Update HUGGINGFACE_ACCESS_TOKEN

support rust program

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,25 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-labels: ''
-assignees: ''
-
----
-
-- **(1) Describe the bug 简述**
-
-
-- **(2) Screen Shot 截图**
-
-
-- **(3) Terminal Traceback 终端traceback（如有）**
-
-
-- **(4) Material to Help Reproduce Bugs 帮助我们复现的测试材料样本（如有）**
-
-
-
-Before submitting an issue 提交issue之前：
-- Please try to upgrade your code. 如果您的代码不是最新的，建议您先尝试更新代码
-- Please check project wiki for common problem solutions.项目[wiki](https://github.com/binary-husky/chatgpt_academic/wiki)有一些常见问题的解决方法

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,75 @@
+name: Report Bug | 报告BUG
+description: "Report bug"
+title: "[Bug]: "
+labels: []
+body:
+  - type: dropdown
+    id: download
+    attributes:
+      label: Installation Method | 安装方法与平台
+      options:
+        - Please choose | 请选择
+        - Pip Install (I ignored requirements.txt)
+        - Pip Install (I used latest requirements.txt)
+        - Anaconda (I ignored requirements.txt)
+        - Anaconda (I used latest requirements.txt)
+        - Docker（Windows/Mac）
+        - Docker（Linux）
+        - Docker-Compose（Windows/Mac）
+        - Docker-Compose（Linux）
+        - Huggingface
+        - Others (Please Describe)
+    validations:
+      required: true
+
+  - type: dropdown
+    id: version
+    attributes:
+      label: Version | 版本
+      options:
+        - Please choose | 请选择
+        - Latest | 最新版
+        - Others | 非最新版
+    validations:
+      required: true
+      
+  - type: dropdown
+    id: os
+    attributes:
+      label: OS | 操作系统
+      options:
+        - Please choose | 请选择
+        - Windows
+        - Mac
+        - Linux
+        - Docker
+    validations:
+      required: true
+      
+  - type: textarea
+    id: describe
+    attributes:
+      label: Describe the bug | 简述
+      description: Describe the bug | 简述
+    validations:
+      required: true
+      
+  - type: textarea
+    id: screenshot
+    attributes:
+      label: Screen Shot | 有帮助的截图
+      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.md

@@ -1,10 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
----
-
-

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -0,0 +1,28 @@
+name: Feature Request | 功能请求
+description: "Feature Request"
+title: "[Feature]: "
+labels: []
+body:
+  - type: dropdown
+    id: download
+    attributes:
+      label: Class | 类型
+      options:
+        - Please choose | 请选择
+        - 其他
+        - 函数插件
+        - 大语言模型
+        - 程序主体
+    validations:
+      required: false
+
+  - type: textarea
+    id: traceback
+    attributes:
+      label: Feature Request | 功能请求
+      description: Feature Request | 功能请求
+
+
+
+
+

.github/workflows/build-with-chatglm.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: Create and publish a Docker image for ChatGLM support
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_chatglm_moss
+
+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+ChatGLM+Moss
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-with-jittorllms.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: Create and publish a Docker image for ChatGLM support
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_jittorllms
+
+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+JittorLLMs
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-with-latex.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: Create and publish a Docker image for Latex support
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_with_latex
+
+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+NoLocal+Latex
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/build-without-local-llms.yml

@@ -0,0 +1,44 @@
+# https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
+name: Create and publish a Docker image
+
+on:
+  push:
+    branches:
+      - 'master'
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}_nolocal
+
+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+NoLocal
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.gitignore

@@ -146,3 +146,7 @@ debug*
 private*
 crazy_functions/test_project/pdf_and_word
 crazy_functions/test_samples
+request_llm/jittorllms
+multi-language
+request_llm/moss
+media

.pre-commit-config.yaml

@@ -0,0 +1,32 @@
+default_language_version:
+  python: python3
+exclude: 'dotnet'
+ci:
+  autofix_prs: true
+  autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions'
+  autoupdate_schedule: 'quarterly'
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+    - id: check-ast
+    # - id: check-yaml
+    - id: check-toml
+    - id: check-json
+    - id: check-byte-order-marker
+      exclude: .gitignore
+    - id: check-merge-conflict
+    - id: detect-private-key
+    - id: trailing-whitespace
+    - id: end-of-file-fixer
+    - id: no-commit-to-branch
+  - repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+    - id: black
+  # - repo: https://github.com/charliermarsh/ruff-pre-commit
+  #   rev: v0.0.261
+  #   hooks:
+  #     - id: ruff
+  #       args: ["--fix"]

Dockerfile

@@ -1,20 +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，请参考 docs/Dockerfile+ChatGLM
-# 如何构建: 先修改 `config.py`， 然后 docker build -t gpt-academic .
-# 如何运行: docker run --rm -it --net=host 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 （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（必要）
 WORKDIR /gpt
-COPY requirements.txt .
+
+
+# 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 ./
 RUN pip3 install -r requirements.txt
 
-COPY . .
 
-# 可选步骤，用于预热模块
+# 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（可以删除）
 RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
 
+
+# 启动（必要）
 CMD ["python3", "-u", "main.py"]

README.md

@@ -1,61 +1,106 @@
+---
+title: GPT-Academic
+emoji: 😻
+colorFrom: blue
+colorTo: blue
+sdk: gradio
+sdk_version: 3.32.0
+app_file: app.py
+pinned: false
+---
+
+# ChatGPT 学术优化
 > **Note**
 > 
-> 本项目依赖的Gradio组件的新版pip包(Gradio 3.26~3.27)有严重bug。所以，请在安装时严格选择requirements.txt中**指定的版本**。 
-> 
-> `pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/`
+> 2023.11.12: 某些依赖包尚不兼容python 3.12，推荐python 3.11。
 > 
+> 2023.12.26: 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。
 
-# <img src="docs/logo.png" width="40" > ChatGPT 学术优化
+<br>
 
-**如果喜欢这个项目，请给它一个Star；如果你发明了更好用的快捷键或函数插件，欢迎发pull requests**
+<div align=center>
+<h1 aligh="center">
+<img src="docs/logo.png" width="40"> GPT 学术优化 (GPT Academic)
+</h1>
 
-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)[Русский|](docs/README_RS.md)[Français](docs/README_FR.md) translated by this project itself.
+[![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]
 
-> **Note**
+[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))
 >
-> 1.请注意只有**红颜色**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[`self_analysis.md`](https://github.com/binary-husky/chatgpt_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)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。常见问题汇总在[`wiki`](https://github.com/binary-husky/chatgpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)当中。
-> 
-> 3.已支持OpenAI和API2D的api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,api2d-key3"`。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。
+> 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。
+
+<br><br>
 
 <div align="center">
 
-功能 | 描述
+功能（⭐= 近期新增功能） | 描述
 --- | ---
-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/chatgpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/chatgpt_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/chatgpt_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/chatgpt_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
-[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ChatGPT先Google搜索，再回答问题，信息流永不过时
+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gradio[主题](https://github.com/binary-husky/chatgpt_academic/issues/173) | 在浏览器url后面添加```/?__dark-theme=true```可以切换dark主题
-[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持，[API2D](https://api2d.com/)接口支持 | 同时被GPT3.5、GPT4和[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)伺候的感觉一定会很不错吧？
-更多LLM模型接入 | 新加入Newbing测试接口(新必应AI)
-…… | ……
-
+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)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）
+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>
 
 
-- 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>
@@ -65,116 +110,165 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
 <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>
 
----
+<br><br>
 
-## 安装-方法1：直接运行 (Windows, Linux or MacOS)
+# Installation
 
-1. 下载项目
-```sh
-git clone https://github.com/binary-husky/chatgpt_academic.git
-cd chatgpt_academic
+```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](https://github.com/binary-husky/gpt_academic/issues/1) 。
+1. 下载项目
 
-（P.S. 程序运行时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。因此，如果您能理解我们的配置读取逻辑，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。`config_private.py`不受git管控，可以让您的隐私信息更加安全。）
+    ```sh
+    git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
+    cd gpt_academic
+    ```
+
+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）推荐
-python -m pip install -r requirements.txt
-# 备注：使用官方pip源或者阿里pip源，其他pip源（如一些大学的pip）有可能出问题，临时换源方法：python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
+    ```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: 如不熟悉python）使用anaconda，步骤也是类似的：
-# （II-1）conda create -n gptac_venv python=3.11
-# （II-2）conda activate gptac_venv
-# （II-3）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
+    ```
+
+
+<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_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", "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
 ```
 
-如果需要支持清华ChatGLM后端，需要额外安装更多依赖（前提条件：熟悉python + 电脑配置够强）：
-```sh
-python -m pip install -r request_llm/requirements_chatglm.txt
-```
+</p>
+</details>
+
+
 
 4. 运行
-```sh
-python main.py
-```
+    ```sh
+    python main.py
+    ```
 
-5. 测试函数插件
-```
-- 测试函数插件模板函数（要求gpt回答历史上的今天发生了什么），您可以根据此函数为模板，实现更复杂的功能
-    点击 "[函数插件模板Demo] 历史上的今天"
-```
+### 安装方法II：使用Docker
 
-## 安装-方法2：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。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)
 
-1. 仅ChatGPT（推荐大多数人选择）
+    ``` 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
+    ```
 
-``` sh
-# 下载项目
-git clone https://github.com/binary-husky/chatgpt_academic.git
-cd chatgpt_academic
-# 配置 “Proxy”， “API_KEY” 以及 “WEB_PORT” (例如50923) 等
-用任意文本编辑器编辑 config.py
-# 安装
-docker build -t gpt-academic .
-#（最后一步-选择1）在Linux环境下，用`--net=host`更方便快捷
-docker run --rm -it --net=host gpt-academic
-#（最后一步-选择2）在macOS/windows环境下，只能用-p选项将容器上的端口(例如50923)暴露给主机上的端口
-docker run --rm -it -p 50923:50923 gpt-academic
-```
+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)
 
-2. ChatGPT+ChatGLM（需要对Docker熟悉 + 读懂Dockerfile + 电脑配置够强）
+    ``` 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
+    ```
 
-``` sh
-# 修改Dockerfile
-cd docs && nano Dockerfile+ChatGLM
-# 构建 （Dockerfile+ChatGLM在docs路径下，请先cd docs）
-docker build -t gpt-academic --network=host -f Dockerfile+ChatGLM .
-# 运行 (1) 直接运行: 
-docker run --rm -it --net=host --gpus=all gpt-academic
-# 运行 (2) 我想运行之前进容器做一些调整: 
-docker run --rm -it --net=host --gpus=all gpt-academic bash
-```
+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。
 
-## 安装-方法3：其他部署方式（需要云服务器知识与经验）
+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)
 
-1. 远程云服务器部署
-请访问[部署wiki-1](https://github.com/binary-husky/chatgpt_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)
+    ``` 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
+    ```
 
-2. 使用WSL2（Windows Subsystem for Linux 子系统）
-请访问[部署wiki-2](https://github.com/binary-husky/chatgpt_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)
 
-3. 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)
+### 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)
 
-## 自定义新的便捷按钮 / 自定义函数插件
+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)
 
-1. 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。）
+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`，添加如下条目，然后重启程序。（如果按钮已存在，那么可以直接修改（前缀、后缀都已支持热修改），无需重启程序即可生效。）
 例如
-```
+
+```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",
@@ -183,40 +277,180 @@ docker run --rm -it --net=host --gpus=all gpt-academic bash
     "Suffix": "",
 },
 ```
+
 <div align="center">
 <img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
 </div>
 
-2. 自定义函数插件
-
+### 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/chatgpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)。
+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>
+
+# 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。
+Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史html存档缓存。
+<div align="center">
+<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
+</div>
+
+2. ⭐Latex/Arxiv论文翻译功能⭐
+<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. 虚空终端（从自然语言输入中，理解用户意图+自动调用其他插件）
+
+- 步骤一：输入 “ 请调用插件翻译PDF论文，地址为https://openreview.net/pdf?id=rJl0r3R9KX ”
+- 步骤二：点击“虚空终端”
+
+<div align="center">
+<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
+</div>
+
+4. 模块化功能设计，简单的接口却能支持强大的功能
+<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. 译解其他开源项目
+<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. 装饰[live2d](https://github.com/fghrsh/live2d_demo)的小功能（默认关闭，需要修改`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>
+
+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/c518b82f-bd53-46e2-baf5-ad1b081c1da4" width="500" >
+</div>
+
+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>
+
+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>
 
 
 
