpt_academic/issues/993).
+    - Use WSL2 (Windows Subsystem for Linux). Please visit the [deployment wiki-2](https://github.com/binary-husky/gpt_academic/wiki/Deploy-on-Windows-Subsystem-for-Linux-WSL2)
+    - How to run under a subpath (such as `http://localhost/subpath`). Please visit [FastAPI Running Instructions](docs/WithFastapi.md)
+
+
+
+# Fortgeschrittene Nutzung
+### I: Benutzerdefinierte Tasten hinzufügen (akademische Hotkeys)
+Öffnen Sie die Datei `core_functional.py` mit einem beliebigen Texteditor und fügen Sie folgenden Eintrag hinzu. Starten Sie dann das Programm neu. (Wenn die Schaltfläche bereits vorhanden ist, können sowohl das Präfix als auch das Suffix schnell geändert werden, ohne dass das Programm neu gestartet werden muss.)
+
+Beispiel:
+```
+"Übersetzung von Englisch nach Chinesisch": {
+    # Präfix, wird vor Ihrer Eingabe hinzugefügt. Zum Beispiel, um Ihre Anforderungen zu beschreiben, z.B. Übersetzen, Code erklären, verbessern usw.
+    "Präfix": "Bitte übersetzen Sie den folgenden Abschnitt ins Chinesische und erklären Sie dann jedes Fachwort in einer Markdown-Tabelle:\n\n",
+
+    # Suffix, wird nach Ihrer Eingabe hinzugefügt. Zum Beispiel, um Ihre Eingabe in Anführungszeichen zu setzen.
+    "Suffix": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: Benutzerdefinierte Funktionsplugins
+Schreiben Sie leistungsstarke Funktionsplugins, um beliebige Aufgaben zu erledigen, die Sie wünschen oder nicht erwartet haben.
+Das Erstellen und Debuggen von Plugins in diesem Projekt ist einfach und erfordert nur Grundkenntnisse in Python. Sie können unser bereitgestelltes Template verwenden, um Ihre eigene Plugin-Funktion zu implementieren.
+Weitere Informationen finden Sie in der [Plugin-Anleitung](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97).
+
+
+# Aktualisierungen
+### I: Neuigkeiten
+
+1. Dialogspeicherungsfunktion. Rufen Sie im Funktionspluginbereich "Aktuellen Dialog speichern" auf, um den aktuellen Dialog als lesbare und wiederherstellbare HTML-Datei zu speichern.
+Darüber hinaus können Sie im Funktionspluginbereich (Dropdown-Menü) "Dialoghistorie laden" aufrufen, um frühere Sitzungen wiederherzustellen.
+Tipp: Wenn kein Dateiname angegeben ist, können Sie direkt auf "Dialoghistorie laden" klicken, um den Verlauf des HTML-Archivs anzuzeigen.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐ Latex/Arxiv-Papierübersetzungsfunktion ⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. Leere Terminaloberfläche (Verständnis der Benutzerabsicht und automatischer Aufruf anderer Plugins aus natürlicher Spracheingabe)
+
+- Schritt 1: Geben Sie "Bitte Plugin aufrufen, um das PDF-Papier zu übersetzen, dessen Adresse https://openreview.net/pdf?id=rJl0r3R9KX ist" ein.
+- Schritt 2: Klicken Sie auf "Leere Terminaloberfläche".
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. Modulare Funktionsgestaltung mit einfacher Schnittstelle für leistungsstarke Funktionen
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. Übersetzung und Lösung anderer Open-Source-Projekte
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. Funktionen zur Dekoration von [live2d](https://github.com/fghrsh/live2d_demo) (standardmäßig deaktiviert, config.py muss geändert werden)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-677397d7-abe6-4358-9bef-3c14a7041b59.png" width="500" >
+</div>
+
+7. OpenAI-Bildgenerierung
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. OpenAI-Audioanalyse und Zusammenfassung
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Latex-Volltextkorrektur
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. Sprach- und Themenwechsel
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II: Versionen:
+- Version 3.70 (ausstehend): Optimierung des AutoGen-Plugin-Themas und Entwicklung einer Reihe von abgeleiteten Plugins
+- Version 3.60: Einführung von AutoGen als Grundlage für neue Plugin-Generation
+- Version 3.57: Unterstützung von GLM3, SparkV3, WenxinYiyanV4, Behebung von Problemen bei gleichzeitiger Verwendung von lokalen Modellen
+- Version 3.56: Dynamische Hinzufügung von Basisfunktionsbuttons, neue Übersichtsseite für PDFs
+- Version 3.55: Überarbeitung der Benutzeroberfläche, Hinzufügung von Schwebefenstern und Menüleiste
+- Version 3.54: Neuer dynamischer Code interpretier (Code Interpreter) (unfertig)
+- Version 3.53: Unterstützung für dynamische Auswahl verschiedener Oberflächenthemen, Verbesserung der Stabilität und Behebung von Mehrbenutzerkonflikten
+- Version 3.50: Verwenden Sie natürliche Sprache, um alle Funktionen dieses Projekts aufzurufen (leeres Terminal), Unterstützung für Plugin-Kategorien, verbesserte Benutzeroberfläche, neue Themen
+- Version 3.49: Unterstützung für Baidu Qianfan Platform und WenxinYiyan
+- Version 3.48: Unterstützung für Alibaba Damo Academy Tongyi Qianwen, Shanghai AI-Lab Shusheng, Xunfei Spark
+- Version 3.46: Vollständig automatisierter Echtzeit-Sprachdialog
+- Version 3.45: Anpassbare ChatGLM2-Feinjustierung
+- Version 3.44: Offizielle Unterstützung für Azure, Verbesserung der Benutzerfreundlichkeit der Benutzeroberfläche
+- Version 3.4: Hinzufügen von Arxiv-Papierübersetzung, LaTeX-Papierkorrektur
+- Version 3.3: Hinzufügen von Internet-Informationen
+- Version 3.2: Funktionsplugins unterstützen weitere Parameter (Dialog speichern, beliebigen Code analysieren und nach beliebigen LLM-Kombinationen fragen)
+- Version 3.1: Unterstützung für die gleichzeitige Abfrage mehrerer GPT-Modelle! Unterstützung für API-Schlüssel-Lastenausgleich
+- Version 3.0: Unterstützung von ChatGLM und anderen kleinen LLMs
+- Version 2.6: Neugestaltung der Plugin-Struktur, Verbesserung der Interaktivität, Hinzufügen weiterer Plugins
+- Version 2.5: Auto-Update zur Lösung von Problemen mit zu langem Text oder Tokenüberschuss beim Zusammenfassen von Code
+- Version 2.4: (1) Hinzufügen der Funktion zur Übersetzung des vollständigen PDF-Texts; (2) Neues Feature zum Wechseln der Position des Eingabebereichs; (3) Hinzufügen der Option für eine vertikale Ausrichtung; (4) Verbesserung der Multithreading-Funktionen von Plugins.
+- Version 2.3: Verbesserte Multithreading-Interaktivität
+- Version 2.2: Funktionsplugins können heiß neu geladen werden
+- Version 2.1: Faltbare Layouts
+- Version 2.0: Einführung modularer Funktionsplugins
+- Version 1.0: Grundfunktionen
+
+Entwickler-QQ-Gruppe von GPT Academic: `610599535`
+
+- Bekannte Probleme
+    - Einige Browserübersetzungsplugins beeinflussen die Frontend-Ausführung dieser Software
+    - Die offizielle Version von Gradio hat derzeit viele Kompatibilitätsprobleme. Installieren Sie Gradio daher unbedingt über `requirement.txt`.
+
+### III: Themen
+Sie können das Theme ändern, indem Sie die Option `THEME` (config.py) ändern.
+1. `Chuanhu-Small-and-Beautiful` [Link](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV: Entwicklungszweige dieses Projekts
+
+1. `master` Branch: Hauptzweig, stabile Version
+2. `frontier` Branch: Entwicklungsbranch, Testversion
+
+
+### V: Referenzen und Lernen
+
+```
+Der Code basiert auf dem Design anderer herausragender Projekte. Die Reihenfolge ist beliebig:
+
+# ChatGLM2-6B von Tsinghua:
+https://github.com/THUDM/ChatGLM2-6B
+
+# JittorLLMs von Tsinghua:
+https://github.com/Jittor/JittorLLMs
+
+# ChatPaper:
+https://github.com/kaixindelele/ChatPaper
+
+# Edge-GPT:
+https://github.com/acheong08/EdgeGPT
+
+# ChuanhuChatGPT:
+https://github.com/GaiZhenbiao/ChuanhuChatGPT
+
+
+
+# Oobabooga One-Click-Installations:
+https://github.com/oobabooga/one-click-installers
+
+# Weitere:
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.Italian.md

@@ -0,0 +1,360 @@
+
+
+
+> **Nota**
+>
+> Questo README è stato tradotto da GPT (implementato da un plugin di questo progetto) e non è al 100% affidabile, per favore valuta attentamente i risultati della traduzione.
+>
+> 2023.11.7: Quando installi le dipendenze, seleziona le versioni **specificate** nel file `requirements.txt`. Comando di installazione: `pip install -r requirements.txt`.
+
+
+# <div align=center><img src="logo.png" width="40"> GPT Ottimizzazione Accademica (GPT Academic)</div>
+
+**Se ti piace questo progetto, per favore dagli una stella; se hai idee o plugin utili, fai una pull request!**
+
+Se ti piace questo progetto, dagli una stella.
+Per tradurre questo progetto in qualsiasi lingua con GPT, leggi ed esegui [`multi_language.py`](multi_language.py) (sperimentale).
+
+> **Nota**
+>
+> 1. Fai attenzione che solo i plugin (pulsanti) **evidenziati** supportano la lettura dei file, alcuni plugin si trovano nel **menu a tendina** nell'area dei plugin. Inoltre, accogliamo e gestiamo con **massima priorità** qualsiasi nuovo plugin attraverso pull request.
+>
+> 2. Le funzioni di ogni file in questo progetto sono descritte in dettaglio nel [rapporto di traduzione automatica del progetto `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告). Con l'iterazione della versione, puoi anche fare clic sui plugin delle funzioni rilevanti in qualsiasi momento per richiamare GPT e rigenerare il rapporto di auto-analisi del progetto. Domande frequenti [`wiki`](https://github.com/binary-husky/gpt_academic/wiki) | [Metodo di installazione standard](#installazione) | [Script di installazione one-click](https://github.com/binary-husky/gpt_academic/releases) | [Configurazione](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。
+>
+> 3. Questo progetto è compatibile e incoraggia l'uso di modelli di linguaggio di grandi dimensioni nazionali, come ChatGLM. Supporto per la coesistenza di più chiavi API, puoi compilare nel file di configurazione come `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`. Quando è necessario sostituire temporaneamente `API_KEY`, inserisci temporaneamente `API_KEY` nell'area di input e premi Invio per confermare.
+
+
+
+
+<div align="center">
+
+Funzionalità (⭐ = Nuove funzionalità recenti) | Descrizione
+--- | ---
+⭐[Integrazione di nuovi modelli](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)！ | Baidu [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu) e [Wenxin](https://cloud.baidu.com/doc/GUIDE/5268.9) Intelligence, [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), Shanghai AI-Lab [bookbrain](https://github.com/InternLM/InternLM), Xunfei [Xinghuo](https://xinghuo.xfyun.cn/), [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Zhipu API, DALLE3
+Revisione, traduzione, spiegazione del codice | Revisione, traduzione, ricerca errori grammaticali nei documenti e spiegazione del codice con un clic
+[Tasti di scelta rapida personalizzati](https://www.bilibili.com/video/BV14s4y1E7jN) | Supporta tasti di scelta rapida personalizzati
+Design modulare | Supporto per plugin personalizzati potenti, i plugin supportano l'[aggiornamento in tempo reale](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[Analisi del codice](https://www.bilibili.com/video/BV1cj411A7VW) | [Plugin] Un clic per analizzare alberi di progetti Python/C/C++/Java/Lua/... o [autoanalisi](https://www.bilibili.com/video/BV1cj411A7VW)
+Lettura di documenti, traduzione di documenti | [Plugin] Un clic per interpretare documenti completi in latex/pdf e generare un riassunto
+Traduzione completa di testi in Latex, revisione completa di testi in Latex | [Plugin] Un clic per tradurre o correggere documenti in latex
+Generazione automatica di commenti in batch | [Plugin] Un clic per generare commenti di funzione in batch
+Traduzione [cinese-inglese](https://www.bilibili.com/video/BV1yo4y157jV/) in Markdown | [Plugin] Hai visto sopra i README in 5 lingue diverse ([Inglese](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md))?
+Generazione di rapporti di analisi chat | [Plugin] Genera automaticamente un rapporto di sintesi dopo l'esecuzione
+Funzionalità di traduzione di testo completo in PDF | [Plugin] Estrai il titolo e il riassunto dei documenti PDF e traduci tutto il testo (multithreading)
+Aiutante per Arxiv | [Plugin] Inserisci l'URL dell'articolo Arxiv per tradurre riassunto e scaricare PDF in un clic
+Controllo completo dei documenti in Latex | [Plugin] Rileva errori grammaticali e ortografici nei documenti in Latex simile a Grammarly + Scarica un PDF per il confronto
+Assistente per Google Scholar | [Plugin] Dato qualsiasi URL della pagina di ricerca di Google Scholar, fai scrivere da GPT gli *articoli correlati* per te
+Concentrazione delle informazioni di Internet + GPT | [Plugin] [Recupera informazioni da Internet](https://www.bilibili.com/video/BV1om4y127ck) utilizzando GPT per rispondere alle domande e rendi le informazioni sempre aggiornate
+⭐Traduzione accurata di articoli Arxiv ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [Plugin] [Traduci articoli Arxiv ad alta qualità](https://www.bilibili.com/video/BV1dz4y1v77A/) con un clic, lo strumento di traduzione degli articoli migliore al mondo al momento
+⭐[Inserimento della conversazione vocale in tempo reale](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [Plugin] [Ascolta l'audio](https://www.bilibili.com/video/BV1AV4y187Uy/) in modo asincrono, taglia automaticamente le frasi e trova automaticamente il momento giusto per rispondere
+Visualizzazione di formule, immagini, tabelle | Mostra contemporaneamente formule in formato tex e renderizzato, supporta formule e evidenziazione del codice
+⭐Plugin multi-agente AutoGen | [Plugin] Esplora le possibilità dell'emergenza intelligence multi-agente con l'aiuto di Microsoft AutoGen!
+Attiva il tema scuro [qui](https://github.com/binary-husky/gpt_academic/issues/173) | Aggiungi ```/?__theme=dark``` alla fine dell'URL del browser per passare al tema scuro
+Supporto di più modelli LLM | Essere servito contemporaneamente da GPT3.5, GPT4, [ChatGLM2 di Tsinghua](https://github.com/THUDM/ChatGLM2-6B), [MOSS di Fudan](https://github.com/OpenLMLab/MOSS)
+⭐Modello di fine-tuning ChatGLM2 | Supporto per l'importazione del modello di fine-tuning di ChatGLM2, fornendo plug-in di assistenza per il fine tuning di ChatGLM2
+Più supporto per modelli LLM, supporto del [deploy di Huggingface](https://huggingface.co/spaces/qingxu98/gpt-academic) | Aggiungi interfaccia Newbing (Bing Translator), introduce il supporto di [JittorLLMs](https://github.com/Jittor/JittorLLMs) di Tsinghua, supporto per [LLaMA](https://github.com/facebookresearch/llama) e [Panguα](https://openi.org.cn/pangu/)
+⭐Pacchetto pip [void-terminal](https://github.com/binary-husky/void-terminal) | Fornisce funzionalità di tutti i plugin di questo progetto direttamente in Python senza GUI (in sviluppo)
+⭐Plugin terminale virtuale | [Plugin] Richiama altri plugin di questo progetto utilizzando linguaggio naturale
+Altre nuove funzionalità (come la generazione di immagini) ... | Vedi alla fine di questo documento ...
+
+</div>
+
+
+- Nuovo layout (modifica l'opzione LAYOUT in `config.py` per passare tra "layout sinistra / destra" e "layout sopra / sotto")
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- Tutti i pulsanti vengono generati dinamicamente leggendo `functional.py`, puoi aggiungere liberamente funzionalità personalizzate, liberando la clipboard
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- Revisione / correzione
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- Se l'output contiene formule, saranno visualizzate sia in formato tex che in formato renderizzato per facilitarne la copia e la lettura.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- Non hai voglia di guardare il codice del progetto? Mostralo direttamente al chatgpt in bocca.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- Chiamate miste di modelli di grandi dimensioni (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Installazione
+### Metodo di installazione I: Esegui direttamente (Windows, Linux o MacOS)
+
+1. Scarica il progetto
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. Configura l'API_KEY
+
+Nel file `config.py`, configura l'API KEY e altre impostazioni, [clicca qui per vedere come configurare l'API in ambienti di rete speciali](https://github.com/binary-husky/gpt_academic/issues/1) . [Pagina Wiki](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+
+「 Il programma controllerà prima se esiste un file di configurazione privata chiamato `config_private.py` e utilizzerà le configurazioni in esso contenute per sovrascrivere le configurazioni con lo stesso nome in `config.py`. Se comprendi questa logica di lettura, ti consigliamo vivamente di creare un nuovo file di configurazione chiamato `config_private.py` accanto a `config.py` e spostare (copiare) le configurazioni da `config.py` a `config_private.py` (basta copiare le voci di configurazione che hai modificato). 」
+
+「 Supporta la configurazione del progetto tramite `variabili d'ambiente`, il formato di scrittura delle variabili d'ambiente è descritto nel file `docker-compose.yml` o nella nostra [pagina Wiki](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明) priorità di lettura della configurazione: `variabili d'ambiente` > `config_private.py` > `config.py`. 」
+
+3. Installa le dipendenze
+```sh
+# (Scelta I: Se familiarizzato con python, python>=3.9) Nota: Usa il repository delle fonti ufficiale di pip o Ali pip per temporaneamente cambiare la fonte: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (Scelta II: Usa Anaconda) Anche in questo caso, i passaggi sono simili (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # Crea l'ambiente anaconda
+conda activate gptac_venv                 # Attiva l'ambiente anaconda
+python -m pip install -r requirements.txt # Questo passaggio è identico alla procedura di installazione con pip
+```
+
+
+<details><summary>Se desideri utilizzare il backend di ChatGLM2 di Tsinghua/Fudan MOSS/RWKV, fai clic per espandere</summary>
+<p>
+
+[Optional] Se desideri utilizzare ChatGLM2 di Tsinghua/Fudan MOSS come backend, è necessario installare ulteriori dipendenze (Requisiti: conoscenza di Python + esperienza con Pytorch + hardware potente):
+```sh
+# [Optional Step I] Supporto per ChatGLM2 di Tsinghua. Note di ChatGLM di Tsinghua: Se si verifica l'errore "Call ChatGLM fail non può caricare i parametri di ChatGLM", fare riferimento a quanto segue: 1: L'installazione predefinita è la versione torch+cpu, per usare cuda è necessario disinstallare torch ed installare nuovamente la versione con torch+cuda; 2: Se il modello non può essere caricato a causa di una configurazione insufficiente, è possibile modificare la precisione del modello in request_llm/bridge_chatglm.py, sostituendo AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) con AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# [Optional Step II] Supporto per Fudan MOSS
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # Attenzione: eseguire questo comando nella directory principale del progetto
+
+# [Optional Step III] Supporto per RWKV Runner
+Consulta il Wiki: https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
+
+# [Optional Step IV] Assicurati che il file di configurazione config.py includa i modelli desiderati. Di seguito sono elencati i modelli attualmente supportati (gli llm di jittorllms supportano solo la soluzione Docker):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+
+4. Esegui
+```sh
+python main.py
+```
+
+### Metodo di installazione II: Utilizzo di Docker
+
+0. Installa tutte le funzionalità del progetto (Questo è un'immagine di grandi dimensioni che include cuda e latex. Potrebbe non essere adatta se hai una connessione lenta o uno spazio su disco limitato)
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+``` sh
+# Modifica il file docker-compose.yml: mantieni solo la configurazione 0 e rimuovi le altre configurazioni. Avvia il seguente comando:
+docker-compose up
+```
+
+1. ChatGPT + Wenxin Yiyu (Poem) + Spark, solo modelli online (Consigliato per la maggior parte delle persone)
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+``` sh
+# Modifica il file docker-compose.yml: mantieni solo la configurazione 1 e rimuovi le altre configurazioni. Avvia il seguente comando:
+docker-compose up
+```
+
+P.S. Se hai bisogno del plugin LaTeX, consulta la pagina Wiki. In alternativa, puoi utilizzare le configurazioni 4 o 0 direttamente per ottenere questa funzionalità.
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + Tongyi Q&W (Richiede conoscenze su Nvidia Docker)
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+``` sh
+# Modifica il file docker-compose.yml: mantieni solo la configurazione 2 e rimuovi le altre configurazioni. Avvia il seguente comando:
+docker-compose up
+```
+
+
+### Metodo di installazione III: Altre opzioni di distribuzione
+1. **Script di esecuzione con un clic per Windows**.
+Se non conosci affatto l'ambiente python in Windows, puoi scaricare uno script di esecuzione con un clic dalla sezione [Release](https://github.com/binary-husky/gpt_academic/releases) per installare la versione che non richiede modelli locali.
+Lo script è stato fornito da [oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. Utilizzo di API di terze parti, Azure, Wenxin Yiyu (Poem), Xinghuo, ecc. vedi [pagina Wiki](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)
+
+3. Guida all'installazione del server cloud remoto.
+Visita la [pagina Wiki sull'installazione del server cloud remoto](https://github.com/binary-husky/gpt_academic/wiki/云服务器远程部署指南).
+
+4. Altre nuove piattaforme o metodi di distribuzione:
+    - Uso di Sealos per il [deployment con un clic](https://github.com/binary-husky/gpt_academic/issues/993).
+    - Uso di WSL2 (Windows Subsystem for Linux). Vedi [Guida all'installazione](https://github.com/binary-husky/gpt_academic/wiki/使用WSL2（Windows-Subsystem-for-Linux-子系统）部署) per maggiori informazioni.
+    - Funzionamento su un sotto-percorso URL (`http://localhost/subpath`). Vedi [istruzioni FastAPI](docs/WithFastapi.md) per maggiori dettagli.
+
+
+
+# Utilizzo avanzato
+### I: Personalizzare nuovi pulsanti rapidi (tasti di scelta rapida accademici)
+Apri `core_functional.py` con qualsiasi editor di testo e aggiungi le seguenti voci, quindi riavvia il programma. (Se il pulsante esiste già, sia il prefisso che il suffisso possono essere modificati a caldo senza la necessità di riavviare il programma.)