-## 版本:
+### II：版本:
+- 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
+- version 3.48: 支持阿里达摩院通义千问，上海AI-Lab书生，讯飞星火
+- version 3.46: 支持完全脱手操作的实时语音对话
+- version 3.45: 支持自定义ChatGLM2微调模型
+- version 3.44: 正式支持Azure，优化界面易用性
+- version 3.4: +arxiv论文翻译、latex论文批改功能
+- version 3.3: +互联网信息综合功能
 - version 3.2: 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)
 - version 3.1: 支持同时问询多个gpt模型！支持api2d，支持多个apikey负载均衡
 - 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：`610599535`
 
-## 参考与学习
+- 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
 
 ```
-代码中参考了很多其他优秀项目中的设计，主要包括：
 
-# 借鉴项目1：借鉴了ChuanhuChatGPT中诸多技巧
+
+### 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：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：
+
+# 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
 
-# 借鉴项目2：清华ChatGLM-6B：
-https://github.com/THUDM/ChatGLM-6B
+# Oobabooga one-click installer:
+https://github.com/oobabooga/one-click-installers
+
+# More：
+https://github.com/gradio-app/gradio
+https://github.com/fghrsh/live2d_demo
 ```

app.py

@@ -0,0 +1,412 @@
+import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
+
+help_menu_description = \
+"""Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
+感谢热情的[开发者们❤️](https://github.com/binary-husky/gpt_academic/graphs/contributors).
+</br></br>常见问题请查阅[项目Wiki](https://github.com/binary-husky/gpt_academic/wiki),
+如遇到Bug请前往[Bug反馈](https://github.com/binary-husky/gpt_academic/issues).
+</br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交
+</br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮
+</br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮
+</br></br>虚空终端使用说明: 点击虚空终端, 然后根据提示输入指令, 再次点击虚空终端
+</br></br>如何保存对话: 点击保存当前的对话按钮
+</br></br>如何语音对话: 请阅读Wiki
+</br></br>如何临时更换API_KEY: 在输入区输入临时API_KEY后提交（网页刷新后失效）"""
+
+def main():
+    import subprocess, sys
+    subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'https://public.agent-matrix.com/publish/gradio-3.32.8-py3-none-any.whl'])
+    import gradio as gr
+    if gr.__version__ not in ['3.32.8']:
+        raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
+    from request_llms.bridge_all import predict
+    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
+    # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址
+    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
+    CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
+    ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
+    DARK_MODE, NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('DARK_MODE', 'NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
+    INIT_SYS_PROMPT = get_conf('INIT_SYS_PROMPT')
+
+    # 如果WEB_PORT是-1, 则随机选取WEB端口
+    PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
+    from check_proxy import get_current_version
+    from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
+    from themes.theme import js_code_for_css_changing, js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
+    from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, init_cookie
+    title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
+
+    # 问询记录, python 版本建议3.9+（越新越好）
+    import logging, uuid
+    os.makedirs(PATH_LOGGING, exist_ok=True)
+    try:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    except:logging.basicConfig(filename=f"{PATH_LOGGING}/chat_secrets.log", level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    # Disable logging output from the 'httpx' logger
+    logging.getLogger("httpx").setLevel(logging.WARNING)
+    print(f"所有问询记录将自动保存在本地目录./{PATH_LOGGING}/chat_secrets.log, 请注意自我隐私保护哦！")
+
+    # 一些普通功能模块
+    from core_functional import get_core_functions
+    functional = get_core_functions()
+
+    # 高级函数插件
+    from crazy_functional import get_crazy_functions
+    DEFAULT_FN_GROUPS = get_conf('DEFAULT_FN_GROUPS')
+    plugins = get_crazy_functions()
+    all_plugin_groups = list(set([g for _, plugin in plugins.items() for g in plugin['Group'].split('|')]))
+    match_group = lambda tags, groups: any([g in groups for g in tags.split('|')])
+
+    # 处理markdown文本格式的转变
+    gr.Chatbot.postprocess = format_io
+
+    # 做一些外观色彩上的调整
+    set_theme = adjust_theme()
+
+    # 代理与自动更新
+    from check_proxy import check_proxy, auto_update, warm_up_modules
+    proxy_info = check_proxy(proxies)
+
+    gr_L1 = lambda: gr.Row().style()
+    gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id, min_width=400)
+    if LAYOUT == "TOP-DOWN":
+        gr_L1 = lambda: DummyWith()
+        gr_L2 = lambda scale, elem_id: gr.Row()
+        CHATBOT_HEIGHT /= 2
+
+    cancel_handles = []
+    customize_btns = {}
+    predefined_btns = {}
+    with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
+        gr.HTML(title_html)
+        gr.HTML('''<center><a href="https://huggingface.co/spaces/qingxu98/gpt-academic?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>请您打开此页面后务必点击上方的“复制空间”（Duplicate Space）按钮！<font color="#FF00FF">使用时，先在输入框填入API-KEY然后回车。</font><br/>切忌在“复制空间”（Duplicate Space）之前填入API_KEY或进行提问，否则您的API_KEY将极可能被空间所有者攫取！<br/>支持任意数量的OpenAI的密钥和API2D的密钥共存，例如输入"OpenAI密钥1,API2D密钥2"，然后提交，即可同时使用两种模型接口。</center>''')
+        secret_css, dark_mode, py_pickle_cookie = gr.Textbox(visible=False), gr.Textbox(DARK_MODE, visible=False), gr.Textbox(visible=False)
+        cookies = gr.State(load_chat_cookies())
+        with gr_L1():
+            with gr_L2(scale=2, elem_id="gpt-chat"):
+                chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
+                if LAYOUT == "TOP-DOWN":  chatbot.style(height=CHATBOT_HEIGHT)
+                history = gr.State([])
+            with gr_L2(scale=1, elem_id="gpt-panel"):
+                with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
+                    with gr.Row():
+                        txt = gr.Textbox(show_label=False, lines=2, placeholder="输入问题或API密钥，输入多个密钥时，用英文逗号间隔。支持多个OpenAI密钥共存。").style(container=False)
+                    with gr.Row():
+                        submitBtn = gr.Button("提交", elem_id="elem_submit", variant="primary")
+                    with gr.Row():
+                        resetBtn = gr.Button("重置", elem_id="elem_reset", variant="secondary"); resetBtn.style(size="sm")
+                        stopBtn = gr.Button("停止", elem_id="elem_stop", variant="secondary"); stopBtn.style(size="sm")
+                        clearBtn = gr.Button("清除", elem_id="elem_clear", variant="secondary", visible=False); clearBtn.style(size="sm")
+                    if ENABLE_AUDIO:
+                        with gr.Row():
+                            audio_mic = gr.Audio(source="microphone", type="numpy", elem_id="elem_audio", streaming=True, show_label=False).style(container=False)
+                    with gr.Row():
+                        status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel")
+
+                with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
+                    with gr.Row():
+                        for k in range(NUM_CUSTOM_BASIC_BTN):
+                            customize_btn = gr.Button("自定义按钮" + str(k+1), visible=False, variant="secondary", info_str=f'基础功能区: 自定义按钮')
+                            customize_btn.style(size="sm")
+                            customize_btns.update({"自定义按钮" + str(k+1): customize_btn})
+                        for k in functional:
+                            if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
+                            variant = functional[k]["Color"] if "Color" in functional[k] else "secondary"
+                            functional[k]["Button"] = gr.Button(k, variant=variant, info_str=f'基础功能区: {k}')
+                            functional[k]["Button"].style(size="sm")
+                            predefined_btns.update({k: functional[k]["Button"]})
+                with gr.Accordion("函数插件区", open=True, elem_id="plugin-panel") as area_crazy_fn:
+                    with gr.Row():
+                        gr.Markdown("插件可读取“输入区”文本/路径作为参数（上传文件自动修正路径）")
+                    with gr.Row(elem_id="input-plugin-group"):
+                        plugin_group_sel = gr.Dropdown(choices=all_plugin_groups, label='', show_label=False, value=DEFAULT_FN_GROUPS,
+                                                      multiselect=True, interactive=True, elem_classes='normal_mut_select').style(container=False)
+                    with gr.Row():
+                        for k, plugin in plugins.items():
+                            if not plugin.get("AsButton", True): continue
+                            visible = True if match_group(plugin['Group'], DEFAULT_FN_GROUPS) else False
+                            variant = plugins[k]["Color"] if "Color" in plugin else "secondary"
+                            info = plugins[k].get("Info", k)
+                            plugin['Button'] = plugins[k]['Button'] = gr.Button(k, variant=variant,
+                                visible=visible, info_str=f'函数插件区: {info}').style(size="sm")
+                    with gr.Row():
+                        with gr.Accordion("更多函数插件", open=True):
+                            dropdown_fn_list = []
+                            for k, plugin in plugins.items():
+                                if not match_group(plugin['Group'], DEFAULT_FN_GROUPS): continue
+                                if not plugin.get("AsButton", True): dropdown_fn_list.append(k)     # 排除已经是按钮的插件
+                                elif plugin.get('AdvancedArgs', False): dropdown_fn_list.append(k)  # 对于需要高级参数的插件，亦在下拉菜单中显示
+                            with gr.Row():
+                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="", show_label=False).style(container=False)
+                            with gr.Row():
+                                plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False,
+                                                                 placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
+                            with gr.Row():
+                                switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary").style(size="sm")
+                    with gr.Row():
+                        with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
+                            file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
+
+        with gr.Floating(init_x="0%", init_y="0%", visible=True, width=None, drag="forbidden", elem_id="tooltip"):
+            with gr.Row():
+                with gr.Tab("上传文件", elem_id="interact-panel"):
+                    gr.Markdown("请上传本地文件/压缩包供“函数插件区”功能调用。请注意: 上传文件后会自动把输入区修改为相应路径。")
+                    file_upload_2 = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload_float")
+
+                with gr.Tab("更换模型", elem_id="interact-panel"):
+                    md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
+                    top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
+                    temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
+                    max_length_sl = gr.Slider(minimum=256, maximum=1024*32, value=4096, step=128, interactive=True, label="Local LLM MaxLength",)
+                    system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt", label="System prompt", value=INIT_SYS_PROMPT)
+
+                with gr.Tab("界面外观", elem_id="interact-panel"):
+                    theme_dropdown = gr.Dropdown(AVAIL_THEMES, value=THEME, label="更换UI主题").style(container=False)
+                    checkboxes = gr.CheckboxGroup(["基础功能区", "函数插件区", "浮动输入区", "输入清除键", "插件参数区"], value=["基础功能区", "函数插件区"], label="显示/隐藏功能区", elem_id='cbs').style(container=False)
+                    opt = ["自定义菜单"]
+                    value=[]
+                    if ADD_WAIFU: opt += ["添加Live2D形象"]; value += ["添加Live2D形象"]
+                    checkboxes_2 = gr.CheckboxGroup(opt, value=value, label="显示/隐藏自定义菜单", elem_id='cbsc').style(container=False)
+                    dark_mode_btn = gr.Button("切换界面明暗 ☀", variant="secondary").style(size="sm")
+                    dark_mode_btn.click(None, None, None, _js=js_code_for_toggle_darkmode)
+                with gr.Tab("帮助", elem_id="interact-panel"):
+                    gr.Markdown(help_menu_description)
+
+        with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_input_secondary:
+            with gr.Accordion("浮动输入区", open=True, elem_id="input-panel2"):
+                with gr.Row() as row:
+                    row.style(equal_height=True)
+                    with gr.Column(scale=10):
+                        txt2 = gr.Textbox(show_label=False, placeholder="Input question here.",
+                                          elem_id='user_input_float', lines=8, label="输入区2").style(container=False)
+                    with gr.Column(scale=1, min_width=40):
+                        submitBtn2 = gr.Button("提交", variant="primary"); submitBtn2.style(size="sm")
+                        resetBtn2 = gr.Button("重置", variant="secondary"); resetBtn2.style(size="sm")
+                        stopBtn2 = gr.Button("停止", variant="secondary"); stopBtn2.style(size="sm")
+                        clearBtn2 = gr.Button("清除", elem_id="elem_clear2", variant="secondary", visible=False); clearBtn2.style(size="sm")
+
+
+        with gr.Floating(init_x="20%", init_y="50%", visible=False, width="40%", drag="top") as area_customize:
+            with gr.Accordion("自定义菜单", open=True, elem_id="edit-panel"):
+                with gr.Row() as row:
+                    with gr.Column(scale=10):
+                        AVAIL_BTN = [btn for btn in customize_btns.keys()] + [k for k in functional]
+                        basic_btn_dropdown = gr.Dropdown(AVAIL_BTN, value="自定义按钮1", label="选择一个需要自定义基础功能区按钮").style(container=False)
+                        basic_fn_title = gr.Textbox(show_label=False, placeholder="输入新按钮名称", lines=1).style(container=False)
+                        basic_fn_prefix = gr.Textbox(show_label=False, placeholder="输入新提示前缀", lines=4).style(container=False)
+                        basic_fn_suffix = gr.Textbox(show_label=False, placeholder="输入新提示后缀", lines=4).style(container=False)
+                    with gr.Column(scale=1, min_width=70):
+                        basic_fn_confirm = gr.Button("确认并保存", variant="primary"); basic_fn_confirm.style(size="sm")
+                        basic_fn_clean   = gr.Button("恢复默认", variant="primary"); basic_fn_clean.style(size="sm")
+                        def assign_btn(persistent_cookie_, cookies_, basic_btn_dropdown_, basic_fn_title, basic_fn_prefix, basic_fn_suffix, clean_up=False):
+                            ret = {}
+                            # 读取之前的自定义按钮
+                            customize_fn_overwrite_ = cookies_['customize_fn_overwrite']
+                            # 更新新的自定义按钮
+                            customize_fn_overwrite_.update({
+                                basic_btn_dropdown_:
+                                    {
+                                        "Title":basic_fn_title,
+                                        "Prefix":basic_fn_prefix,
+                                        "Suffix":basic_fn_suffix,
+                                    }
+                                }
+                            )
+                            if clean_up:
+                                customize_fn_overwrite_ = {}
+                            cookies_.update(customize_fn_overwrite_)    # 更新cookie
+                            visible = (not clean_up) and (basic_fn_title != "")
+                            if basic_btn_dropdown_ in customize_btns:
+                                # 是自定义按钮，不是预定义按钮
+                                ret.update({customize_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
+                            else:
+                                # 是预定义按钮
+                                ret.update({predefined_btns[basic_btn_dropdown_]: gr.update(visible=visible, value=basic_fn_title)})
+                            ret.update({cookies: cookies_})
+                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)   # persistent cookie to dict
+                            except: persistent_cookie_ = {}
+                            persistent_cookie_["custom_bnt"] = customize_fn_overwrite_      # dict update new value
+                            persistent_cookie_ = to_cookie_str(persistent_cookie_)          # persistent cookie to dict
+                            ret.update({py_pickle_cookie: persistent_cookie_})             # write persistent cookie
+                            return ret
+
+                        # update btn
+                        h = basic_fn_confirm.click(assign_btn, [py_pickle_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix],
+                                                   [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
+                        h.then(None, [py_pickle_cookie], None, _js="""(py_pickle_cookie)=>{setCookie("py_pickle_cookie", py_pickle_cookie, 365);}""")
+                        # clean up btn
+                        h2 = basic_fn_clean.click(assign_btn, [py_pickle_cookie, cookies, basic_btn_dropdown, basic_fn_title, basic_fn_prefix, basic_fn_suffix, gr.State(True)],
+                                                   [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()])
+                        h2.then(None, [py_pickle_cookie], None, _js="""(py_pickle_cookie)=>{setCookie("py_pickle_cookie", py_pickle_cookie, 365);}""")
+
+                        def persistent_cookie_reload(persistent_cookie_, cookies_):
+                            ret = {}
+                            for k in customize_btns:
+                                ret.update({customize_btns[k]: gr.update(visible=False, value="")})
+
+                            try: persistent_cookie_ = from_cookie_str(persistent_cookie_)    # persistent cookie to dict
+                            except: return ret
+
+                            customize_fn_overwrite_ = persistent_cookie_.get("custom_bnt", {})
+                            cookies_['customize_fn_overwrite'] = customize_fn_overwrite_
+                            ret.update({cookies: cookies_})
+
+                            for k,v in persistent_cookie_["custom_bnt"].items():
+                                if v['Title'] == "": continue
+                                if k in customize_btns: ret.update({customize_btns[k]: gr.update(visible=True, value=v['Title'])})
+                                else: ret.update({predefined_btns[k]: gr.update(visible=True, value=v['Title'])})
+                            return ret
+
+        # 功能区显示开关与功能区的互动
+        def fn_area_visibility(a):
+            ret = {}
+            ret.update({area_input_primary: gr.update(visible=("浮动输入区" not in a))})
+            ret.update({area_input_secondary: gr.update(visible=("浮动输入区" in a))})
+            ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
+            if "浮动输入区" in a: ret.update({txt: gr.update(value="")})
+            return ret
+        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, plugin_advanced_arg] )
+        checkboxes.select(None, [checkboxes], None, _js=js_code_show_or_hide)
+
+        # 功能区显示开关与功能区的互动
+        def fn_area_visibility_2(a):
+            ret = {}
+            ret.update({area_customize: gr.update(visible=("自定义菜单" in a))})
+            return ret
+        checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] )
+        checkboxes_2.select(None, [checkboxes_2], None, _js=js_code_show_or_hide_group2)
+
+        # 整理反复出现的控件句柄组合
+        input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
+        output_combo = [cookies, chatbot, history, status]
+        predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True)], outputs=output_combo)
+        # 提交按钮、重置按钮
+        cancel_handles.append(txt.submit(**predict_args))
+        cancel_handles.append(txt2.submit(**predict_args))
+        cancel_handles.append(submitBtn.click(**predict_args))
+        cancel_handles.append(submitBtn2.click(**predict_args))
+        resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset)   # 先在前端快速清除chatbot&status
+        resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset)  # 先在前端快速清除chatbot&status
+        resetBtn.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])    # 再在后端清除history
+        resetBtn2.click(lambda: ([], [], "已重置"), None, [chatbot, history, status])   # 再在后端清除history
+        clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
+        clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
+        if AUTO_CLEAR_TXT:
+            submitBtn.click(None, None, [txt, txt2], _js=js_code_clear)
+            submitBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
+            txt.submit(None, None, [txt, txt2], _js=js_code_clear)
+            txt2.submit(None, None, [txt, txt2], _js=js_code_clear)
+        # 基础功能区的回调函数注册
+        for k in functional:
+            if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
+            click_handle = functional[k]["Button"].click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(k)], outputs=output_combo)
+            cancel_handles.append(click_handle)
+        for btn in customize_btns.values():
+            click_handle = btn.click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(btn.value)], outputs=output_combo)
+            cancel_handles.append(click_handle)
+        # 文件上传区，接收文件后与chatbot的互动
+        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None,   _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
+        file_upload_2.upload(on_file_uploaded, [file_upload_2, chatbot, txt, txt2, checkboxes, cookies], [chatbot, txt, txt2, cookies]).then(None, None, None, _js=r"()=>{toast_push('上传完毕 ...'); cancel_loading_status();}")
+        # 函数插件-固定按钮区
+        for k in plugins:
+            if not plugins[k].get("AsButton", True): continue
+            click_handle = plugins[k]["Button"].click(ArgsGeneralWrapper(plugins[k]["Function"]), [*input_combo], output_combo)
+            click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+            cancel_handles.append(click_handle)
+        # 函数插件-下拉菜单与随变按钮的互动
+        def on_dropdown_changed(k):
+            variant = plugins[k]["Color"] if "Color" in plugins[k] else "secondary"
+            info = plugins[k].get("Info", k)
+            ret = {switchy_bt: gr.update(value=k, variant=variant, info_str=f'函数插件区: {info}')}
+            if plugins[k].get("AdvancedArgs", False): # 是否唤起高级插件参数区
+                ret.update({plugin_advanced_arg: gr.update(visible=True,  label=f"插件[{k}]的高级参数说明：" + plugins[k].get("ArgsReminder", [f"没有提供高级参数功能说明"]))})
+            else:
+                ret.update({plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
+            return ret
+        dropdown.select(on_dropdown_changed, [dropdown], [switchy_bt, plugin_advanced_arg] )
+
+        def on_md_dropdown_changed(k):
+            return {chatbot: gr.update(label="当前模型："+k)}
+        md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
+
+        def on_theme_dropdown_changed(theme, secret_css):
+            adjust_theme, css_part1, _, adjust_dynamic_theme = load_dynamic_theme(theme)
+            if adjust_dynamic_theme:
+                css_part2 = adjust_dynamic_theme._get_theme_css()
+            else:
+                css_part2 = adjust_theme()._get_theme_css()
+            return css_part2 + css_part1
+
+        theme_handle = theme_dropdown.select(on_theme_dropdown_changed, [theme_dropdown, secret_css], [secret_css])
+        theme_handle.then(
+            None,
+            [secret_css],
+            None,
+            _js=js_code_for_css_changing
+        )
+        # 随变按钮的回调函数注册
+        def route(request: gr.Request, k, *args, **kwargs):
+            if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
+            yield from ArgsGeneralWrapper(plugins[k]["Function"])(request, *args, **kwargs)
+        click_handle = switchy_bt.click(route,[switchy_bt, *input_combo], output_combo)
+        click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
+        cancel_handles.append(click_handle)
+        # 终止按钮的回调函数注册
+        stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
+        stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
+        plugins_as_btn = {name:plugin for name, plugin in plugins.items() if plugin.get('Button', None)}
+        def on_group_change(group_list):
+            btn_list = []
+            fns_list = []
+            if not group_list: # 处理特殊情况：没有选择任何插件组
+                return [*[plugin['Button'].update(visible=False) for _, plugin in plugins_as_btn.items()], gr.Dropdown.update(choices=[])]
+            for k, plugin in plugins.items():
+                if plugin.get("AsButton", True):
+                    btn_list.append(plugin['Button'].update(visible=match_group(plugin['Group'], group_list))) # 刷新按钮
+                    if plugin.get('AdvancedArgs', False): dropdown_fn_list.append(k) # 对于需要高级参数的插件，亦在下拉菜单中显示
+                elif match_group(plugin['Group'], group_list): fns_list.append(k) # 刷新下拉列表
+            return [*btn_list, gr.Dropdown.update(choices=fns_list)]
+        plugin_group_sel.select(fn=on_group_change, inputs=[plugin_group_sel], outputs=[*[plugin['Button'] for name, plugin in plugins_as_btn.items()], dropdown])
+        if ENABLE_AUDIO:
+            from crazy_functions.live_audio.audio_io import RealtimeAudioDistribution
+            rad = RealtimeAudioDistribution()
+            def deal_audio(audio, cookies):
+                rad.feed(cookies['uuid'].hex, audio)
+            audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
+
+
+        demo.load(init_cookie, inputs=[cookies], outputs=[cookies])
+        demo.load(persistent_cookie_reload, inputs = [py_pickle_cookie, cookies],
+            outputs = [py_pickle_cookie, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
+        demo.load(None, inputs=[dark_mode], outputs=None, _js="""(dark_mode)=>{apply_cookie_for_checkbox(dark_mode);}""")    # 配置暗色主题或亮色主题
+        demo.load(None, inputs=[gr.Textbox(LAYOUT, visible=False)], outputs=None, _js='(LAYOUT)=>{GptAcademicJavaScriptInit(LAYOUT);}')
+
+    # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
+    def run_delayed_tasks():
+        import threading, webbrowser, time
+        print(f"如果浏览器没有自动打开，请复制并转到以下URL：")
+        if DARK_MODE:   print(f"\t「暗色主题已启用（支持动态切换主题）」: http://localhost:{PORT}")
+        else:           print(f"\t「亮色主题已启用（支持动态切换主题）」: http://localhost:{PORT}")
+
+        def auto_updates(): time.sleep(0); auto_update()
+        def open_browser(): time.sleep(2); webbrowser.open_new_tab(f"http://localhost:{PORT}")
+        def warm_up_mods(): time.sleep(6); warm_up_modules()
+
+        threading.Thread(target=auto_updates, name="self-upgrade", daemon=True).start() # 查看自动更新
+        threading.Thread(target=open_browser, name="open-browser", daemon=True).start() # 打开浏览器页面
+        threading.Thread(target=warm_up_mods, name="warm-up", daemon=True).start()      # 预热tiktoken模块
+
+    run_delayed_tasks()
+    demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", share=False, favicon_path="docs/logo.png", blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile"])
+
+
+    # 如果需要在二级路径下运行
+    # CUSTOM_PATH = get_conf('CUSTOM_PATH')
+    # if CUSTOM_PATH != "/":
+    #     from toolbox import run_gradio_in_subpath
+    #     run_gradio_in_subpath(demo, auth=AUTHENTICATION, port=PORT, custom_path=CUSTOM_PATH)
+    # else:
+    #     demo.launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION, favicon_path="docs/logo.png",
+    #                 blocked_paths=["config.py","config_private.py","docker-compose.yml","Dockerfile",f"{PATH_LOGGING}/admin"])
+
+if __name__ == "__main__":
+    main()

check_proxy.py

@@ -3,15 +3,19 @@ def check_proxy(proxies):
     import requests
     proxies_https = proxies['https'] if proxies is not None else '无'
     try:
-        response = requests.get("https://ipapi.co/json/",
-                                proxies=proxies, timeout=4)
+        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}"
         elif 'error' in data:
-            result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
+            alternative = _check_with_backup_source(proxies)
+            if alternative is None:
+                result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
+            else:
+                result = f"代理配置 {proxies_https}, 代理所在地：{alternative}"
+        else:
+            result = f"代理配置 {proxies_https}, 代理数据解析失败：{data}"
         print(result)
         return result
     except:
@@ -19,6 +23,11 @@ def check_proxy(proxies):
         print(result)
         return result
 