+Ad esempio,
+```
+"Traduzione avanzata Cinese-Inglese": {
+     # Prefisso, sarà aggiunto prima del tuo input. Ad esempio, utilizzato per descrivere la tua richiesta, come traduzione, spiegazione del codice, rifinitura, ecc.
+     "Prefisso": "Si prega di tradurre il seguente testo in cinese e fornire spiegazione per i termini tecnici utilizzati, utilizzando una tabella in markdown uno per uno:\n\n",
+
+     # Suffisso, sarà aggiunto dopo il tuo input. Ad esempio, in combinazione con il prefisso, puoi circondare il tuo input con virgolette.
+     "Suffisso": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: Plugin di funzioni personalizzate
+Scrivi potentissimi plugin di funzioni per eseguire qualsiasi compito che desideri, sia che tu lo pensi o meno.
+La scrittura di plugin per questo progetto è facile e richiede solo conoscenze di base di Python. Puoi seguire il [Guida ai Plugin di Funzione](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97) per maggiori dettagli.
+
+
+# Aggiornamenti
+### I: Aggiornamenti
+
+1. Funzionalità di salvataggio della conversazione. Chiamare `Salva la conversazione corrente` nell'area del plugin per salvare la conversazione corrente come un file html leggibile e ripristinabile.
+Inoltre, nella stessa area del plugin (menu a tendina) chiamare `Carica la cronologia della conversazione` per ripristinare una conversazione precedente.
+Suggerimento: fare clic su `Carica la cronologia della conversazione` senza specificare un file per visualizzare la tua cronologia di archiviazione HTML.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐ Funzionalità di traduzione articoli Latex/Arxiv ⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. Terminale vuoto (Comprensione dell'intento dell'utente dai testi liberi + Chiamata automatica di altri plugin)
+
+- Passaggio 1: Digitare "Chiamare il plugin per tradurre un documento PDF, l'indirizzo è https://openreview.net/pdf?id=rJl0r3R9KX"
+- Passaggio 2: Fare clic su "Terminale vuoto"
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. Design modulare, interfacce semplici che supportano funzionalità potenti
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. Traduzione e interpretazione di altri progetti open source
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. Funzionalità leggera per [live2d](https://github.com/fghrsh/live2d_demo) (disabilitata per impostazione predefinita, richiede modifica di `config.py`)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. Generazione di immagini di OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. Elaborazione e riepilogo audio di OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Correzione totale del testo di Latex
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. Cambio linguaggio e tema
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+### II: Versioni:
+- versione 3.70 (todo): Ottimizzazione della visualizzazione del tema AutoGen e sviluppo di una serie di plugin correlati.
+- versione 3.60: Introduzione di AutoGen come fondamento per i plugin della nuova generazione.
+- versione 3.57: Supporto per GLM3, StarFirev3, Wenxin-yiyanv4 e correzione di bug sulla concorrenza dell'uso di modelli locali.
+- versione 3.56: Possibilità di aggiungere dinamicamente pulsanti per funzionalità di base e nuova pagina di riepilogo del PDF.
+- versione 3.55: Ristrutturazione dell'interfaccia utente, introduzione di finestre fluttuanti e barre dei menu.
+- versione 3.54: Nuovo interprete di codice dinamico (Code Interpreter) (da perfezionare).
+- versione 3.53: Possibilità di selezionare dinamicamente diversi temi dell'interfaccia utente, miglioramento della stabilità e risoluzione dei conflitti tra utenti multipli.
+- versione 3.50: Utilizzo del linguaggio naturale per chiamare tutte le funzioni dei plugin di questo progetto (Terminale vuoto), supporto per la classificazione dei plugin, miglioramento dell'interfaccia utente e design di nuovi temi.
+- versione 3.49: Supporto per la piattaforma Baidu Qianfan e Wenxin-yiyan.
+- versione 3.48: Supporto per Alibaba DAXI 所见即所答, Shanghai AI-Lab Shusheng, Xunfei StarFire.
+- versione 3.46: Supporto per la chat vocale in tempo reale completamente automatica.
+- versione 3.45: Supporto personalizzato per il micro-aggiustamento del modello ChatGLM2.
+- versione 3.44: Supporto ufficiale per Azure, miglioramento dell'usabilità dell'interfaccia.
+- versione 3.4: + Funzionalità di traduzione di documenti arXiv e correzione di documenti LaTeX.
+- versione 3.3: + Funzionalità di sintesi delle informazioni su Internet.
+- versione 3.2: Il plugin di funzione supporta più interfacce dei parametri (funzionalità di salvataggio della conversazione, interpretazione di codici in qualsiasi linguaggio contemporaneamente, interrogare qualsiasi combinazione di LLM).
+- versione 3.1: Supporto per l'interrogazione simultanea di più modelli GPT! Supporto per api2d, equilibrio del carico con più apikey.
+- versione 3.0: Supporto per chatglm e altri piccoli llm.
+- versione 2.6: Rielaborazione della struttura del plugin, miglioramento dell'interattività, aggiunta di ulteriori plugin.
+- versione 2.5: Aggiornamento automatico, risoluzione del problema della lunghezza eccessiva del testo durante il riepilogo di grandi blocchi di codice che supera i token.
+- versione 2.4: (1) Nuova funzionalità di traduzione di documenti PDF; (2) Nuova funzionalità di scambio delle posizioni tra l'area di input (input area); (3) Nuova opzione di layout verticale; (4) Ottimizzazione del plugin a threading multiplo.
+- versione 2.3: Miglioramento dell'interattività con threading multiplo.
+- versione 2.2: Supporto per il plugin con ricarica a caldo.
+- versione 2.1: Layout pieghevole.
+- versione 2.0: Introduzione di plugin modulari.
+- versione 1.0: Funzioni di base
+
+GPT Academic Developer QQ Group: `610599535`
+
+- Problemi noti
+    - Alcuni plug-in di traduzione del browser possono interferire con il funzionamento del frontend di questo software
+    - L'app Gradio ufficiale ha molti bug di compatibilità, si consiglia di installare Gradio tramite `requirement.txt`
+
+### III: Temi
+Il tema può essere modificato modificando l'opzione `THEME` (config.py)
+1. `Chuanhu-Small-and-Beautiful` [Website](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV: Branch di Sviluppo di questo progetto
+
+1. `master` branch: branch principale, versione stabile
+2. `frontier` branch: branch di sviluppo, versione di test
+
+
+### V: Riferimenti e Risorse di Apprendimento
+
+```
+Nel codice sono state utilizzate diverse idee dagli altri progetti, senza un ordine specifico:
+
+# ChatGLM2-6B di Tsinghua:
+https://github.com/THUDM/ChatGLM2-6B
+
+# JittorLLMs di Tsinghua:
+https://github.com/Jittor/JittorLLMs
+
+# ChatPaper:
+https://github.com/kaixindelele/ChatPaper
+
+# Edge-GPT:
+https://github.com/acheong08/EdgeGPT
+
+# ChuanhuChatGPT:
+https://github.com/GaiZhenbiao/ChuanhuChatGPT
+
+
+
+# Installazione con un solo clic di Oobabooga:
+https://github.com/oobabooga/one-click-installers
+
+# Altre risorse:
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.Japanese.md

@@ -0,0 +1,344 @@
+
+
+
+> **注意**
+>
+> 此READMEはGPTによる翻訳で生成されました（このプロジェクトのプラグインによって実装されています）、翻訳結果は100%正確ではないため、注意してください。
+>
+> 2023年11月7日: 依存関係をインストールする際は、`requirements.txt`で**指定されたバージョン**を選択してください。 インストールコマンド: `pip install -r requirements.txt`。
+
+
+# <div align=center><img src="logo.png" width="40"> GPT 学術最適化 (GPT Academic)</div>
+
+**このプロジェクトが気に入った場合は、Starを付けてください。また、便利なショートカットキーまたはプラグインを作成した場合は、プルリクエストを歓迎します！**
+GPTを使用してこのプロジェクトを任意の言語に翻訳するには、[`multi_language.py`](multi_language.py)を読み込んで実行します（実験的な機能）。
+
+> **注意**
+>
+> 1. **強調された** プラグイン（ボタン）のみがファイルを読み込むことができることに注意してください。一部のプラグインは、プラグインエリアのドロップダウンメニューにあります。また、新しいプラグインのPRを歓迎し、最優先で対応します。
+>
+> 2. このプロジェクトの各ファイルの機能は、[自己分析レポート`self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E5%A0%82)で詳しく説明されています。バージョンが進化するにつれて、関連する関数プラグインをクリックして、プロジェクトの自己分析レポートをGPTで再生成することもできます。よくある質問については、[`wiki`](https://github.com/binary-husky/gpt_academic/wiki)をご覧ください。[標準的なインストール方法](#installation) | [ワンクリックインストールスクリプト](https://github.com/binary-husky/gpt_academic/releases) | [構成の説明](https://github.com/binary-husky/gpt_academic/wiki/Project-Configuration-Explain)。
+>
+> 3. このプロジェクトは、[ChatGLM](https://www.chatglm.dev/)などの中国製の大規模言語モデルも互換性があり、試してみることを推奨しています。複数のAPIキーを共存させることができ、設定ファイルに`API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`のように記入できます。`API_KEY`を一時的に変更する必要がある場合は、入力エリアに一時的な`API_KEY`を入力し、Enterキーを押して提出すると有効になります。
+
+
+
+
+<div align="center">
+
+機能（⭐= 最近追加された機能） | 説明
+--- | ---
+⭐[新しいモデルの追加](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)！ | Baidu [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu)とWenxin Yiyu, [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), Shanghai AI-Lab [Shusheng](https://github.com/InternLM/InternLM), Xunfei [Xinghuo](https://xinghuo.xfyun.cn/), [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Zhantu API, DALLE3
+校正、翻訳、コード解説 | 一括校正、翻訳、論文の文法エラーの検索、コードの解説
+[カスタムショートカットキー](https://www.bilibili.com/video/BV14s4y1E7jN) | カスタムショートカットキーのサポート
+モジュール化された設計 | カスタムでパワフルな[プラグイン](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)のサポート、プラグインの[ホットリロード](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[プログラム解析](https://www.bilibili.com/video/BV1cj411A7VW) | [プラグイン] Python/C/C++/Java/Lua/...のプロジェクトツリーを簡単に解析するか、[自己解析](https://www.bilibili.com/video/BV1cj411A7VW)
+論文の読み込み、[翻訳](https://www.bilibili.com/video/BV1KT411x7Wn) | [プラグイン] LaTeX/PDFの論文全文を翻訳して要約を作成する
+LaTeX全文の[翻訳](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[校正](https://www.bilibili.com/video/BV1FT411H7c5/) | [プラグイン] LaTeX論文を翻訳や校正する
+一括コメント生成 | [プラグイン] 関数コメントを一括生成する
+Markdownの[日英翻訳](https://www.bilibili.com/video/BV1yo4y157jV/) | [プラグイン] 5つの言語（[英語](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)など）のREADMEをご覧になりましたか？
+チャット分析レポートの生成 | [プラグイン] 実行後にサマリーレポートを自動生成する
+[PDF論文全文の翻訳機能](https://www.bilibili.com/video/BV1KT411x7Wn) | [プラグイン] PDF論文のタイトルと要約を抽出し、全文を翻訳する（マルチスレッド）
+[Arxivアシスタント](https://www.bilibili.com/video/BV1LM4y1279X) | [プラグイン] arxiv論文のURLを入力すると、要約を翻訳してPDFをダウンロードできます
+LaTeX論文の一括校正 | [プラグイン] Grammarlyのように、LaTeX論文の文法とスペルを修正して対照PDFを出力する
+[Google Scholar統合アシスタント](https://www.bilibili.com/video/BV19L411U7ia) | [プラグイン] 任意のGoogle Scholar検索ページのURLを指定して、関連資料をGPTに書かせることができます
+インターネット情報の集約+GPT | [プラグイン] インターネットから情報を取得して質問に答え、情報が常に最新になるようにします
+⭐Arxiv論文の詳細な翻訳 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [プラグイン] arxiv論文を超高品質で翻訳します。最高の論文翻訳ツールです
+⭐[リアルタイム音声入力](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [プラグイン] 非同期[音声をリッスン(https://www.bilibili.com/video/BV1AV4y187Uy/)し、自動で文章を区切り、回答のタイミングを自動で探します
+公式/画像/表の表示 | 公式の[tex形式とレンダリング形式](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)を同時に表示し、公式とコードのハイライトをサポートします
+⭐AutoGenマルチエージェントプラグイン | [プラグイン] Microsoft AutoGenを利用して、マルチエージェントのインテリジェントなエマージェンスを探索します
+ダーク[テーマ](https://github.com/binary-husky/gpt_academic/issues/173)を起動 | ブラウザのURLに```/?__theme=dark```を追加すると、ダークテーマに切り替えられます
+[複数のLLMモデル](https://www.bilibili.com/video/BV1wT411p7yf)のサポート | GPT3.5、GPT4、[Tsinghua ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)、[Fudan MOSS](https://github.com/OpenLMLab/MOSS)などを同時に使えるのは最高の感じですよね？
+⭐ChatGLM2ファインチューニングモデル | ChatGLM2ファインチューニングモデルをロードして使用することができ、ChatGLM2ファインチューニングの補助プラグインが用意されています
+さらなるLLMモデルの導入、[HuggingFaceデプロイのサポート](https://huggingface.co/spaces/qingxu98/gpt-academic) | Newbingインターフェース（新しいBing）の追加、Tsinghua [Jittorllms](https://github.com/Jittor/JittorLLMs)の導入、[LLaMA](https://github.com/facebookresearch/llama)および[盤古α](https://openi.org.cn/pangu/)のサポート
+⭐[void-terminal](https://github.com/binary-husky/void-terminal) pipパッケージ | GUIから独立して、Pythonから直接このプロジェクトのすべての関数プラグインを呼び出せます（開発中）
+⭐Void Terminalプラグイン | [プラグイン] 自然言語で、このプロジェクトの他のプラグインを直接実行します
+その他の新機能の紹介（画像生成など）...... | 末尾をご覧ください ......