+def _check_with_backup_source(proxies):
+    import random, string, requests
+    random_string = ''.join(random.choices(string.ascii_letters + string.digits, k=32))
+    try: return requests.get(f"http://{random_string}.edns.ip-api.com/json", proxies=proxies, timeout=4).json()['dns']['geo']
+    except: return None
 
 def backup_and_download(current_version, remote_version):
     """
@@ -36,9 +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.gpt-academic.top/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)
@@ -56,22 +65,24 @@ def patch_and_restart(path):
     """
     一键更新协议：覆盖和重启
     """
-    import distutils
+    from distutils import dir_util
     import shutil
     import os
     import sys
     import time
+    import glob
     from colorful import print亮黄, print亮绿, print亮红
     # if not using config_private, move origin config.py as config_private.py
     if not os.path.exists('config_private.py'):
         print亮黄('由于您没有设置config_private.py私密配置，现将您的现有配置移动至config_private.py以防止配置丢失，',
               '另外您可以随时在history子文件夹下找回旧版的程序。')
         shutil.copyfile('config.py', 'config_private.py')
-    distutils.dir_util.copy_tree(path+'/chatgpt_academic-master', './')
-    import subprocess
+    path_new_version = glob.glob(path + '/*-master')[0]
+    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: 
+        import subprocess
         subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
     except:
         print亮红('pip包依赖安装出现问题，需要手动安装新增的依赖库 `python -m pip install -r requirements.txt`，然后在用常规的`python main.py`的方式启动。')
@@ -92,18 +103,17 @@ def get_current_version():
     return current_version
 
 
-def auto_update():
+def auto_update(raise_error=False):
     """
     一键更新协议：查询版本和用户意见
     """
     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.gpt-academic.top/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"]:
@@ -113,10 +123,9 @@ def auto_update():
         with open('./version', 'r', encoding='utf8') as f:
             current_version = f.read()
             current_version = json.loads(current_version)['version']
-        if (remote_version - current_version) >= 0.01:
+        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']:
@@ -124,26 +133,44 @@ def auto_update():
                 try:
                     patch_and_restart(path)
                 except:
-                    print('更新失败。')
+                    msg = '更新失败。'
+                    if raise_error:
+                        from toolbox import trimmed_format_exc
+                        msg += trimmed_format_exc()
+                    print(msg)
             else:
                 print('自动更新程序：已禁用')
                 return
         else:
             return
     except:
-        print('自动更新程序：已禁用')
+        msg = '自动更新程序：已禁用。建议排查：代理网络配置。'
+        if raise_error:
+            from toolbox import trimmed_format_exc
+            msg += trimmed_format_exc()
+        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

@@ -34,58 +34,28 @@ def print亮紫(*kw,**kargs):
 def print亮靛(*kw,**kargs):
     print("\033[1;36m",*kw,"\033[0m",**kargs)
 
-
-
-def print亮红(*kw,**kargs):
-    print("\033[1;31m",*kw,"\033[0m",**kargs)
-def print亮绿(*kw,**kargs):
-    print("\033[1;32m",*kw,"\033[0m",**kargs)
-def print亮黄(*kw,**kargs):
-    print("\033[1;33m",*kw,"\033[0m",**kargs)
-def print亮蓝(*kw,**kargs):
-    print("\033[1;34m",*kw,"\033[0m",**kargs)
-def print亮紫(*kw,**kargs):
-    print("\033[1;35m",*kw,"\033[0m",**kargs)
-def print亮靛(*kw,**kargs):
-    print("\033[1;36m",*kw,"\033[0m",**kargs)
-    
-print_red = print红
-print_green = print绿
-print_yellow = print黄
-print_blue = print蓝
-print_purple = print紫
-print_indigo = print靛
-
-print_bold_red = print亮红
-print_bold_green = print亮绿
-print_bold_yellow = print亮黄
-print_bold_blue = print亮蓝
-print_bold_purple = print亮紫
-print_bold_indigo = print亮靛
-    
-if not stdout.isatty():
-    # redirection, avoid a fucked up log file
-    print红 = print
-    print绿 = print
-    print黄 = print
-    print蓝 = print
-    print紫 = print
-    print靛 = print
-    print亮红 = print
-    print亮绿 = print
-    print亮黄 = print
-    print亮蓝 = print
-    print亮紫 = print
-    print亮靛 = print
-    print_red = print
-    print_green = print
-    print_yellow = print
-    print_blue = print
-    print_purple = print
-    print_indigo = print
-    print_bold_red = print
-    print_bold_green = print
-    print_bold_yellow = print
-    print_bold_blue = print
-    print_bold_purple = print
-    print_bold_indigo = print
+# Do you like the elegance of Chinese characters?
+def sprint红(*kw):
+    return "\033[0;31m"+' '.join(kw)+"\033[0m"
+def sprint绿(*kw):
+    return "\033[0;32m"+' '.join(kw)+"\033[0m"
+def sprint黄(*kw):
+    return "\033[0;33m"+' '.join(kw)+"\033[0m"
+def sprint蓝(*kw):
+    return "\033[0;34m"+' '.join(kw)+"\033[0m"
+def sprint紫(*kw):
+    return "\033[0;35m"+' '.join(kw)+"\033[0m"
+def sprint靛(*kw):
+    return "\033[0;36m"+' '.join(kw)+"\033[0m"
+def sprint亮红(*kw):
+    return "\033[1;31m"+' '.join(kw)+"\033[0m"
+def sprint亮绿(*kw):
+    return "\033[1;32m"+' '.join(kw)+"\033[0m"
+def sprint亮黄(*kw):
+    return "\033[1;33m"+' '.join(kw)+"\033[0m"
+def sprint亮蓝(*kw):
+    return "\033[1;34m"+' '.join(kw)+"\033[0m"
+def sprint亮紫(*kw):
+    return "\033[1;35m"+' '.join(kw)+"\033[0m"
+def sprint亮靛(*kw):
+    return "\033[1;36m"+' '.join(kw)+"\033[0m"

config.py

@@ -1,71 +1,370 @@
-# [step 1]>> 例如： API_KEY = "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" （此key无效）
-API_KEY = "sk-此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
+"""
+    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.
+    Configuration reading priority: environment variable > config_private.py > config.py
+"""
 
-# [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改
+# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
+API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
+
+
+# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
+API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
+
+
+# [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改；如果使用本地或无地域限制的大模型时，此处也不需要修改
 USE_PROXY = False
 if USE_PROXY:
-    # 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
-    # 例如    "socks5h://localhost:11284"
-    # [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）
-    # [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，打开你的科学上网软件查看代理的协议(socks5/http)、地址(localhost)和端口(11284)
+    """
+    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] 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
+    """
     proxies = {
         #          [协议]://  [地址]  :[端口]
-        "http":  "socks5h://localhost:11284",
-        "https": "socks5h://localhost:11284",
+        "http":  "socks5h://localhost:11284",  # 再例如  "http":  "http://127.0.0.1:7890",
+        "https": "socks5h://localhost:11284",  # 再例如  "https": "http://127.0.0.1:7890",
     }
 else:
     proxies = None
 
-# [step 3]>> 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
-# 一言以蔽之：免费用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
+# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
+
+# 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"}
+API_URL_REDIRECT = {}
+
+
+# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
+# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
 DEFAULT_WORKER_NUM = 3
 
 
-# [step 4]>> 以下配置可以优化体验，但大部分场合下并不需要修改
-# 对话窗的高度
+# 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
+# 更多主题, 请查阅Gradio主题商店: https://huggingface.co/spaces/gradio/theme-gallery 可选 ["Gstaff/Xkcd", "NoCrypt/Miku", ...]
+THEME = "Chuanhu-Small-and-Beautiful"
+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
 
+
 # 代码高亮
 CODE_HIGHLIGHT = True
 
+
 # 窗口布局
-LAYOUT = "LEFT-RIGHT"  # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
+LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
+
+
+# 暗色模式 / 亮色模式
+DARK_MODE = False
+
 
 # 发送请求到OpenAI后，等待多久判定为超时
 TIMEOUT_SECONDS = 30
 
+
 # 网页的端口, -1代表随机端口
 WEB_PORT = -1
 
+
 # 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
 MAX_RETRY = 2
 
-# OpenAI模型选择是（gpt4现在只对申请成功的人开放，体验gpt-4可以试试api2d）
-LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing"]
+# OpenAI模型选择是（gpt4现在只对申请成功的人开放）
+LLM_MODEL = "gpt-3.5-turbo" # 可选 "chatglm"
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "api2d-gpt-3.5-turbo", "spark", "azure-gpt-3.5"]
+
+# 插件分类默认选项
+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-16k" # 可选 ↓↓↓
+AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
+                    "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-3-turbo",
+                    "gemini-pro", "chatglm3", "claude-2"]
+# P.S. 其他可用的模型还包括 [
+# "moss", "qwen-turbo", "qwen-plus", "qwen-max"
+# "zhipuai", "qianfan", "deepseekcoder", "llama2", "qwen-local", "gpt-3.5-turbo-0613",
+# "gpt-3.5-turbo-16k-0613",  "gpt-3.5-random", "api2d-gpt-3.5-turbo", 'api2d-gpt-3.5-turbo-16k',
+# "spark", "sparkv2", "sparkv3", "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-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
+CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
+
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
+LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
 
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100
 
+
+# 是否在提交时自动清空输入框
+AUTO_CLEAR_TXT = False
+
+
+# 加一个live2d装饰
+ADD_WAIFU = True
+
+
 # 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
 # [("username", "password"), ("username2", "password2"), ...]
 AUTHENTICATION = []
 
-# 重新URL重新定向，实现更换API_URL的作用（常规情况下，不要修改!!）
-# 格式 {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
-API_URL_REDIRECT = {}
 
 # 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!）
 CUSTOM_PATH = "/"
 
-# 如果需要使用newbing，把newbing的长长的cookie放到这里
+
+# 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_llms/README.md
+SLACK_CLAUDE_BOT_ID = ''
+SLACK_CLAUDE_USER_TOKEN = ''
+
+
+# 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
+
+
+# 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 = {}
+
+
+# 使用Newbing (不推荐使用，未来将删除)
 NEWBING_STYLE = "creative"  # ["creative", "balanced", "precise"]
 NEWBING_COOKIES = """
-your bing cookies here
+put your new bing cookies here
+"""
+
+
+# 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
+ENABLE_AUDIO = False
+ALIYUN_TOKEN=""     # 例如 f37f30e0f9934c34a992f6f64f7eba4f
+ALIYUN_APPKEY=""    # 例如 RoPlZrM88DnAFkZK
+ALIYUN_ACCESSKEY="" # （无需填写）
+ALIYUN_SECRET=""    # （无需填写）
+
+
+# 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
+
+
+# # 火山引擎YUNQUE大模型
+# YUNQUE_SECRET_KEY = ""
+# YUNQUE_ACCESS_KEY = ""
+# YUNQUE_MODEL = ""
+
+
+# Claude API KEY
+ANTHROPIC_API_KEY = ""
+
+
+# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
+MATHPIX_APPID = ""
+MATHPIX_APPKEY = ""
+
+
+# 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 = ""
+
+
+# GROBID服务器地址（填写多个可以均衡负载），用于高质量地读取PDF文档
+# 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://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",
+                     "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
+
+"""
+在线大模型配置关联关系示意图
+│
+├── "gpt-3.5-turbo" 等openai模型
+│   ├── API_KEY
+│   ├── CUSTOM_API_KEY_PATTERN（不常用）
+│   ├── API_ORG（不常用）
+│   └── API_URL_REDIRECT（不常用）
+│
+├── "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
+│   └── ANTHROPIC_API_KEY
+│
+├── "stack-claude"
+│   ├── SLACK_CLAUDE_BOT_ID
+│   └── SLACK_CLAUDE_USER_TOKEN
+│
+├── "qianfan" 百度千帆大模型库
+│   ├── BAIDU_CLOUD_QIANFAN_MODEL
+│   ├── BAIDU_CLOUD_API_KEY
+│   └── BAIDU_CLOUD_SECRET_KEY
+│
+├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
+│   └── ZHIPUAI_API_KEY
+│
+├── "qwen-turbo" 等通义千问大模型
+│   └──  DASHSCOPE_API_KEY
+│
+├── "Gemini"
+│   └──  GEMINI_API_KEY
+│
+└── "newbing" Newbing接口不再稳定，不推荐使用
+    ├── NEWBING_STYLE
+    └── NEWBING_COOKIES
+
+
+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
+├── CODE_HIGHLIGHT 代码高亮
+├── LAYOUT 窗口布局
+├── DARK_MODE 暗色模式 / 亮色模式
+├── DEFAULT_FN_GROUPS 插件分类默认选项
+├── 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
+
+
+插件在线服务配置依赖关系示意图
+│
+├── 语音功能
+│   ├── ENABLE_AUDIO
+│   ├── ALIYUN_TOKEN
+│   ├── ALIYUN_APPKEY
+│   ├── ALIYUN_ACCESSKEY
+│   └── ALIYUN_SECRET
+│
+└── PDF文档精准解析
+    ├── GROBID_URLS
+    ├── MATHPIX_APPID
+    └── MATHPIX_APPKEY
+
+
 """

core_functional.py

@@ -1,71 +1,173 @@
 # 'primary' 颜色对应 theme.py 中的 primary_hue
 # 'secondary' 颜色对应 theme.py 中的 neutral_hue
 # 'stop' 颜色对应 theme.py 中的 color_er
-# 默认按钮颜色是 secondary
+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": {
-            # 前言
-            "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"Furthermore, list all modification and explain the reasons to do so in markdown table." + "\n\n",
-            # 后语
+
+        "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"",
-            "Color":    r"secondary",    # 按钮颜色
+            # [3] 按钮颜色 (可选参数，默认 secondary)
+            "Color":    r"secondary",
+            # [4] 按钮是否可见 (可选参数，默认 True，即可见)
+            "Visible": True,
+            # [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":   r"",
+            # 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"+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"]
+                    ```
+
+                    警告：
+                    （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"Can you 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." +
-                        r"If you find grammar or spelling mistakes, please list mistakes you find in a two-column markdown table, " +
-                        r"put the original text the first column, " +
-                        r"put the corrected text in the second column and highlight the key words you fixed.""\n"
+            "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. "
+                        r"If you find grammar or spelling mistakes, please list mistakes you find in a two-column markdown table, "
+                        r"put the original text the first column, "
+                        r"put the corrected text in the second column and highlight the key words you fixed. "
+                        r"Finally, please provide the proofreaded text.""\n\n"
                         r"Example:""\n"
                         r"Paragraph: How is you? Do you knows what is it?""\n"
                         r"| Original sentence | Corrected sentence |""\n"
                         r"| :--- | :--- |""\n"
                         r"| How **is** you? | How **are** you? |""\n"
-                        r"| Do you **knows** what **is** **it**? | Do you **know** what **it** **is** ? |""\n"
+                        r"| Do you **knows** what **is** **it**? | Do you **know** what **it** **is** ? |""\n\n"
                         r"Below is a paragraph from an academic paper. "
                         r"You need to report all grammar and spelling mistakes as the example before."
                         + "\n\n",
             "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,
         },
+        
+        
         "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,
         },
+        
+        
         "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:" + "\n\n",
+            "Visible":  False,
+            "Suffix":   r"",
+        }
     }
+
+
+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()
+    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

@@ -1,19 +1,20 @@
 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():
-    ###################### 第一组插件 ###########################
     from crazy_functions.读文章写摘要 import 读文章写摘要
     from crazy_functions.生成函数注释 import 批量生成函数注释
     from crazy_functions.解析项目源代码 import 解析项目本身
     from crazy_functions.解析项目源代码 import 解析一个Python项目
+    from crazy_functions.解析项目源代码 import 解析一个Matlab项目
     from crazy_functions.解析项目源代码 import 解析一个C项目的头文件
     from crazy_functions.解析项目源代码 import 解析一个C项目
     from crazy_functions.解析项目源代码 import 解析一个Golang项目
+    from crazy_functions.解析项目源代码 import 解析一个Rust项目
     from crazy_functions.解析项目源代码 import 解析一个Java项目
-    from crazy_functions.解析项目源代码 import 解析一个Rect项目
+    from crazy_functions.解析项目源代码 import 解析一个前端项目
     from crazy_functions.高级功能函数模板 import 高阶功能模板函数
-    from crazy_functions.代码重写为全英文_多线程 import 全项目切换英文
     from crazy_functions.Latex全文润色 import Latex英文润色
     from crazy_functions.询问多个大语言模型 import 同时问询
     from crazy_functions.解析项目源代码 import 解析一个Lua项目
@@ -21,209 +22,702 @@ def get_crazy_functions():
     from crazy_functions.总结word文档 import 总结word文档
     from crazy_functions.解析JupyterNotebook import 解析ipynb文件
     from crazy_functions.对话历史存档 import 对话历史存档
+    from crazy_functions.对话历史存档 import 载入对话历史存档
+    from crazy_functions.对话历史存档 import 删除所有本地对话历史记录
+    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
-    function_plugins = {
-
-        "解析整个Python项目": {
-            "Color": "stop",    # 按钮颜色
-            "Function": HotReload(解析一个Python项目)
-        },
-        "保存当前的对话": {
-            "AsButton":False,
-            "Function": HotReload(对话历史存档)
-        },
-        "[测试功能] 解析Jupyter Notebook文件": {
-            "Color": "stop",
-            "AsButton":False,
-            "Function": HotReload(解析ipynb文件),
-            "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-            "ArgsReminder": "若输入0，则不解析notebook中的Markdown块", # 高级参数输入区的显示提示
-        },
-        "批量总结Word文档": {
-            "Color": "stop",
-            "Function": HotReload(总结word文档)
-        },
-        "解析整个C++项目头文件": {
-            "Color": "stop",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个C项目的头文件)
-        },
-        "解析整个C++项目（.cpp/.hpp/.c/.h）": {
-            "Color": "stop",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个C项目)
-        },
-        "解析整个Go项目": {
-            "Color": "stop",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个Golang项目)
-        },
-        "解析整个Java项目": {
-            "Color": "stop",  # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个Java项目)
-        },
-        "解析整个React项目": {
-            "Color": "stop",  # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个Rect项目)
-        },
-        "解析整个Lua项目": {
-            "Color": "stop",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个Lua项目)
-        },
-        "解析整个CSharp项目": {
-            "Color": "stop",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(解析一个CSharp项目)
-        },
-        "读Tex论文写摘要": {
-            "Color": "stop",    # 按钮颜色
-            "Function": HotReload(读文章写摘要)
-        },
-        "Markdown/Readme英译中": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "stop",
-            "Function": HotReload(Markdown英译中)
-        },
-        "批量生成函数注释": {
-            "Color": "stop",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(批量生成函数注释)
-        },
-        "[多线程Demo] 解析此项目本身（源码自译解）": {
-            "Function": HotReload(解析项目本身)
-        },
-        "[多线程demo] 把本项目源代码切换成全英文": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(全项目切换英文)
-        },
-        "[函数插件模板Demo] 历史上的今天": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Function": HotReload(高阶功能模板函数)
-        },
-
-    }
-    ###################### 第二组插件 ###########################
-    # [第二组插件]: 经过充分测试
     from crazy_functions.批量总结PDF文档 import 批量总结PDF文档
-    from crazy_functions.批量总结PDF文档pdfminer import 批量总结PDF文档pdfminer
     from crazy_functions.批量翻译PDF文档_多线程 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全文翻译 import Latex中译英
-    from crazy_functions.Latex全文翻译 import Latex英译中
+    from crazy_functions.Latex全文润色 import Latex英文纠错
     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.update({
-        "批量翻译PDF文档（多线程）": {
+    function_plugins = {
+        "虚空终端": {
+            "Group": "对话|编程|学术|智能体",
             "Color": "stop",
-            "AsButton": True,  # 加入下拉菜单中
-            "Function": HotReload(批量翻译PDF文档)
+            "AsButton": True,
+            "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "解析Jupyter Notebook文件": {
+            "Group": "编程",
+            "Color": "stop",
+            "AsButton": False,
+            "Info": "解析Jupyter Notebook文件 | 输入参数为路径",
+            "Function": HotReload(解析ipynb文件),
+            "AdvancedArgs": True,  # 调用时，唤起高级参数输入区（默认False）
+            "ArgsReminder": "若输入0，则不解析notebook中的Markdown块",  # 高级参数输入区的显示提示
+        },
+        "读Tex论文写摘要": {
+            "Group": "学术",
+            "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "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),
+        },
+        "[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),
+        },
+        "历史上的今天": {
+            "Group": "对话",
+            "AsButton": True,
+            "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,
+            "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),
         },
         "询问多个GPT模型": {
-            "Color": "stop",    # 按钮颜色
-            "Function": HotReload(同时问询)
+            "Group": "对话",
+            "Color": "stop",
+            "AsButton": True,
+            "Function": HotReload(同时问询),
         },
-        "[测试功能] 批量总结PDF文档": {
+        "批量总结PDF文档": {
+            "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Function": HotReload(批量总结PDF文档)
-        },
-        "[测试功能] 批量总结PDF文档pdfminer": {
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(批量总结PDF文档pdfminer)
+            "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),
         },
         "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
-            "Function": HotReload(谷歌检索小助手)
+            "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),
         },
-
         "理解PDF文档内容 （模仿ChatPDF）": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
+            "Group": "学术",
             "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(理解PDF文档内容标准文件输入)
+            "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),
         },
-        "[测试功能] 英文Latex项目全文润色（输入路径或上传压缩包）": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
+        "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
-            "Function": HotReload(Latex英文润色)
-        },
-        "[测试功能] 中文Latex项目全文润色（输入路径或上传压缩包）": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(Latex中文润色)
-        },
-        "[测试功能] Latex项目全文中译英（输入路径或上传压缩包）": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(Latex中译英)
-        },
-        "[测试功能] Latex项目全文英译中（输入路径或上传压缩包）": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(Latex英译中)
-        },
-        "[测试功能] 批量Markdown中译英（输入路径或上传压缩包）": {
-            # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "stop",
-            "AsButton": False,  # 加入下拉菜单中
-            "Function": HotReload(Markdown中译英)
+            "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),
         },
 
-
-    })
-
-    ###################### 第三组插件 ###########################
-    # [第三组插件]: 尚未充分测试的函数插件，放在这里
-    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）": {
+        "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
-            "Function": HotReload(下载arxiv论文并翻译摘要)
-        }
-    })
-
-    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（先输入问题，再点击按钮，需要访问谷歌）": {
+            "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),
+        },
+        # 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
-            "Function": HotReload(连接网络回答问题)
-        }
-    })
+            "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),
+        },
+    }
+
+    # -=--=- 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),
+                }
+            }
+        )
+    except:
+        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),
+                }
+            }
+        )
+        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),
+                }
+            }
+        )
+    except:
+        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),
+                },
+            }
+        )
+    except:
+        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&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(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        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(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),
+                }
+            }
+        )
+    except:
+        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),
+                }
+            }
+        )
+    except:
+        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（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(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        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(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        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(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(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        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)
+                }
+            }
+        )
+    except:
+        print(trimmed_format_exc())
+        print("Load function plugin failed")
+
+    try:
+        from toolbox import get_conf
+
+        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(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),
+                }
+            }
+        )
+    except:
+        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),
+                }
+            }
+        )
+    except:
+        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.高级功能函数模板 import 测试图表渲染
+    #     function_plugins.update({
+    #         "绘制逻辑关系（测试图表渲染）": {
+    #             "Group": "智能体",
+    #             "Color": "stop",
+    #             "AsButton": True,
+    #             "Function": HotReload(测试图表渲染)
+    #         }
+    #     })
+    # except:
+    #     print(trimmed_format_exc())
+    #     print('Load function plugin failed')
+
+    # try:
+    #     from crazy_functions.chatglm微调工具 import 微调数据集生成
+    #     function_plugins.update({
+    #         "黑盒模型学习: 微调数据集生成 (先上传数据集)": {
+    #             "Color": "stop",
+    #             "AsButton": False,
+    #             "AdvancedArgs": True,
+    #             "ArgsReminder": "针对数据集输入（如 绿帽子*深蓝色衬衫*黑色运动裤）给出指令，例如您可以将以下命令复制到下方: --llm_to_learn=azure-gpt-3.5 --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、过去经历进行描写。要求：100字以内，用第二人称。' --system_prompt=''",
+    #             "Function": HotReload(微调数据集生成)
+    #         }
+    #     })
+    # except:
+    #     print('Load function plugin failed')
+
+    """
+    设置默认值:
+    - 默认 Group = 对话
+    - 默认 AsButton = True
+    - 默认 AdvancedArgs = False
+    - 默认 Color = secondary
+    """
+    for name, function_meta in function_plugins.items():
+        if "Group" not in function_meta:
+            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"
 
-    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）": {
-            "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)
-        },
-    })
-    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）": {
-            "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)
-        },
-    })
-    ###################### 第n组插件 ###########################
     return function_plugins

crazy_functions/CodeInterpreter.py

@@ -0,0 +1,232 @@
+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/Langchain知识库.py

@@ -0,0 +1,106 @@
+from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_lastest_msg
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_files_from_everything
+
+
+
+@CatchException
+def 知识库问答(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
+    """
+    history = []    # 清空历史，以免输入溢出
+
+    # < --------------------读取参数--------------- >
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    kai_id = plugin_kwargs.get("advanced_arg", 'default')
+
+    chatbot.append((f"向`{kai_id}`知识库中添加文件。", "[Local Message] 从一批文件(txt, md, tex)中读取数据构建知识库, 然后进行问答。"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # resolve deps
+    try:
+        from zh_langchain import construct_vector_store
+        from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+        from .crazy_utils 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..."])
+        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)
+        return
+
+    # < --------------------读取文件--------------- >
+    file_manifest = []
+    spl = ["txt", "doc", "docx", "email", "epub", "html", "json", "md", "msg", "pdf", "ppt", "pptx", "rtf"]
+    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
+    print('Checking Text2vec ...')
+    from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+    with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
+        HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
+
+    # < -------------------构建知识库--------------- >
+    chatbot.append(['<br/>'.join(file_manifest), "正在构建知识库..."])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    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()
+    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.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):
+    # resolve deps
+    try:
+        from zh_langchain import construct_vector_store
+        from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+        from .crazy_utils 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..."])
+        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)
+        return
+
+    # < -------------------  --------------- >
+    kai = knowledge_archive_interface()
+
+    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)
+
+    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=[], 
+        sys_prompt=system_prompt
+    )
+    history.extend((prompt, gpt_say))
+    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

crazy_functions/Latex全文润色.py

@@ -1,6 +1,6 @@
-from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
-fast_debug = False
+from toolbox import update_ui, trimmed_format_exc, promote_file_to_downloadzone, get_log_folder
+from toolbox import CatchException, report_exception, write_history_to_file, zip_folder
+
 
 class PaperFileGroup():
     def __init__(self):
@@ -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
@@ -26,16 +26,35 @@ 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)
                     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))]
+        for r, k in zip(self.sp_file_result, self.sp_file_index):
+            self.file_result[k] += r
 
-def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
+    def write_result(self):
+        manifest = []
+        for path, res in zip(self.file_paths, self.file_result):
+            with open(path + '.polish.tex', 'w', encoding='utf8') as f:
+                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])
+        t = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
+        zip_folder(folder, get_log_folder(), f'{t}-polished.zip')
+
+
+def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en', mode='polish'):
     import time, os, re
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
@@ -47,7 +66,7 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         with open(fp, 'r', encoding='utf-8', errors='replace') as f:
             file_content = f.read()
             # 定义注释的正则表达式
-            comment_pattern = r'%.*'
+            comment_pattern = r'(?<!\\)%.*'
             # 使用正则表达式查找注释，并替换为空字符串
             clean_tex_content = re.sub(comment_pattern, '', file_content)
             # 记录删除注释后的文本
@@ -58,28 +77,27 @@ def 多文件润色(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     pfg.run_file_split(max_token_limit=1024)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 抽取摘要 ----------> 
-    # if language == 'en':
-    #     abs_extract_inputs = f"Please write an abstract for this paper"
-
-    # # 单线，获取文章meta信息
-    # paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
-    #     inputs=abs_extract_inputs,
-    #     inputs_show_user=f"正在抽取摘要信息。",
-    #     llm_kwargs=llm_kwargs,
-    #     chatbot=chatbot, history=[],
-    #     sys_prompt="Your job is to collect information from materials。",
-    # )
 
     #  <-------- 多线程润色开始 ----------> 
     if language == 'en':
-        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:" + 
+        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:" + 
+                            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:" + 
                         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':
-        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：" + 
-                        f"\n\n{frag}" for frag in pfg.sp_file_contents]
+        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：" + 
+                            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_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)]
 
@@ -95,27 +113,40 @@ 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 ----------> 
+    try:
+        pfg.sp_file_result = []
+        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()
+        pfg.zip_result()
+    except:
+        print(trimmed_format_exc())
+
     #  <-------- 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_results_to_file(gpt_response_collection, file_name=create_report_file_name)
+    res = write_history_to_file(gpt_response_collection, file_basename=create_report_file_name)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
+
     history = gpt_response_collection
     chatbot.append((f"{fp}完成了吗？", res))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
 
 @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"])
+        "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
@@ -126,12 +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')
@@ -142,7 +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？",
@@ -153,7 +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
@@ -164,12 +195,51 @@ 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')
+
+
+
+
+@CatchException
+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？",
+        "对整个Latex项目进行纠错。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 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 tiktoken```。")
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+    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_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
+    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
-from toolbox import CatchException, report_execption, write_results_to_file
+from toolbox import update_ui, promote_file_to_downloadzone
+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)
@@ -46,7 +46,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         with open(fp, 'r', encoding='utf-8', errors='replace') as f:
             file_content = f.read()
             # 定义注释的正则表达式
-            comment_pattern = r'%.*'
+            comment_pattern = r'(?<!\\)%.*'
             # 使用正则表达式查找注释，并替换为空字符串
             clean_tex_content = re.sub(comment_pattern, '', file_content)
             # 记录删除注释后的文本
@@ -95,7 +95,8 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
 
     #  <-------- 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_results_to_file(gpt_response_collection, file_name=create_report_file_name)
+    res = write_history_to_file(gpt_response_collection, create_report_file_name)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
     history = gpt_response_collection
     chatbot.append((f"{fp}完成了吗？", res))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -105,7 +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？",
@@ -116,7 +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
@@ -127,12 +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')
@@ -142,7 +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？",
@@ -153,7 +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
@@ -164,12 +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 +1,484 @@
+from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
+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 ('.' 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
+
+    # <-------------- convert pdf into tex ------------->
+    project_folder = pdf2tex_project(file_manifest[0])
+
+    # Translate English Latex to Chinese Latex, and compile it
+    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)
+
+    # <-------------- 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/Latex输出PDF结果.py

@@ -0,0 +1,306 @@
+from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone
+from toolbox import CatchException, report_exception, 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,'*'))
+    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 ('.' 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_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, 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_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

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

@@ -0,0 +1,141 @@
+from toolbox import CatchException, update_ui, promote_file_to_downloadzone
+from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+import datetime, json
+
+def fetch_items(list_of_items, batch_size):
+    for i in range(0, len(list_of_items), batch_size):
+        yield list_of_items[i:i + batch_size]
+
+def string_to_options(arguments):
+    import argparse
+    import shlex
+
+    # Create an argparse.ArgumentParser instance
+    parser = argparse.ArgumentParser()
+
+    # Add command-line arguments
+    parser.add_argument("--llm_to_learn", type=str, help="LLM model to learn", default="gpt-3.5-turbo")
+    parser.add_argument("--prompt_prefix", type=str, help="Prompt prefix", default='')
+    parser.add_argument("--system_prompt", type=str, help="System prompt", default='')
+    parser.add_argument("--batch", type=int, help="System prompt", default=50)
+    parser.add_argument("--pre_seq_len", type=int, help="pre_seq_len", default=50)
+    parser.add_argument("--learning_rate", type=float, help="learning_rate", default=2e-2)
+    parser.add_argument("--num_gpus", type=int, help="num_gpus", default=1)
+    parser.add_argument("--json_dataset", type=str, help="json_dataset", default="")
+    parser.add_argument("--ptuning_directory", type=str, help="ptuning_directory", default="")
+
+
+
+    # Parse the arguments
+    args = parser.parse_args(shlex.split(arguments))
+
+    return args
+
+@CatchException
+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
+    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）
+    """
+    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: 
+        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)
+
+    dat = []
+    with open(txt, 'r', encoding='utf8') as f:
+        for line in f.readlines():
+            json_dat = json.loads(line)
+            dat.append(json_dat["content"])
+
+    llm_kwargs['llm_model'] = arguments.llm_to_learn
+    for batch in fetch_items(dat, arguments.batch):
+        res = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+            inputs_array=[f"{arguments.prompt_prefix}\n\n{b}" for b in (batch)],
+            inputs_show_user_array=[f"Show Nothing" for _ in (batch)],
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot,
+            history_array=[[] for _ in (batch)],
+            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')
+
+    promote_file_to_downloadzone(txt+'.generated.json', rename_file='generated.json', chatbot=chatbot)
+    return
+
+
+
+@CatchException
+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
+    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）
+    """
+    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: 
+        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
+    learning_rate = arguments.learning_rate                               # 2e-2
+    num_gpus = arguments.num_gpus                   # 1
+    json_dataset = arguments.json_dataset                 # 't_code.json'
+    ptuning_directory = arguments.ptuning_directory       # '/home/hmp/ChatGLM2-6B/ptuning'
+
+    command = f"torchrun --standalone --nnodes=1 --nproc-per-node={num_gpus} main.py \
+        --do_train \
+        --train_file AdvertiseGen/{json_dataset} \
+        --validation_file AdvertiseGen/{json_dataset} \
+        --preprocessing_num_workers 20 \
+        --prompt_column content \
+        --response_column summary \
+        --overwrite_cache \
+        --model_name_or_path THUDM/chatglm2-6b \
+        --output_dir output/clothgen-chatglm2-6b-pt-{pre_seq_len}-{learning_rate} \
+        --overwrite_output_dir \
+        --max_source_length 256 \
+        --max_target_length 256 \
+        --per_device_train_batch_size 1 \
+        --per_device_eval_batch_size 1 \
+        --gradient_accumulation_steps 16 \
+        --predict_with_generate \
+        --max_steps 100 \
+        --logging_steps 10 \
+        --save_steps 20 \
+        --learning_rate {learning_rate} \
+        --pre_seq_len {pre_seq_len} \
+        --quantization_bit 4"
+
+    process = subprocess.Popen(command, shell=True, cwd=ptuning_directory)
+    try:
+        process.communicate(timeout=3600*24)
+    except subprocess.TimeoutExpired:
+        process.kill()
+    return