+</div>
+
+
+
+- もし出力に数式が含まれている場合、TeX形式とレンダリング形式の両方で表示されます。これにより、コピーと読み取りが容易になります。
+
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- プロジェクトのコードを見るのがめんどくさい？プロジェクト全体を`chatgpt`に広報口頭発表してもらえるよ
+
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- 異なる言語モデルの組み合わせ呼び出し（ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4）
+
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# インストール
+### 方法I：直接実行（Windows、Linux、またはMacOS）
+
+1. プロジェクトをダウンロード
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. APIキーを設定する
+
+`config.py`でAPIキーやその他の設定を設定します。特殊なネットワーク環境の設定方法については、[こちらをクリックして確認してください](https://github.com/binary-husky/gpt_academic/issues/1)。[Wikiページ](https://github.com/binary-husky/gpt_academic/wiki/Getting-Started)も参照してください。
+
+「プログラムは、`config.py`と同じ場所にある`config_private.py`という名前のプライベート設定ファイルが存在するかどうかを優先的にチェックし、同じ名前の設定をコピーします。この読み込みロジックを理解できる場合、`config.py`の横に`config_private.py`という名前の新しい設定ファイルを作成し、`config.py`の設定を転送（コピー）することを強くお勧めします（変更した設定項目だけをコピーします）。」
+
+「プロジェクトを環境変数で設定することもサポートしています。環境変数の書式は、`docker-compose.yml`ファイルや[Wikiページ](https://github.com/binary-husky/gpt_academic/wiki/Getting-Started)を参考にしてください。設定の優先度は、`環境変数` > `config_private.py` > `config.py`の順です。」
+
+3. 依存関係をインストールする
+```sh
+# （オプションI：Pythonに詳しい場合、Python 3.9以上）注：公式のpipソースまたは阿里pipソースを使用し、一時的なソースの変更方法は、python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/です。
+python -m pip install -r requirements.txt
+
+# （オプションII：Anacondaを使用する場合）手順は同様です (https://www.bilibili.com/video/BV1rc411W7Dr)：
+conda create -n gptac_venv python=3.11    # Anaconda環境を作成
+conda activate gptac_venv                 # Anaconda環境をアクティベート
+python -m pip install -r requirements.txt # この手順はpipのインストール手順と同じです
+```
+
+<details><summary>清華ChatGLM2/復旦MOSS/RWKVがバックエンドとしてサポートされている場合、ここをクリックして展開してください</summary>
+<p>
+
+【オプションステップ】 清華ChatGLM2/復旦MOSSをバックエンドとしてサポートする場合は、さらに追加の依存関係をインストールする必要があります（前提条件：Pythonに精通していて、PytorchとNVIDIA GPUを使用したことがあり、十分なコンピュータの構成を持っていること）：
+
+```sh
+# 【オプションステップI】 清華ChatGLM2のサポートを追加する。 清華ChatGLM2に関する注意点： "Call ChatGLM fail 不能正常加载ChatGLM的参数" のエラーが発生した場合、次の手順を参照してください。 1: デフォルトでインストールされているのはtorch+cpu版です。CUDAを使用するにはtorchをアンインストールしてtorch+cuda版を再インストールする必要があります。 2: モデルをロードできない場合は、request_llm/bridge_chatglm.pyのモデル精度を変更できます。AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)をAutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)に変更します。
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# 【オプションステップII】 復旦MOSSのサポートを追加する
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # このコマンドを実行するときは、プロジェクトのルートパスである必要があります。
+
+# 【オプションステップIII】 RWKV Runnerのサポートを追加する
+Wikiを参照してください: https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
+
+# 【オプションステップIV】 config.py設定ファイルに、以下のすべてのモデルが含まれていることを確認します。以下のモデルがすべてサポートされています（jittorllmsはDockerのみサポートされています）：
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+4. 実行する
+```sh
+python main.py
+```
+
+### 方法II：Dockerを使用する
+
+0. プロジェクトのフルスケールデプロイ（これは、CUDAとLaTeXを含む大規模なイメージですが、ネットワーク速度が遅いまたはディスク容量が小さい場合はおすすめしません）
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+```sh
+# docker-compose.ymlを編集し、スキーム0を残し、その他を削除してから実行する：
+docker-compose up
+```
+
+1. ChatGPT + 文心一言 + sparkなどのオンラインモデルのみを含む（ほとんどの人におすすめ）
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+```sh
+# docker-compose.ymlを編集し、スキーム1を残し、その他を削除してから実行する：
+docker-compose up
+```
+
+P.S. LaTeXプラグインの機能を使用する場合は、Wikiを参照してください。また、LaTeX機能を使用するためには、スキーム4またはスキーム0を直接使用することもできます。
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + 通慧千問（Nvidia Dockerに精通している場合）
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+```sh
+# docker-compose.ymlを編集し、スキーム2を残し、その他を削除してから実行する：
+docker-compose up
+```
+
+
+### 方法III：その他のデプロイメントオプション
+
+1. **Windowsのワンクリック実行スクリプト**。
+Python環境に詳しくないWindowsユーザーは、[リリース](https://github.com/binary-husky/gpt_academic/releases)からワンクリック実行スクリプトをダウンロードして、ローカルモデルのないバージョンをインストールできます。
+スクリプトの貢献者は[oobabooga](https://github.com/oobabooga/one-click-installers)です。
+
+2. 第三者のAPI、Azureなど、文心一言、星火などを使用するには、[Wikiページ](https://github.com/binary-husky/gpt_academic/wiki/Getting-Started)を参照してください。
+
+3. クラウドサーバーでのリモートデプロイの回避策ガイドを参照してください。
+[クラウドサーバーでのリモートデプロイの回避策ガイドwiki](https://github.com/binary-husky/gpt_academic/wiki/Getting-Started#%E4%BA%91%E3%82%B5%E3%83%BC%E3%83%90%E3%83%BC%E3%83%AA%E3%82%BC%E3%83%A0%E3%82%B5%E3%83%BC%E3%83%90%E3%81%AE%E3%83%AA%E3%83%A2%E3%83%BC%E3%83%88%E3%83%87%E3%83%97%E3%83%AD%E3%82%A4%E6%8C%87%E5%8D%97)
+
+4. その他の新しいデプロイプラットフォームや方法
+    - Sealosを使用した[ワンクリックデプロイ](https://github.com/binary-husky/gpt_academic/issues/993)
+    - WSL2（Windows Subsystem for Linux）の使用方法については、[デプロイwiki-2](https://github.com/binary-husky/gpt_academic/wiki/Getting-Started)を参照してください。
+    - サブパス（例：`http://localhost/subpath`）でFastAPIを実行する方法については、[FastAPIの実行方法](docs/WithFastapi.md)を参照してください。
+
+
+
+# 高度な使用法
+### I：カスタムショートカットボタンの作成（学術的なショートカットキー）
+テキストエディタで`core_functional.py`を開き、次の項目を追加し、プログラムを再起動します。（ボタンが存在する場合、プレフィックスとサフィックスはホット変更に対応しており、プログラムを再起動せずに有効にすることができます。）
+例：
+```
+"超级英译中"： {
+    # プレフィックス、入力の前に追加されます。例えば、要求を記述するために使用されます。翻訳、コードの解説、校正など
+    "プレフィックス"： "下記の内容を中国語に翻訳し、専門用語を一つずつマークダウンテーブルで解説してください：\n\n"、
+
+    # サフィックス、入力の後に追加されます。プレフィックスと一緒に使用して、入力内容を引用符で囲むことができます。
+    "サフィックス"： ""、
+}、
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II：関数プラグインのカスタマイズ
+自分の望む任意のタスクを実行するために、強力な関数プラグインを作成できます。
+このプロジェクトのプラグインの作成とデバッグの難易度は非常に低く、一定のPythonの基礎知識があれば、提供されたテンプレートを参考に自分自身のプラグイン機能を実装することができます。
+詳細については、[関数プラグインガイド](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)を参照してください。
+
+
+# 更新
+### I：ダイナミック
+
+1. 会話の保存機能。プラグインエリアで `Save Current Conversation` を呼び出すだけで、現在の会話を読み取り可能で復旧可能なhtmlファイルとして保存できます。
+また、プラグインエリア（ドロップダウンメニュー）で `Load Conversation History Archive` を呼び出すことで、以前の会話を復元できます。
+ヒント：ファイルを指定せずに `Load Conversation History Archive` をクリックすると、履歴のhtmlアーカイブのキャッシュを表示することができます。
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐Latex/Arxiv論文の翻訳機能⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. ゼロのターミナル（自然言語入力からユーザの意図を理解+他のプラグインを自動的に呼び出す）
+
+- ステップ1：「プラグインのPDF論文の翻訳を呼び出してください、アドレスはhttps://openreview.net/pdf?id=rJl0r3R9KX」と入力します。
+- ステップ2：「Zero Terminal」をクリックします。
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. モジュール化された機能設計、シンプルなインターフェイスで強力な機能をサポートする
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. 他のオープンソースプロジェクトの翻訳
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. [live2d](https://github.com/fghrsh/live2d_demo)のデコレーション機能（デフォルトでは無効で、`config.py`を変更する必要があります）
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. OpenAI画像生成
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. OpenAIオーディオ解析と要約
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Latex全体の校正と修正
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. 言語、テーマの切り替え
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II：バージョン:
+- version 3.70（todo）: AutoGenプラグインのテーマを最適化し、一連の派生プラグインを設計する
+- version 3.60: AutoGenを次世代プラグインの基盤として導入
+- version 3.57: GLM3、星火v3、文心一言v4をサポート、ローカルモデルの並行バグを修正
+- version 3.56: 基本機能ボタンを動的に追加、新しい報告書PDF集約ページ
+- version 3.55: フロントエンドのデザインを再構築し、浮動ウィンドウとメニューバーを導入
+- version 3.54: 新しい動的コードインタプリタ（Code Interpreter）の追加（未完成）
+- version 3.53: 異なるテーマを動的に選択できるように、安定性の向上と複数ユーザの競合問題の解決
+- version 3.50: 自然言語でこのプロジェクトのすべての関数プラグインを呼び出すことができるようになりました（ゼロのターミナル）プラグインの分類をサポートし、UIを改善し、新しいテーマを設計
+- version 3.49: Baidu Qianfanプラットフォームと文心一言をサポート
+- version 3.48: Alibaba DAMO Academy Tongyi Qianwen、Shanghai AI-Lab Shusheng、Xunfei Xinghuoをサポート
+- version 3.46: 完全なオートモードのリアルタイム音声対話をサポート
+- version 3.45: カスタムChatGLM2ファインチューニングモデルをサポート
+- version 3.44: 公式にAzureをサポート、UIの使いやすさを最適化
+- version 3.4: +arxiv論文の翻訳、latex論文の校閲機能
+- version 3.3: +インターネット情報の総合機能
+- version 3.2: 関数プラグインがさらに多くのパラメータインターフェースをサポート（会話の保存機能、任意の言語のコードの解釈、同時に任意のLLMの組み合わせを尋ねる）
+- version 3.1: 複数のgptモデルに同時に質問できるようにサポートされました！ api2dをサポートし、複数のapikeyの負荷分散をサポートしました
+- version 3.0: chatglmと他の小さなllmのサポート
+- version 2.6: プラグインの構造を再構築し、対話性を高め、より多くのプラグインを追加しました
+- version 2.5: 自己更新、ソースコード全体の要約時のテキストの長さ、トークンのオーバーフローの問題を解決しました
+- version 2.4: (1)新しいPDF全文翻訳機能を追加しました。(2)入力エリアの位置を切り替えるための新しい機能を追加しました。(3)垂直レイアウトオプションを追加しました。(4)マルチスレッド関数プラグインを最適化しました。
+- version 2.3: マルチスレッドの対話を強化しました
+- version 2.2: 関数プラグインのホットリロードをサポート
+- version 2.1: 折りたたみ式のレイアウト
+- version 2.0: モジュール化された関数プラグインの導入
+- version 1.0: 基本機能
+
+GPT Academic開発者QQグループ：`610599535`
+
+-既知の問題
+    - 一部のブラウザ翻訳プラグインがこのソフトウェアのフロントエンドの実行を妨げる
+    - 公式Gradioには互換性の問題があり、必ず`requirement.txt`を使用してGradioをインストールしてください
+
+### III：テーマ
+`THEME`オプション（`config.py`）を変更することで、テーマを変更できます
+1. `Chuanhu-Small-and-Beautiful` [リンク](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV：本プロジェクトの開発ブランチ
+
+1. `master`ブランチ：メインブランチ、安定版
+2. `frontier`ブランチ：開発ブランチ、テスト版
+
+
+### V：参考と学習
+
+```
+コードの中には、他の優れたプロジェクトのデザインを参考にしたものが多く含まれています。順序は問いません：
+
+# 清華ChatGLM2-6B:
+https://github.com/THUDM/ChatGLM2-6B
+
+# 清華JittorLLMs:
+https://github.com/Jittor/JittorLLMs
+
+# ChatPaper:
+https://github.com/kaixindelele/ChatPaper
+
+# Edge-GPT:
+https://github.com/acheong08/EdgeGPT
+
+# ChuanhuChatGPT:
+https://github.com/GaiZhenbiao/ChuanhuChatGPT
+
+
+
+# Oobaboogaワンクリックインストーラー：
+https://github.com/oobabooga/one-click-installers
+
+# その他：
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.Korean.md

@@ -0,0 +1,363 @@
+
+
+
+> **참고**
+>
+> 이 README는 GPT 번역으로 생성되었습니다 (이 프로젝트의 플러그인에 의해 구현됨) . 100% 신뢰할 수 없으므로 번역 결과를 주의 깊게 검토하십시오.
+>
+> 2023.11.7: 종속성을 설치할 때, `requirements.txt`에 **지정된 버전**을 선택하십시오. 설치 명령어: `pip install -r requirements.txt`.
+
+
+
+
+# <div align=center><img src="logo.png" width="40"> GPT 학술 최적화 (GPT Academic)</div>
+
+**이 프로젝트가 마음에 드신다면, Star를 부탁드립니다. 편리한 단축키나 플러그인을 발견하셨다면 Pull Request를 환영합니다!**
+GPT를 사용하여 이 프로젝트를 임의의 언어로 번역하려면 [`multi_language.py`](multi_language.py)를 읽고 실행하십시오 (실험적).
+
+
+> **참고**
+>
+> 1. **강조 표시**된 플러그인 (버튼)만 파일을 읽을 수 있습니다. 일부 플러그인은 플러그인 영역의 **드롭다운 메뉴**에 있습니다. 또한 새로운 플러그인에 대한 모든 PR을 환영하며, 이를 **가장 우선적**으로 처리합니다.
+>
+> 2. 이 프로젝트의 각 파일의 기능은 [자체 분석 보고서 `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic%EC%A0%9C%ED%94%84%EB%AA%85%EC%84%B1%EB%B0%A9%EC%8B%9D%EC%9D%98_%EA%B2%B0%EA%B3%BC)에서 자세히 설명되어 있습니다. 버전이 반복됨에 따라, 관련 기능 플러그인을 언제든지 클릭하여 GPT를 호출하여 프로젝트의 자체 분석 보고서를 다시 생성할 수 있습니다. 자주 묻는 질문은 [`위키`](https://github.com/binary-husky/gpt_academic/wiki)를 참조하십시오. [일반적인 설치 방법](#installation) | [원클릭 설치 스크립트](https://github.com/binary-husky/gpt_academic/releases) | [설정 설명서](https://github.com/binary-husky/gpt_academic/wiki/%EC%84%A4%EC%A0%95%EC%82%AC%EB%AA%85_%EA%B0%84%EB%8B%A8_%EC%84%B8%ED%8A%B8%EB%B2%84_%EC%B6%94%EA%B0%80)
+
+
+> 3. 이 프로젝트는 ChatGLM 등 대형 언어 모델 (ChatGLM 등) 실행을 지원하고 권장합니다. 여러 개의 API 키를 동시에 사용할 수 있으며, 구성 파일에 `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`와 같이 입력할 수 있습니다. `API_KEY`를 일시적으로 변경해야 하는 경우, 입력 영역에 임시 `API_KEY`를 입력한 다음 Enter 키를 누르면 적용됩니다.
+
+
+
+
+
+<div align="center">
+
+기능 (⭐= 최근 추가 기능) | 설명
+--- | ---
+⭐[새 모델 추가](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)! | Baidu [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu)와 Wenxin Yiyan, [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), Shanghai AI-Lab [Shusheng](https://github.com/InternLM/InternLM), Xunfei [Star](https://xinghuo.xfyun.cn/), [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Zhipu API, DALLE3
+문체 개선, 번역, 코드 설명 | 일괄적인 문체 개선, 번역, 논문 문법 오류 탐색, 코드 설명
+[사용자 정의 단축키](https://www.bilibili.com/video/BV14s4y1E7jN) | 사용자 정의 단축키 지원
+모듈화 설계 | 사용자 정의 가능한 강력한 [플러그인](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions) 지원, 플러그인 지원 [핫 업데이트](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[프로그램 분석](https://www.bilibili.com/video/BV1cj411A7VW) | [플러그인] 한 번에 Python/C/C++/Java/Lua/... 프로젝트 트리를 분석하거나 [자체 분석](https://www.bilibili.com/video/BV1cj411A7VW)
+논문 읽기, 논문 [번역](https://www.bilibili.com/video/BV1KT411x7Wn) | [플러그인] LaTeX/PDF 논문 전문을 읽고 요약 생성
+LaTeX 전체 [번역](https://www.bilibili.com/video/BV1nk4y1Y7Js/), [개선](https://www.bilibili.com/video/BV1FT411H7c5/) | [플러그인] LaTeX 논문 번역 또는 개선
+일괄 주석 생성 | [플러그인] 함수 주석 일괄 생성
+Markdown [한 / 영 번역](https://www.bilibili.com/video/BV1yo4y157jV/) | 위의 5개 언어로 작성된 [README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)를 살펴보셨나요?
+채팅 분석 보고서 생성 | [플러그인] 실행 후 요약 보고서 자동 생성
+[PDF 논문 전체 번역](https://www.bilibili.com/video/BV1KT411x7Wn) 기능 | [플러그인] PDF 논문 제목 및 요약 추출 + 전체 번역 (멀티 스레드)
+[Arxiv 도우미](https://www.bilibili.com/video/BV1LM4y1279X) | [플러그인] arxiv 논문 url 입력시 요약 번역 + PDF 다운로드
+LaTeX 논문 일괄 교정 | [플러그인] Grammarly를 모사하여 LaTeX 논문에 대한 문법 및 맞춤법 오류 교정 + 대조 PDF 출력
+[Google 학술 통합 도우미](https://www.bilibili.com/video/BV19L411U7ia) | 임의의 Google 학술 검색 페이지 URL을 지정하여 gpt가 [related works를 작성](https://www.bilibili.com/video/BV1GP411U7Az/)하게 해주세요.
+인터넷 정보 집계 + GPT | [플러그인] [인터넷에서 정보를 가져와서](https://www.bilibili.com/video/BV1om4y127ck) 질문에 대답하도록 GPT를 자동화하세요. 정보가 절대로 오래되지 않도록 해줍니다.
+⭐Arxiv 논문 세심한 번역 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [플러그인] [arxiv 논문을 고품질 번역으로](https://www.bilibili.com/video/BV1dz4y1v77A/) 번역하는 최고의 도구
+⭐[실시간 음성 대화 입력](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [플러그인] 비동기적으로 [오디오를 모니터링](https://www.bilibili.com/video/BV1AV4y187Uy/)하여 문장을 자동으로 분절하고 대답 시기를 자동으로 찾습니다.
+수식/이미지/표 표시 | [tex 형식 및 렌더링 형식](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)의 수식을 동시에 표시하며, 수식 및 코드 하이라이트 지원
+⭐AutoGen multi-agent 플러그인 | [플러그인] Microsoft AutoGen을 활용하여 여러 개의 에이전트가 지능적으로 발생하는 가능성을 탐색하세요!
+다크 모드 주제 지원 | 브라우저의 URL 뒤에 ```/?__theme=dark```를 추가하여 다크 모드로 전환하세요.
+[다양한 LLM 모델](https://www.bilibili.com/video/BV1wT411p7yf) 지원 | GPT3.5, GPT4, [Tsinghua ChatGLM2](https://github.com/THUDM/ChatGLM2-6B), [Fudan MOSS](https://github.com/OpenLMLab/MOSS)을 함께 사용하는 느낌은 좋을 것입니다, 그렇지 않습니까?