crazy_functions/crazy_functions_test.py

@@ -4,16 +4,24 @@
     运行方法 python crazy_functions/crazy_functions_test.py
 """
     
+# ==============================================================================================================================
+
 def validate_path():
     import os, sys
     dir_name = os.path.dirname(__file__)
     root_dir_assume = os.path.abspath(os.path.dirname(__file__) +  '/..')
     os.chdir(root_dir_assume)
     sys.path.append(root_dir_assume)
-    
 validate_path() # validate path so you can run from base directory
+
+# ==============================================================================================================================
+
 from colorful import *
 from toolbox import get_conf, ChatBotWithCookies
+import contextlib
+import os
+import sys
+from functools import wraps
 proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY = \
     get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY')
 
@@ -30,7 +38,43 @@ history = []
 system_prompt = "Serve me as a writing and programming assistant."
 web_port = 1024
 
+# ==============================================================================================================================
 
+def silence_stdout(func):
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        _original_stdout = sys.stdout
+        sys.stdout = open(os.devnull, 'w')
+        for q in func(*args, **kwargs):
+            sys.stdout = _original_stdout
+            yield q
+            sys.stdout = open(os.devnull, 'w')
+        sys.stdout.close()
+        sys.stdout = _original_stdout
+    return wrapper
+
+class CLI_Printer():
+    def __init__(self) -> None:
+        self.pre_buf = ""
+
+    def print(self, buf):
+        bufp = ""
+        for index, chat in enumerate(buf):
+            a, b = chat
+            bufp += sprint亮靛('[Me]:' + a) + '\n'
+            bufp += '[GPT]:' + b
+            if index < len(buf)-1: 
+                bufp += '\n'
+
+        if self.pre_buf!="" and bufp.startswith(self.pre_buf):
+            print(bufp[len(self.pre_buf):], end='')
+        else:
+            print('\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n'+bufp, end='')
+        self.pre_buf = bufp
+        return
+    
+cli_printer = CLI_Printer()
+# ==============================================================================================================================
 def test_解析一个Python项目():
     from crazy_functions.解析项目源代码 import 解析一个Python项目
     txt = "crazy_functions/test_project/python/dqn"
@@ -81,29 +125,13 @@ def test_下载arxiv论文并翻译摘要():
 
 def test_联网回答问题():
     from crazy_functions.联网的ChatGPT import 连接网络回答问题
-    # txt = "“我们称之为高效”是什么梗？"
-    # >>        从第0份、第1份、第2份搜索结果可以看出，“我们称之为高效”是指在游戏社区中，用户们用来形容一些游戏策略或行为非常高效且能够带来好的效果的用语。这个用语最初可能是在群星（Stellaris）这个游戏里面流行起来的，后来也传播到了其他游戏中，比如巨像（Titan）等游戏。其中第1份搜索结果中的一篇文章也指出，“我们称之为高效”这 一用语来源于群星（Stellaris）游戏中的一个情节。
-    # txt = "为什么说枪毙P社玩家没有一个冤枉的？"
-    # >>        它们都是关于一个知乎用户所发的帖子，引用了一群游戏玩家对于需要对P社玩家进行枪毙的讨论，这个话题的本质是玩家们对于P 社游戏中的政治与历史元素的不同看法，以及其中不少玩家以极端立场宣扬的想法和言论，因此有人就以枪毙这些玩家来回应此类言论。但是这个话题本身并没有实质内容，只是一个玩笑或者恶搞，并不应该被当做真实的态度或者观点，因此这种说法没有实际意义。
     # txt = "谁是应急食品？"
     # >>        '根据以上搜索结果可以得知，应急食品是“原神”游戏中的角色派蒙的外号。'
     # txt = "道路千万条，安全第一条。后面两句是？"
     # >>        '行车不规范，亲人两行泪。'
-    # txt = "What is in the canister?"
-    # >>        Rainbow Six Siege 游戏中 Smoke 的 Canister 中装有何种物质相关的官方信息。
-    # txt = "失败的man是什么?"
-    # >>        根据第1份搜索结果，可以得知失败的man是指一位在B站购买了蜘蛛侠COS服后穿上后被网友嘲笑的UP主，而“失败的man”是蜘蛛侠英文名“spiderman”的谐音梗，并且网友们还 给这位UP主起了“苍蝇侠”的外号。因此，失败的man是指这位UP主在穿上蜘蛛侠COS服后被网友嘲笑的情况。
-    # txt = "老六是什么，起源于哪里？"
-    # >>        老六是网络流行语，最初起源于游戏《CSGO》，指游戏中玩家中独来独往、游离于队伍之外的“自由人”或玩得比较菜或者玩得比较阴险的人 ，后来逐渐演变成指玩得比较阴险的玩家。
-    # txt = "罗小黑战记因为什么经常被吐槽？"
-    # >>        3. 更新速度。罗小黑战记的更新时间不定，时而快时而慢，给观众留下了等待的时间过长的印象。
-    # txt = "沙特、伊朗最近的关系如何？"
-    # >>        最近在中国的斡旋下，沙特和伊朗于3月10日达成了恢复两国外交关系的协议，这表明两国关系已经重新回到正常化状态。
     # txt = "You should have gone for the head. What does that mean?"
     # >>        The phrase "You should have gone for the head" is a quote from the Marvel movies, Avengers: Infinity War and Avengers: Endgame. It was spoken by the character Thanos in Infinity War and by Thor in Endgame.
     txt = "AutoGPT是什么？"
-    # >>        AutoGPT是一个基于GPT-4语言模型的开源应用程序。它可以根据用户需求自主执行任务，包括事件分析、营销方案撰写、代码编程、数学运算等等，并完全不需要用户插手。它可以自己思考，给出实现的步骤和实现细节，甚至可以自问自答执 行任务。最近它在GitHub上爆火，成为了业内最热门的项目之一。
-    # txt = "钟离带什么圣遗物？"
     for cookies, cb, hist, msg in 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): 
         print("当前问答：", cb[-1][-1].replace("\n"," "))
     for i, it in enumerate(cb): print亮蓝(it[0]); print亮黄(it[1])
@@ -115,6 +143,75 @@ def test_解析ipynb文件():
         print(cb)
 
 
+def test_数学动画生成manim():
+    from crazy_functions.数学动画生成manim import 动画生成
+    txt = "A ball split into 2, and then split into 4, and finally split into 8."
+    for cookies, cb, hist, msg in 动画生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        print(cb)
+
+
+
+def test_Markdown多语言():
+    from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
+    txt = "README.md"
+    history = []
+    for lang in ["English", "French", "Japanese", "Korean", "Russian", "Italian", "German", "Portuguese", "Arabic"]:
+        plugin_kwargs = {"advanced_arg": lang}
+        for cookies, cb, hist, msg in Markdown翻译指定语言(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+            print(cb)
+
+def test_Langchain知识库():
+    from crazy_functions.Langchain知识库 import 知识库问答
+    txt = "./"
+    chatbot = ChatBotWithCookies(llm_kwargs)
+    for cookies, cb, hist, msg in silence_stdout(知识库问答)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        cli_printer.print(cb)   #  print(cb)
+    
+    chatbot = ChatBotWithCookies(cookies)
+    from crazy_functions.Langchain知识库 import 读取知识库作答
+    txt = "What is the installation method？"
+    for cookies, cb, hist, msg in silence_stdout(读取知识库作答)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        cli_printer.print(cb)   #  print(cb)
+
+def test_Langchain知识库读取():
+    from crazy_functions.Langchain知识库 import 读取知识库作答
+    txt = "远程云服务器部署？"
+    for cookies, cb, hist, msg in silence_stdout(读取知识库作答)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        cli_printer.print(cb)   #  print(cb)
+
+def test_Latex():
+    from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比, Latex翻译中文并重新编译PDF
+
+    # txt = r"https://arxiv.org/abs/1706.03762"
+    # txt = r"https://arxiv.org/abs/1902.03185"
+    # txt = r"https://arxiv.org/abs/2305.18290"
+    # txt = r"https://arxiv.org/abs/2305.17608"
+    # txt = r"https://arxiv.org/abs/2211.16068"                     #  ACE
+    # txt = r"C:\Users\x\arxiv_cache\2211.16068\workfolder"  #  ACE
+    # txt = r"https://arxiv.org/abs/2002.09253"
+    # txt = r"https://arxiv.org/abs/2306.07831"
+    # txt = r"https://arxiv.org/abs/2212.10156"
+    # txt = r"https://arxiv.org/abs/2211.11559"
+    # txt = r"https://arxiv.org/abs/2303.08774"
+    txt = r"https://arxiv.org/abs/2303.12712"
+    # txt = r"C:\Users\fuqingxu\arxiv_cache\2303.12712\workfolder"
+    
+
+    for cookies, cb, hist, msg in (Latex翻译中文并重新编译PDF)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        cli_printer.print(cb)   #  print(cb)
+
+
+
+    # txt = "2302.02948.tar"
+    # print(txt)
+    # main_tex, work_folder = Latex预处理(txt)
+    # print('main tex:', main_tex)
+    # res = 编译Latex(main_tex, work_folder)
+    # # for cookies, cb, hist, msg in silence_stdout(编译Latex)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    #     cli_printer.print(cb)   #  print(cb)
+
+
+
 # test_解析一个Python项目()
 # test_Latex英文润色()
 # test_Markdown中译英()
@@ -124,7 +221,11 @@ def test_解析ipynb文件():
 # test_下载arxiv论文并翻译摘要()
 # test_解析一个Cpp项目()
 # test_联网回答问题()
-test_解析ipynb文件()
-
-input("程序完成，回车退出。")
-print("退出。")
+# test_解析ipynb文件()
+# test_数学动画生成manim()
+# test_Langchain知识库()
+# test_Langchain知识库读取()
+if __name__ == "__main__":
+    test_Latex()
+    input("程序完成，回车退出。")
+    print("退出。")

crazy_functions/crazy_utils.py

@@ -1,8 +1,11 @@
-from toolbox import update_ui, get_conf, trimmed_format_exc
+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=()))
 
@@ -60,18 +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
@@ -86,7 +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'
@@ -129,6 +135,13 @@ 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
+    if llm.startswith('spark'): return True
+    if llm.startswith('zhipuai') or llm.startswith('glm-'): return True
+    return False
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         inputs_array, inputs_show_user_array, llm_kwargs,
@@ -166,15 +179,15 @@ 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 (llm_kwargs['llm_model'].startswith('gpt-') or llm_kwargs['llm_model'].startswith('api2d-')):
+    if not can_multi_process(llm_kwargs['llm_model']):
         max_workers = 1
 
     executor = ThreadPoolExecutor(max_workers=max_workers)
@@ -185,19 +198,21 @@ 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,
                     sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
@@ -205,13 +220,13 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                 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'
@@ -226,6 +241,7 @@ 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"
@@ -242,6 +258,7 @@ 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:
@@ -259,9 +276,6 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         time.sleep(refresh_interval)
         cnt += 1
         worker_done = [h.done() for h in futures]
-        if all(worker_done):
-            executor.shutdown()
-            break
         # 更好的UI视觉效果
         observe_win = []
         # 每个线程都要“喂狗”（看门狗）
@@ -270,8 +284,7 @@ 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'
@@ -280,6 +293,9 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         # 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))]
         yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
+        if all(worker_done):
+            executor.shutdown()
+            break
 
     # 异步任务结束
     gpt_response_collection = []
@@ -293,99 +309,10 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
             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):
     """
@@ -463,14 +390,16 @@ def read_and_clean_pdf_text(fp):
                     '- ', '') for t in text_areas['blocks'] if 'lines' in t]
 
         ############################## <第 2 步，获取正文主字体> ##################################
-        fsize_statiscs = {}
-        for span in meta_span:
-            if span[1] not in fsize_statiscs: fsize_statiscs[span[1]] = 0
-            fsize_statiscs[span[1]] += span[2]
-        main_fsize = max(fsize_statiscs, key=fsize_statiscs.get)
-        if REMOVE_FOOT_NOTE:
-            give_up_fize_threshold = main_fsize * REMOVE_FOOT_FFSIZE_PERCENT
-
+        try:
+            fsize_statiscs = {}
+            for span in meta_span:
+                if span[1] not in fsize_statiscs: fsize_statiscs[span[1]] = 0
+                fsize_statiscs[span[1]] += span[2]
+            main_fsize = max(fsize_statiscs, key=fsize_statiscs.get)
+            if REMOVE_FOOT_NOTE:
+                give_up_fize_threshold = main_fsize * REMOVE_FOOT_FFSIZE_PERCENT
+        except:
+            raise RuntimeError(f'抱歉, 我们暂时无法解析此PDF文档: {fp}。')
         ############################## <第 3 步，切分和重新整合> ##################################
         mega_sec = []
         sec = []
@@ -536,6 +465,9 @@ 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):
@@ -563,3 +495,114 @@ def read_and_clean_pdf_text(fp):
         #    print亮绿('***************************')
 
     return meta_txt, page_one_meta
+
+
+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。
+    - 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。
+    - 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。
+    """
+    import glob, os
+
+    success = True
+    if txt.startswith('http'):
+        # 网络的远程文件
+        import requests
+        from toolbox import get_conf
+        from toolbox import get_log_folder, gen_time_str
+        proxies = get_conf('proxies')
+        try:
+            r = requests.get(txt, proxies=proxies)
+        except:
+            raise ConnectionRefusedError(f"无法下载资源{txt}，请检查。")
+        path = os.path.join(get_log_folder(plugin_name='web_download'), gen_time_str()+type)
+        with open(path, 'wb+') as f: f.write(r.content)
+        project_folder = get_log_folder(plugin_name='web_download')
+        file_manifest = [path]
+    elif txt.endswith(type):
+        # 直接给定文件
+        file_manifest = [txt]
+        project_folder = os.path.dirname(txt)
+    elif os.path.exists(txt):
+        # 本地路径，递归搜索
+        project_folder = txt
+        file_manifest = [f for f in glob.glob(f'{project_folder}/**/*'+type, recursive=True)]
+        if len(file_manifest) == 0:
+            success = False
+    else:
+        project_folder = None
+        file_manifest = []
+        success = False
+
+    return success, file_manifest, project_folder
+
+
+
+@Singleton
+class nougat_interface():
+    def __init__(self):
+        self.threadLock = threading.Lock()
+
+    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}')
+        with ProxyNetworkActivate("Nougat_Download"):
+            process = subprocess.Popen(command, shell=True, cwd=cwd, env=os.environ)
+        try:
+            stdout, stderr = process.communicate(timeout=timeout)
+        except subprocess.TimeoutExpired:
+            process.kill()
+            stdout, stderr = process.communicate()
+            print("Process timed out!")
+            return False
+        return True
+
+
+    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...",
+                                         chatbot=chatbot, history=history, delay=0)
+        self.threadLock.acquire()
+        import glob, threading, os
+        from toolbox import get_log_folder, gen_time_str
+        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）",
+                                         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)
+        res = glob.glob(os.path.join(dst,'*.mmd'))
+        if len(res) == 0:
+            self.threadLock.release()
+            raise RuntimeError("Nougat解析论文失败。")
+        self.threadLock.release()
+        return res[0]
+
+
+
+
+def try_install_deps(deps, reload_m=[]):
+    import subprocess, sys, importlib
+    for dep in deps:
+        subprocess.check_call([sys.executable, '-m', 'pip', 'install', '--user', dep])