+⭐ChatGLM2 fine-tuned 모델 | ChatGLM2 fine-tuned 모델 로드를 지원하며, ChatGLM2 fine-tuned 보조 플러그인 제공
+더 많은 LLM 모델 연결, [huggingface 배포](https://huggingface.co/spaces/qingxu98/gpt-academic) 지원 | Newbing 인터페이스(신 밍), Tsinghua [Jittorllms](https://github.com/Jittor/JittorLLMs) 도입, [LLaMA](https://github.com/facebookresearch/llama)와 [Pangu-alpha](https://openi.org.cn/pangu/)를 지원합니다.
+⭐[void-terminal](https://github.com/binary-husky/void-terminal) 패키지 | GUI에서 독립, Python에서 이 프로젝트의 모든 함수 플러그인을 직접 호출 (개발 중)
+⭐Void 터미널 플러그인 | [플러그인] 자연어로 이 프로젝트의 다른 플러그인을 직접 영속합니다.
+기타 새로운 기능 소개 (이미지 생성 등) …… | 본 문서 맨 끝 참조 ……
+</div>
+
+
+- 새로운 인터페이스(`config.py`의 LAYOUT 옵션 수정으로 "왼쪽-오른쪽 레이아웃"과 "위-아래 레이아웃"을 전환할 수 있음)
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- 모든 버튼은 functional.py를 동적으로 읽어 생성되므로 원하는대로 사용자 정의 기능을 추가할 수 있으며 클립 보드를 해제할 수 있습니다.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- 문체 개선/오류 수정
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- If the output contains equations, they will be displayed in both tex format and rendered format for easy copying and reading.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- Don't feel like looking at the project code? Just give it to ChatGPT and let it dazzle you.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- Mix and match multiple powerful language models (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Installation
+### Installation Method I: Run Directly (Windows, Linux or MacOS)
+
+1. Download the project
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. Configure API_KEY
+
+In `config.py`, configure the API KEY and other settings, [click here to view special network environment configuration methods](https://github.com/binary-husky/gpt_academic/issues/1). [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。
+
+" The program will first check if there is a confidential configuration file named `config_private.py` and use its configuration to override the configuration with the same name in `config.py`. If you can understand this reading logic, we strongly recommend that you create a new configuration file named `config_private.py` next to `config.py` and move (copy) the configuration from `config.py` to `config_private.py` (only copy the modified configuration items). "
+
+" You can configure the project through `environment variables`. The format of the environment variables can be found in the `docker-compose.yml` file or our [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明). The priority of the configuration reading is: `environment variables` > `config_private.py` > `config.py`. "
+
+3. Install dependencies
+```sh
+# (Option I: if familiar with python, python>=3.9) Note: Use the official pip source or Aliyun pip source. Temporary switching source method: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (Option II: using Anaconda) The steps are similar (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # Create an Anaconda environment
+conda activate gptac_venv                 # Activate the Anaconda environment
+python -m pip install -r requirements.txt # This step is the same as the pip installation step
+```
+
+
+<details><summary>Click here to expand if you need support for Tsinghua ChatGLM2/Fudan MOSS/RWKV backend</summary>
+<p>
+
+[Optional Step] If you need support for Tsinghua ChatGLM2/Fudan MOSS as the backend, you need to install additional dependencies (Prerequisites: Familiar with Python + Have used Pytorch + Sufficient computer configuration):
+```sh
+# [Optional Step I] Support for Tsinghua ChatGLM2. Note for Tsinghua ChatGLM: If you encounter the error "Call ChatGLM fail cannot load ChatGLM parameters", refer to the following: 1: The default installation above is torch+cpu version. To use cuda, uninstall torch and reinstall torch+cuda; 2: If you cannot load the model due to insufficient computer configuration, you can modify the model precision in request_llm/bridge_chatglm.py, change AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) to AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# [Optional Step II] Support for Fudan MOSS
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # When executing this line of code, make sure you are in the project root path
+
+# [Optional Step III] Support for RWKV Runner
+Refer to the wiki: https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
+
+# [Optional Step IV] Make sure that the AVAIL_LLM_MODELS in the config.py configuration file includes the expected models. The currently supported models are as follows (the jittorllms series only supports the docker solution):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+
+4. Run
+```sh
+python main.py
+```
+
+### Installation Method II: Use Docker
+
+0. Deploy all the capabilities of the project (this is a large image that includes cuda and latex. However, it is not recommended if your internet speed is slow or your hard disk is small)
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+``` sh
+# Modify docker-compose.yml, keep scheme 0 and delete the others. Then run:
+docker-compose up
+```
+
+1. ChatGPT+Random Quotes+Wikipedia Summary+Spark and other online models (recommended for most people)
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+``` sh
+# Modify docker-compose.yml, keep scheme 1 and delete the others. Then run:
+docker-compose up
+```
+
+P.S. If you need the Latex plugin feature, please refer to the Wiki. Additionally, you can also use scheme 4 or scheme 0 directly to get the Latex feature.
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + Thousand Questions (Requires familiarity with [Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian) runtime)
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+``` sh
+# Modify docker-compose.yml, keep scheme 2 and delete the others. Then run:
+docker-compose up
+```
+
+
+### Installation Method III: Other Deployment Methods
+1. **One-click run script for Windows**.
+Windows users who are completely unfamiliar with the Python environment can download the one-click run script without local models from the [Release](https://github.com/binary-husky/gpt_academic/releases) section.
+The script contribution comes from [oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. Use third-party APIs, Azure, etc., Random Quotes, Spark, etc., see the [Wiki page](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+
+3. Pitfall guide for remote deployment on cloud servers.
+Please visit the [cloud server remote deployment wiki](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
+
+4. Some new deployment platforms or methods
+   - Use Sealos for [one-click deployment](https://github.com/binary-husky/gpt_academic/issues/993).
+   - Use WSL2 (Windows Subsystem for Linux). Please visit [deployment wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
+   - How to run in a subpath (such as `http://localhost/subpath`). Please refer to [FastAPI running instructions](docs/WithFastapi.md)
+
+
+
+# 고급 사용법
+### I: 사용자 정의 바로 가기 버튼 추가 (학술 단축키)
+임의의 텍스트 편집기로 `core_functional.py` 파일을 열고 다음과 같은 항목을 추가한 다음 프로그램을 다시 시작하십시오. (이미 버튼이 있는 경우에는 접두사와 접미사를 실시간으로 수정할 수 있으므로 프로그램을 다시 시작할 필요가 없습니다.)
+예시:
+```
+"초급영문 번역": {
+    # 접두사, 입력 내용 앞에 추가됩니다. 예를 들어 요구 사항을 설명하는 데 사용됩니다. 예를 들어 번역, 코드 설명, 교정 등
+    "Prefix": "다음 내용을 한국어로 번역하고 전문 용어에 대한 설명을 적용한 마크다운 표를 사용하세요:\n\n",
+
+    # 접미사, 입력 내용 뒤에 추가됩니다. 예를 들어 접두사와 함께 입력 내용을 따옴표로 감쌀 수 있습니다.
+    "Suffix": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: 사용자 정의 함수 플러그인
+원하는 작업을 수행하기 위해 능력있는 함수 플러그인을 작성하세요.
+이 프로젝트의 플러그인 작성 및 디버깅은 난이도가 낮으며, 일정한 Python 기본 지식만 있으면 우리가 제공하는 템플릿을 본따서 고유한 플러그인 기능을 구현할 수 있습니다.
+자세한 내용은 [함수 플러그인 가이드](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)를 참조하세요.
+
+
+# 업데이트
+### I: 다이나믹
+
+1. 대화 저장 기능. 플러그인 영역에서 '현재 대화 저장'을 호출하여 현재 대화를 볼 수 있고, html 파일을 복구할 수 있습니다.
+또한 플러그인 영역에서 '대화 기록 불러오기'를 호출하여 이전 대화를 복원할 수 있습니다.
+팁: 파일을 지정하지 않고 '대화 기록 불러오기'를 바로 클릭하면 이전 html 기록 캐시를 볼 수 있습니다.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐Latex/Arxiv 논문 번역 기능⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. 빈 터미널 (자연어 입력에서 사용자 의도 이해 + 자동 플러그인 호출)
+
+- 단계 1: "플러그인을 사용하여 PDF 논문을 번역하십시오. 주소는 https://openreview.net/pdf?id=rJl0r3R9KX입니다." 입력
+- 단계 2: "빈 터미널" 클릭
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. 모듈화된 기능 디자인, 간단한 인터페이스로 강력한 기능 제공
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. 다른 오픈 소스 프로젝트 번역
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. [live2d](https://github.com/fghrsh/live2d_demo)의 작은 기능 추가 (기본 설정은 닫혀 있으며, `config.py`를 수정해야 합니다.)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. OpenAI 이미지 생성
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. OpenAI 오디오 분석 및 요약
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Latex 전체 교정 오류
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. 언어, 테마 변경
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II: 버전:
+- 버전 3.70 (예정): AutoGen 플러그인 테마 개선 및 다른 테마 플러그인 디자인
+- 버전 3.60: AutoGen을 새로운 세대 플러그인의 기반으로 도입
+- 버전 3.57: GLM3, Starfire v3, 文心一言 v4 지원, 로컬 모델의 동시성 버그 수정
+- 버전 3.56: 동적으로 기본 기능 버튼 추가, 새로운 보고서 PDF 요약 페이지
+- 버전 3.55: 프론트 엔드 인터페이스 리팩토링, 화면 따라다니는 윈도우 및 메뉴 바 도입
+- 버전 3.54: 새로운 동적 코드 해석기 (Code Interpreter) 추가 (완벽하게 완성되지 않음)
+- 버전 3.53: 다른 인터페이스 테마 동적 선택 기능 추가, 안정성 향상 및 다중 사용자 충돌 문제 해결
+- 버전 3.50: 자연어로 이 프로젝트의 모든 함수 플러그인을 호출하는 기능 (빈 터미널) 추가, 플러그인 분류 지원, UI 개선, 새로운 테마 설계
+- 버전 3.49: Baidu Qianfan 플랫폼 및 문심일언 지원
+- 버전 3.48: Ali DameiYuan Sematic Query, Shanghai AI-Lab Shusheng, Xunfei Starfire 지원
+- 버전 3.46: 완전 자동 운전 가능한 실시간 음성 대화 지원
+- 버전 3.45: 사용자 정의 ChatGLM2 fine-tuning 모델 지원
+- 버전 3.44: Azure 정식 지원, 인터페이스의 사용 편의성 개선
+- 버전 3.4: +arxiv 논문 번역, latex 논문 교정 기능 추가
+- 버전 3.3: +인터넷 정보 종합 기능
+- 버전 3.2: 함수 플러그인이 더 많은 매개변수 인터페이스를 지원합니다 (대화 저장 기능, 임의의 언어 코드 해석 + 임의의 LLM 조합을 동시에 요청)
+- 버전 3.1: 여러 GPT 모델에 동시에 질문할 수 있는 기능 추가! api2d 지원, 여러 개의 apikey 부하 균형 조정 지원
+- 버전 3.0: chatglm 및 기타 소규모 llm 지원
+- 버전 2.6: 플러그인 구조를 재구성하여 상호 작용성 향상, 더 많은 플러그인 추가
+- 버전 2.5: 자동 업데이트, 소스 코드 요약 중 텍스트가 너무 길고 토큰이 오버플로되는 문제 해결
+- 버전 2.4: (1)PDF 전체 번역 기능 추가; (2)입력 영역 위치 전환 기능 추가; (3)수직 레이아웃 옵션 추가; (4)멀티 스레드 함수 플러그인 최적화
+- 버전 2.3: 멀티 스레드 상호 작용성 강화
+- 버전 2.2: 함수 플러그인의 핫 리로드 지원
+- 버전 2.1: 접을 수 있는 레이아웃
+- 버전 2.0: 모듈화 함수 플러그인 도입
+- 버전 1.0: 기본 기능
+
+GPT Academic 개발자 QQ 그룹: `610599535`
+- 알려진 문제
+    - 특정 웹 브라우저 번역 플러그인이 이 소프트웨어의 프론트엔드 실행에 방해가 되는 경우가 있습니다.