+    import site
+    importlib.reload(site)
+    for m in reload_m:
+        importlib.reload(__import__(m))
+
+
+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)
+    # 正常情况
+    return plugin_kwargs.get(key, default)

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

@@ -0,0 +1,70 @@
+import time
+import importlib
+from toolbox import trimmed_format_exc, gen_time_str, get_log_folder
+from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
+from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
+import multiprocessing
+
+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
+
+def try_make_module(code, chatbot):
+    module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
+    fn_path = f'{get_log_folder(plugin_name="gen_plugin_verify")}/{module_file}.py'
+    with open(fn_path, 'w', encoding='utf8') as f: f.write(code)
+    promote_file_to_downloadzone(fn_path, chatbot=chatbot)
+    class_name = get_class_name(code)
+    manager = multiprocessing.Manager()
+    return_dict = manager.dict()
+    p = multiprocessing.Process(target=is_function_successfully_generated, args=(fn_path, class_name, return_dict))
+    # only has 10 seconds to run
+    p.start(); p.join(timeout=10)
+    if p.is_alive(): p.terminate(); p.join()
+    p.close()
+    return return_dict["success"], return_dict['traceback']
+
+# check is_function_successfully_generated
+def is_function_successfully_generated(fn_path, class_name, return_dict):
+    return_dict['success'] = False
+    return_dict['traceback'] = ""
+    try:
+        # Create a spec for the module
+        module_spec = importlib.util.spec_from_file_location('example_module', fn_path)
+        # Load the module
+        example_module = importlib.util.module_from_spec(module_spec)
+        module_spec.loader.exec_module(example_module)
+        # Now you can use the module
+        some_class = getattr(example_module, class_name)
+        # Now you can create an instance of the class
+        instance = some_class()
+        return_dict['success'] = True
+        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
+    return_dict['traceback'] = ""
+    try:
+        module_file = 'gpt_fn_' + gen_time_str().replace('-','_')
+        fn_path = f'{get_log_folder(plugin_name="gen_plugin_run")}/{module_file}.py'
+        with open(fn_path, 'w', encoding='utf8') as f: f.write(code)
+        class_name = get_class_name(code)
+        # Create a spec for the module
+        module_spec = importlib.util.spec_from_file_location('example_module', fn_path)
+        # Load the module
+        example_module = importlib.util.module_from_spec(module_spec)
+        module_spec.loader.exec_module(example_module)
+        # Now you can use the module
+        some_class = getattr(example_module, class_name)
+        # Now you can create an instance of the class
+        instance = some_class()
+        return_dict['result'] = instance.run(file_path)
+        return_dict['success'] = True
+    except:
+        return_dict['traceback'] = trimmed_format_exc()

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

@@ -0,0 +1,111 @@
+"""
+https://github.com/langchain-ai/langchain/blob/master/docs/extras/modules/model_io/output_parsers/pydantic.ipynb
+
+Example 1.
+
+# Define your desired data structure.
+class Joke(BaseModel):
+    setup: str = Field(description="question to set up a joke")
+    punchline: str = Field(description="answer to resolve the joke")
+
+    # You can add custom validation logic easily with Pydantic.
+    @validator("setup")
+    def question_ends_with_question_mark(cls, field):
+        if field[-1] != "?":
+            raise ValueError("Badly formed question!")
+        return field
+
+
+Example 2.
+
+# Here's another example, but with a compound typed field.
+class Actor(BaseModel):
+    name: str = Field(description="name of an actor")
+    film_names: List[str] = Field(description="list of names of films they starred in")
+"""
+
+import json, re, logging
+
+
+PYDANTIC_FORMAT_INSTRUCTIONS = """The output should be formatted as a JSON instance that conforms to the JSON schema below.
+
+As an example, for the schema {{"properties": {{"foo": {{"title": "Foo", "description": "a list of strings", "type": "array", "items": {{"type": "string"}}}}}}, "required": ["foo"]}}
+the object {{"foo": ["bar", "baz"]}} is a well-formatted instance of the schema. The object {{"properties": {{"foo": ["bar", "baz"]}}}} is not well-formatted.
+
+Here is the output schema:
+```
+{schema}
+```"""
+
+
+PYDANTIC_FORMAT_INSTRUCTIONS_SIMPLE = """The output should be formatted as a JSON instance that conforms to the JSON schema below.
+```
+{schema}
+```"""
+
+class JsonStringError(Exception): ...
+
+class GptJsonIO():
+
+    def __init__(self, schema, example_instruction=True):
+        self.pydantic_object = schema
+        self.example_instruction = example_instruction
+        self.format_instructions = self.generate_format_instructions()
+
+    def generate_format_instructions(self):
+        schema = self.pydantic_object.schema()
+
+        # Remove extraneous fields.
+        reduced_schema = schema
+        if "title" in reduced_schema:
+            del reduced_schema["title"]
+        if "type" in reduced_schema:
+            del reduced_schema["type"]
+        # Ensure json in context is well-formed with double quotes.
+        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)
+
+    def generate_output(self, text):
+        # Greedy search for 1st json candidate.
+        match = re.search(
+            r"\{.*\}", text.strip(), re.MULTILINE | re.IGNORECASE | re.DOTALL
+        )
+        json_str = ""
+        if match: json_str = match.group()
+        json_object = json.loads(json_str, strict=False)
+        final_object = self.pydantic_object.parse_obj(json_object)
+        return final_object
+
+    def generate_repair_prompt(self, broken_json, error):
+        prompt = "Fix a broken json string.\n\n" + \
+                 "(1) The broken json string need to fix is: \n\n" + \
+                 "```" + "\n" + \
+                 broken_json + "\n" + \
+                 "```" + "\n\n" + \
+                 "(2) The error message is: \n\n" + \
+                 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
+        gpt_gen_fn: gpt_gen_fn(inputs, sys_prompt)
+        """
+        try:
+            result = self.generate_output(response)
+        except Exception as e:
+            try:
+                logging.info(f'Repairing json：{response}')
+                repair_prompt = self.generate_repair_prompt(broken_json = response, error=repr(e))
+                result = self.generate_output(gpt_gen_fn(repair_prompt, self.format_instructions))
+                logging.info('Repaire json success.')
+            except Exception as e:
+                # 没辙了，放弃治疗
+                logging.info('Repaire json fail.')
+                raise JsonStringError('Cannot repair json.', str(e))
+        return result
+

crazy_functions/latex_fns/latex_actions.py

@@ -0,0 +1,467 @@
+from toolbox import update_ui, update_ui_lastest_msg, get_log_folder
+from toolbox import get_conf, objdump, objload, 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
+
+import os, shutil
+import re
+import numpy as np
+
+pj = os.path.join
+
+
+def split_subprocess(txt, project_folder, return_dict, opts):
+    """
+    break down latex file to a linked list,
+    each node use a preserve flag to indicate whether it should
+    be proccessed by GPT.
+    """
+    text = txt
+    mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
+
+    # 吸收title与作者以上的部分
+    text, mask = set_forbidden_text(text, mask, r"^(.*?)\\maketitle", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"^(.*?)\\begin{document}", re.DOTALL)
+    # 吸收iffalse注释
+    text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
+    # 吸收在42行以内的begin-end组合
+    text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
+    # 吸收匿名公式
+    text, mask = set_forbidden_text(text, mask, [ r"\$\$([^$]+)\$\$",  r"\\\[.*?\\\]" ], re.DOTALL)
+    # 吸收其他杂项
+    text, mask = set_forbidden_text(text, mask, [ r"\\section\{(.*?)\}", r"\\section\*\{(.*?)\}", r"\\subsection\{(.*?)\}", r"\\subsubsection\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, [ r"\\bibliography\{(.*?)\}", r"\\bibliographystyle\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{thebibliography\}.*?\\end\{thebibliography\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{figure\}(.*?)\\end\{figure\}", r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{multline\}(.*?)\\end\{multline\}", r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{table\}(.*?)\\end\{table\}", r"\\begin\{table\*\}(.*?)\\end\{table\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{minipage\}(.*?)\\end\{minipage\}", r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{align\*\}(.*?)\\end\{align\*\}", r"\\begin\{align\}(.*?)\\end\{align\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{equation\}(.*?)\\end\{equation\}", r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\includepdf\[(.*?)\]\{(.*?)\}", r"\\clearpage", r"\\newpage", r"\\appendix", r"\\tableofcontents", r"\\include\{(.*?)\}"])
+    text, mask = set_forbidden_text(text, mask, [r"\\vspace\{(.*?)\}", r"\\hspace\{(.*?)\}", r"\\label\{(.*?)\}", r"\\begin\{(.*?)\}", r"\\end\{(.*?)\}", r"\\item "])
+    text, mask = set_forbidden_text_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
+    # reverse 操作必须放在最后
+    text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\abstract\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
+    root = convert_to_linklist(text, mask)
+
+    # 最后一步处理，增强稳健性
+    root = post_process(root)
+
+    # 输出html调试文件，用红色标注处保留区（PRESERVE），用黑色标注转换区（TRANSFORM）
+    with open(pj(project_folder, 'debug_log.html'), 'w', encoding='utf8') as f:
+        segment_parts_for_gpt = []
+        nodes = []
+        node = root
+        while True:
+            nodes.append(node)
+            show_html = node.string.replace('\n','<br/>')
+            if not node.preserve:
+                segment_parts_for_gpt.append(node.string)
+                f.write(f'<p style="color:black;">#{node.range}{show_html}#</p>')
+            else:
+                f.write(f'<p style="color:red;">{show_html}</p>')
+            node = node.next
+            if node is None: break
+
+    for n in nodes: n.next = None   # break
+    return_dict['nodes'] = nodes
+    return_dict['segment_parts_for_gpt'] = segment_parts_for_gpt
+    return return_dict
+
+class LatexPaperSplit():
+    """
+    break down latex file to a linked list,
+    each node use a preserve flag to indicate whether it should
+    be proccessed by GPT.
+    """
+    def __init__(self) -> None:
+        self.nodes = None
+        self.msg = "*{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
+            "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.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):
+        """
+        Merge the result after the GPT process completed
+        """
+        result_string = ""
+        node_cnt = 0
+        line_cnt = 0
+        
+        for node in self.nodes:
+            if node.preserve:
+                line_cnt += node.string.count('\n')
+                result_string += node.string
+            else:
+                translated_txt = fix_content(arr[node_cnt], node.string)
+                begin_line = line_cnt
+                end_line = line_cnt + translated_txt.count('\n')
+
+                # reverse translation if any error
+                if any([begin_line-buggy_line_surgery_n_lines <= b_line <= end_line+buggy_line_surgery_n_lines for b_line in buggy_lines]):
+                    translated_txt = node.string
+
+                result_string += translated_txt
+                node_cnt += 1
+                line_cnt += translated_txt.count('\n')
+
+        if mode == 'translate_zh':
+            pattern = re.compile(r'\\begin\{abstract\}.*\n')
+            match = pattern.search(result_string)
+            if not match:
+                # match \abstract{xxxx}
+                pattern_compile = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
+                match = pattern_compile.search(result_string)
+                position = match.regs[1][0]
+            else:
+                # match \begin{abstract}xxxx\end{abstract}
+                position = match.end()
+            result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
+        return result_string
+
+
+    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
+        be proccessed by GPT.
+        P.S. use multiprocessing to avoid timeout error
+        """
+        import multiprocessing
+        manager = multiprocessing.Manager()
+        return_dict = manager.dict()
+        p = multiprocessing.Process(
+            target=split_subprocess, 
+            args=(txt, project_folder, return_dict, opts))
+        p.start()
+        p.join()
+        p.close()
+        self.nodes = return_dict['nodes']
+        self.sp = return_dict['segment_parts_for_gpt']
+        return self.sp
+
+
+class LatexPaperFileGroup():
+    """
+    use tokenizer to break down text according to max_token_limit
+    """
+    def __init__(self):
+        self.file_paths = []
+        self.file_contents = []
+        self.sp_file_contents = []
+        self.sp_file_index = []
+        self.sp_file_tag = []
+        # count_token
+        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):
+        """
+        use tokenizer to break down text according to max_token_limit
+        """
+        for index, file_content in enumerate(self.file_contents):
+            if self.get_token_num(file_content) < max_token_limit:
+                self.sp_file_contents.append(file_content)
+                self.sp_file_index.append(index)
+                self.sp_file_tag.append(self.file_paths[index])
+            else:
+                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")
+
+    def merge_result(self):
+        self.file_result = ["" for _ in range(len(self.file_paths))]
+        for r, k in zip(self.sp_file_result, self.sp_file_index):
+            self.file_result[k] += r
+
+    def write_result(self):
+        manifest = []
+        for path, res in zip(self.file_paths, self.file_result):
+            with open(path + '.polish.tex', 'w', encoding='utf8') as f:
+                manifest