+    - 공식 Gradio에는 호환성 문제가 많기 때문에 `requirement.txt`를 사용하여 Gradio를 설치하십시오.
+
+### III: 테마
+`THEME` 옵션 (`config.py`)을 수정하여 테마를 변경할 수 있습니다.
+1. `Chuanhu-Small-and-Beautiful` [URL](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV: 이 프로젝트의 개발 브랜치
+
+1. `master` 브랜치: 메인 브랜치, 안정 버전
+2. `frontier` 브랜치: 개발 브랜치, 테스트 버전
+
+
+### V: 참고 및 학습
+
+```
+코드에서는 다른 우수한 프로젝트의 디자인을 많이 참고했습니다. 순서는 문제 없이 나열됩니다:
+
+# 清华ChatGLM2-6B:
+https://github.com/THUDM/ChatGLM2-6B
+
+# 清华JittorLLMs:
+https://github.com/Jittor/JittorLLMs
+
+# ChatPaper:
+https://github.com/kaixindelele/ChatPaper
+
+# Edge-GPT:
+https://github.com/acheong08/EdgeGPT
+
+# ChuanhuChatGPT:
+https://github.com/GaiZhenbiao/ChuanhuChatGPT
+
+
+
+# Oobabooga 원 클릭 설치 프로그램:
+https://github.com/oobabooga/one-click-installers
+
+# 더보기：
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo

docs/README.Portuguese.md

@@ -0,0 +1,357 @@
+
+
+
+> **Nota**
+>
+> Este README foi traduzido pelo GPT (implementado por um plugin deste projeto) e não é 100% confiável. Por favor, verifique cuidadosamente o resultado da tradução.
+>
+> 7 de novembro de 2023: Ao instalar as dependências, favor selecionar as **versões especificadas** no `requirements.txt`. Comando de instalação: `pip install -r requirements.txt`.
+
+# <div align=center><img src="logo.png" width="40"> GPT Acadêmico</div>
+
+**Se você gosta deste projeto, por favor, dê uma estrela nele. Se você inventou atalhos de teclado ou plugins úteis, fique à vontade para criar pull requests!**
+Para traduzir este projeto para qualquer idioma utilizando o GPT, leia e execute [`multi_language.py`](multi_language.py) (experimental).
+
+> **Nota**
+>
+> 1. Observe que apenas os plugins (botões) marcados em **destaque** são capazes de ler arquivos, alguns plugins estão localizados no **menu suspenso** do plugin area. Também damos boas-vindas e prioridade máxima a qualquer novo plugin via PR.
+>
+> 2. As funcionalidades de cada arquivo deste projeto estão detalhadamente explicadas em [autoanálise `self_analysis.md`](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告). Com a iteração das versões, você também pode clicar nos plugins de funções relevantes a qualquer momento para chamar o GPT para regerar o relatório de autonálise do projeto. Perguntas frequentes [`wiki`](https://github.com/binary-husky/gpt_academic/wiki) | [Método de instalação convencional](#installation) | [Script de instalação em um clique](https://github.com/binary-husky/gpt_academic/releases) | [Explicação de configuração](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。
+>
+> 3. Este projeto é compatível e encoraja o uso de modelos de linguagem chineses, como ChatGLM. Vários api-keys podem ser usados simultaneamente, podendo ser especificados no arquivo de configuração como `API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`. Quando precisar alterar temporariamente o `API_KEY`, insira o `API_KEY` temporário na área de entrada e pressione Enter para que ele seja efetivo.
+
+
+<div align="center">
+
+Funcionalidades (⭐= funcionalidade recentemente adicionada) | Descrição
+--- | ---
+⭐[Integração com novos modelos](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B)！ | [Qianfan](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu) da Baidu, Wenxin e [Tongyi Qianwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary), [Shusheng](https://github.com/InternLM/InternLM) da Shanghai AI-Lab, [Xinghuo](https://xinghuo.xfyun.cn/) da Iflytek, [LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), Zhipu API, DALLE3
+Aprimoramento, tradução, explicação de códigos | Aprimoramento com um clique, tradução, busca de erros gramaticais em artigos e explicação de códigos
+[Atalhos de teclado personalizados](https://www.bilibili.com/video/BV14s4y1E7jN) | Suporte para atalhos de teclado personalizados
+Design modular | Suporte a plugins poderosos e personalizáveis, plugins com suporte a [atualização a quente](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
+[Análise de código](https://www.bilibili.com/video/BV1cj411A7VW) | [Plugin] Análise instantânea da estrutura de projetos em Python/C/C++/Java/Lua/... ou [autoanálise](https://www.bilibili.com/video/BV1cj411A7VW)
+Leitura de artigos, [tradução](https://www.bilibili.com/video/BV1KT411x7Wn) de artigos | [Plugin] Interpretação instantânea de artigos completos em latex/pdf e geração de resumos
+Tradução completa de artigos em latex [PDF](https://www.bilibili.com/video/BV1nk4y1Y7Js/), [aprimoramento](https://www.bilibili.com/video/BV1FT411H7c5/) | [Plugin] Tradução completa ou aprimoramento de artigos em latex com um clique
+Geração em lote de comentários | [Plugin] Geração em lote de comentários de funções com um clique
+Tradução (inglês-chinês) de Markdown | [Plugin] Você já viu o [README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md) nas 5 línguas acima?
+Criação de relatório de análise de bate-papo | [Plugin] Geração automática de relatório de resumo após a execução
+Tradução [completa de artigos em PDF](https://www.bilibili.com/video/BV1KT411x7Wn) | [Plugin] Extração de título e resumo de artigos em PDF + tradução completa (multithreading)
+Auxiliar Arxiv | [Plugin] Insira o URL de um artigo Arxiv para traduzir o resumo + baixar o PDF com um clique
+Correção automática de artigos em latex | [Plugin] Correções gramaticais e ortográficas de artigos em latex semelhante ao Grammarly + saída PDF comparativo
+Auxiliar Google Scholar | [Plugin] Insira qualquer URL da busca do Google Acadêmico e deixe o GPT [escrever trabalhos relacionados](https://www.bilibili.com/video/BV1GP411U7Az/) para você
+Agregação de informações da Internet + GPT | [Plugin] Capturar informações da Internet e obter respostas de perguntas com o GPT em um clique, para que as informações nunca fiquem desatualizadas
+⭐Tradução refinada de artigos do Arxiv ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [Plugin] Tradução de alta qualidade de artigos do Arxiv com um clique, a melhor ferramenta de tradução de artigos atualmente
+⭐Entrada de conversa de voz em tempo real | [Plugin] Monitoramento de áudio [assíncrono](https://www.bilibili.com/video/BV1AV4y187Uy/), segmentação automática de frases, detecção automática de momentos de resposta
+Exibição de fórmulas, imagens e tabelas | Exibição de fórmulas em formato tex e renderizadas simultaneamente, suporte a fórmulas e destaque de código
+⭐Plugin AutoGen para vários agentes | [Plugin] Explore a emergência de múltiplos agentes com o AutoGen da Microsoft!
+Ativar o tema escuro | Adicione ```/?__theme=dark``` ao final da URL para alternar para o tema escuro
+Suporte a múltiplos modelos LLM | Ser atendido simultaneamente pelo GPT3.5, GPT4, [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B) do Tsinghua University e [MOSS](https://github.com/OpenLMLab/MOSS) da Fudan University se sente incrível, não é mesmo?
+⭐Modelo de ajuste fino ChatGLM2 | Suporte para carregar o modelo ChatGLM2 ajustado e fornecer plugins de assistência ao ajuste fino do ChatGLM2
+Mais modelos LLM e suporte para [implantação pela HuggingFace](https://huggingface.co/spaces/qingxu98/gpt-academic) | Integração com a interface Newbing (Bing novo), introdução do [Jittorllms](https://github.com/Jittor/JittorLLMs) da Tsinghua University com suporte a [LLaMA](https://github.com/facebookresearch/llama) e [Panguα](https://openi.org.cn/pangu/)
+⭐Pacote pip [void-terminal](https://github.com/binary-husky/void-terminal) | Chame todas as funções plugins deste projeto diretamente em Python, sem a GUI (em desenvolvimento)
+⭐Plugin Terminal do Vácuo | [Plugin] Chame outros plugins deste projeto diretamente usando linguagem natural
+Apresentação de mais novas funcionalidades (geração de imagens, etc.) ... | Veja no final deste documento ...
+
+</div>
+
+
+- Nova interface (altere a opção LAYOUT em `config.py` para alternar entre os "Layouts de lado a lado" e "Layout de cima para baixo")
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/d81137c3-affd-4cd1-bb5e-b15610389762" width="700" >
+</div>
+
+
+- Todos os botões são gerados dinamicamente através da leitura do `functional.py`, você pode adicionar funcionalidades personalizadas à vontade, liberando sua área de transferência
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
+</div>
+
+- Aprimoramento/Correção
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
+</div>
+
+
+
+- Se a saída contiver fórmulas, elas serão exibidas tanto em formato tex quanto renderizado para facilitar a cópia e a leitura.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
+</div>
+
+- Não tem vontade de ver o código do projeto? O projeto inteiro está diretamente na boca do chatgpt.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
+</div>
+
+- Combinação de vários modelos de linguagem (ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
+</div>
+
+# Instalação
+### Método de instalação I: Executar diretamente (Windows, Linux ou MacOS)
+
+1. Baixe o projeto
+```sh
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+cd gpt_academic
+```
+
+2. Configure a API_KEY
+
+No arquivo `config.py`, configure a API KEY e outras configurações. [Clique aqui para ver o método de configuração em redes especiais](https://github.com/binary-husky/gpt_academic/issues/1). [Página Wiki](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+
+「 O programa verificará primeiro se existe um arquivo de configuração privada chamado `config_private.py` e substituirá as configurações correspondentes no arquivo `config.py`. Se você entender essa lógica de leitura, é altamente recomendável criar um novo arquivo de configuração chamado `config_private.py` ao lado do `config.py` e copiar as configurações do `config.py` para o `config_private.py` (copiando apenas os itens de configuração que você modificou). 」
+
+「 Suporte para configurar o projeto por meio de `variáveis de ambiente`, o formato de gravação das variáveis de ambiente pode ser encontrado no arquivo `docker-compose.yml` ou em nossa [página Wiki](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明). A prioridade de leitura das configurações é: `variáveis de ambiente` > `config_private.py` > `config.py`. 」
+
+
+3. Instale as dependências
+```sh
+# (Opção I: Se você está familiarizado com o Python, Python>=3.9) Observação: Use o pip oficial ou o pip da Aliyun. Método temporário para alternar fontes: python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+python -m pip install -r requirements.txt
+
+# (Opção II: Use o Anaconda) Os passos também são semelhantes (https://www.bilibili.com/video/BV1rc411W7Dr):
+conda create -n gptac_venv python=3.11    # Crie um ambiente do Anaconda
+conda activate gptac_venv                 # Ative o ambiente do Anaconda
+python -m pip install -r requirements.txt # Este passo é igual ao da instalação do pip
+```
+
+
+<details><summary>Se você quiser suporte para o ChatGLM2 do THU/ MOSS do Fudan/RWKV como backend, clique para expandir</summary>
+<p>
+
+[Opcional] Se você quiser suporte para o ChatGLM2 do THU/ MOSS do Fudan, precisará instalar dependências extras (pré-requisitos: familiarizado com o Python + já usou o PyTorch + o computador tem configuração suficiente):
+```sh
+# [Opcional Passo I] Suporte para ChatGLM2 do THU. Observações sobre o ChatGLM2 do THU: Se você encontrar o erro "Call ChatGLM fail 不能正常加载ChatGLM的参数" (Falha ao chamar o ChatGLM, não é possível carregar os parâmetros do ChatGLM), consulte o seguinte: 1: A versão instalada por padrão é a versão torch+cpu. Se você quiser usar a versão cuda, desinstale o torch e reinstale uma versão com torch+cuda; 2: Se a sua configuração não for suficiente para carregar o modelo, você pode modificar a precisão do modelo em request_llm/bridge_chatglm.py, alterando todas as ocorrências de AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) para AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+python -m pip install -r request_llms/requirements_chatglm.txt
+
+# [Opcional Passo II] Suporte para MOSS do Fudan
+python -m pip install -r request_llms/requirements_moss.txt
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss  # Observe que você deve estar no diretório raiz do projeto ao executar este comando
+
+# [Opcional Passo III] Suporte para RWKV Runner
+Consulte a página Wiki: https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
+
+# [Opcional Passo IV] Verifique se o arquivo de configuração config.py contém os modelos desejados, os modelos compatíveis são os seguintes (a série jittorllms suporta apenas a solução Docker):
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+```
+
+</p>
+</details>
+
+
+
+4. Execute
+```sh
+python main.py
+```
+
+### Método de instalação II: Usando o Docker
+
+0. Implante todas as capacidades do projeto (este é um contêiner grande que inclui CUDA e LaTeX. Não recomendado se você tiver uma conexão lenta com a internet ou pouco espaço em disco)
+[![fullcapacity](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
+
+``` sh
+# Modifique o arquivo docker-compose.yml para incluir apenas a seção 0 e excluir as outras seções. Em seguida, execute:
+docker-compose up
+```
+
+1. ChatGPT + 文心一言 + spark + outros modelos online (recomendado para a maioria dos usuários)
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
+[![basicaudio](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
+
+``` sh
+# Modifique o arquivo docker-compose.yml para incluir apenas a seção 1 e excluir as outras seções. Em seguida, execute:
+docker-compose up
+```
+
+Obs.: Se você precisar do plugin Latex, consulte a Wiki. Além disso, você também pode usar a seção 4 ou 0 para obter a funcionalidade do LaTeX.
+
+2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + 通义千问 (você precisa estar familiarizado com o [Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian) para executar este modo)
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
+
+``` sh
+# Modifique o arquivo docker-compose.yml para incluir apenas a seção 2 e excluir as outras seções. Em seguida, execute:
+docker-compose up
+```
+
+
+### Método de instalação III: Outros métodos de implantação
+1. **Script de execução com um clique para Windows**.
+Usuários do Windows que não estão familiarizados com o ambiente Python podem baixar o script de execução com um clique da [Release](https://github.com/binary-husky/gpt_academic/releases) para instalar a versão sem modelos locais.
+A contribuição do script vem de [oobabooga](https://github.com/oobabooga/one-click-installers).
+
+2. Usar APIs de terceiros, Azure, etc., 文心一言, 星火, consulte a [página Wiki](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明).
+
+3. Guia para evitar armadilhas na implantação em servidor em nuvem.
+Consulte o [wiki de implantação em servidor em nuvem](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97).
+
+4. Algumas novas plataformas ou métodos de implantação
+    - Use Sealos [implantação com um clique](https://github.com/binary-husky/gpt_academic/issues/993).
+    - Use o WSL2 (Subsistema do Windows para Linux). Consulte [wiki de implantação](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2).
+    - Como executar em um subdiretório da URL (como `http://localhost/subpath`). Consulte [instruções de execução com o FastAPI](docs/WithFastapi.md)
+
+
+
+# Uso Avançado
+### I: Personalização de Novos Botões de Atalho (Atalhos Acadêmicos)
+Abra o arquivo `core_functional.py` em qualquer editor de texto, adicione o seguinte item e reinicie o programa. (Se o botão já existir, o prefixo e o sufixo podem ser modificados a qualquer momento sem reiniciar o programa).
+Por exemplo:
+```
+"超级英译中": {
+    # Prefixo, adicionado antes do seu input. Por exemplo, usado para descrever sua solicitação, como traduzir, explicar o código, revisar, etc.
+    "Prefix": "Por favor, traduza o parágrafo abaixo para o chinês e explique cada termo técnico dentro de uma tabela markdown:\n\n",
+
+    # Sufixo, adicionado após o seu input. Por exemplo, em conjunto com o prefixo, pode-se colocar seu input entre aspas.
+    "Suffix": "",
+},
+```
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
+</div>
+
+### II: Personalização de Funções Plugins
+Crie poderosos plugins de função para executar tarefas que você pode e não pode imaginar.
+Criar plugins neste projeto é fácil, basta seguir o modelo fornecido, desde que você tenha conhecimento básico de Python.
+Consulte o [Guia dos Plugins de Função](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97) para mais detalhes.
+
+
+# Atualizações
+### I: Dinâmico
+
+1. Função de salvar conversas. Chame a função "Salvar a conversa atual" na área de plugins para salvar a conversa atual em um arquivo HTML legível e recuperável. Além disso, chame a função "Carregar histórico de conversas" na área de plugins (menu suspenso) para restaurar conversas anteriores.
+Dica: Se você clicar diretamente em "Carregar histórico de conversas" sem especificar o arquivo, poderá visualizar o cache do histórico do arquivo HTML.
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐Tradução de artigos Latex/Arxiv⭐
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
+</div>
+
+3. Terminal vazio (entendendo a intenção do usuário a partir do texto em linguagem natural e chamando automaticamente outros plugins)
+
+- Passo 1: Digite "Por favor, chame o plugin 'Traduzir artigo PDF' e forneça o link https://openreview.net/pdf?id=rJl0r3R9KX"
+- Passo 2: Clique em "Terminal vazio"
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. Design de recursos modular, interface simples com suporte a recursos poderosos
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
+<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
+</div>
+
+5. Tradução e interpretação de outros projetos de código aberto
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
+<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
+</div>
+
+6. Recursos adicionais para [live2d](https://github.com/fghrsh/live2d_demo) (desativados por padrão, requer modificação no arquivo `config.py`)
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
+</div>
+
+7. Geração de imagens pela OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
+</div>
+
+8. Análise e resumo de áudio pela OpenAI
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
+</div>
+
+9. Correção de erros em texto e código LaTeX
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
+</div>
+
+10. Alternância de idioma e tema
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
+</div>
+
+
+
+### II: Versões:
+- Versão 3.70 (a fazer): Melhorar o plugin AutoGen e projetar uma série de plugins relacionados.
+- Versão 3.60: Introdução do AutoGen como base para a próxima geração de plugins.
+- Versão 3.57: Suporte para GLM3, Starfire v3, Wenxin Yiyan v4, correção de bugs relacionados a modelos locais executados simultaneamente.
+- Versão 3.56: Suporte para adicionar dinamicamente botões de função básicos e nova página de resumo em PDF.
+- Versão 3.55: Reformulação da interface do usuário, introdução de janelas flutuantes e menus.
+- Versão 3.54: Novo interpretador de código dinâmico (Code Interpreter) (em desenvolvimento)
+- Versão 3.53: Suporte para alterar dinamicamente o tema da interface, melhorias de estabilidade e correção de conflitos entre vários usuários.
+- Versão 3.50: Chamada de todas as funções de plugins deste projeto usando linguagem natural (Terminal vazio), suporte a categorização de plugins, melhorias na interface do usuário e design de novos temas.
+- Versão 3.49: Suporte para Baidu Qianfan Platform e Wenxin Yiyan.
+- Versão 3.48: Suporte para Alibaba DAMO Academy Tongyi Qianwen, Shanghai AI-Lab Shusheng e Xunfei Xinghuo.
+- Versão 3.46: Suporte para diálogos em tempo real totalmente automáticos.
+- Versão 3.45: Suporte para personalização do modelo ChatGLM2.
+- Versão 3.44: Suporte oficial ao Azure, aprimoramentos na usabilidade da interface.
+- Versão 3.4: Tradução completa de artigos Arxiv/Latex, correção de artigos Latex.
+- Versão 3.3: Funcionalidade de consulta a informações na internet.
+- Versão 3.2: Maior suporte para parâmetros de função de plugins (função de salvar conversas, interpretação de código em qualquer linguagem + perguntas sobre combinações LLM arbitrariamente).
+- Versão 3.1: Suporte para fazer perguntas a modelos GPT múltiplos! Suporte para API2D, balanceamento de carga em vários APIKeys.
+- Versão 3.0: Suporte para chatglm e outros pequenos modelos LLM.
+- Versão 2.6: Refatoração da estrutura de plugins, melhoria na interação, adição de mais plugins.
+- Versão 2.5: Auto-atualizável, resolve problemas de texto muito longo ou estouro de tokens ao resumir grandes projetos de código.
+- Versão 2.4: (1) Novo recurso de tradução completa de PDF; (2) Nova função para alternar a posição da área de input; (3) Nova opção de layout vertical; (4) Melhoria dos plugins de função em várias threads.
+- Versão 2.3: Melhorias na interação em várias threads.
+- Versão 2.2: Suporte para recarregar plugins sem reiniciar o programa.
+- Versão 2.1: Layout dobrável.
+- Versão 2.0: Introdução de plugins de função modular.
+- Versão 1.0: Funcionalidades básicas.
+
+GPT Academic QQ Group: `610599535`
+
+- Problemas conhecidos
+    - Alguns plugins de tradução de navegadores podem interferir na execução deste software.
+    - A biblioteca Gradio possui alguns bugs de compatibilidade conhecidos. Certifique-se de instalar o Gradio usando o arquivo `requirement.txt`.
+
+### III: Temas
+Você pode alterar o tema atualizando a opção `THEME` (config.py).
+1. `Chuanhu-Small-and-Beautiful` [Link](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV: Branches de Desenvolvimento deste Projeto
+
+1. Branch `master`: Branch principal, versão estável.
+2. Branch `frontier`: Branch de desenvolvimento, versão de teste.
+
+
+### V: Referências para Aprendizado
+
+```
+O código referenciou muitos projetos excelentes, em ordem aleatória:
+
+# Tsinghua ChatGLM2-6B:
+https://github.com/THUDM/ChatGLM2-6B
+
+# Tsinghua JittorLLMs:
+https://github.com/Jittor/JittorLLMs
+
+# ChatPaper:
+https://github.com/kaixindelele/ChatPaper
+
+# Edge-GPT:
+https://github.com/acheong08/EdgeGPT
+
+# ChuanhuChatGPT:
+https://github.com/GaiZhenbiao/ChuanhuChatGPT
+
+
+
+# Oobabooga instalador com um clique:
+https://github.com/oobabooga/instaladores-de-um-clique
+
+# Mais:
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo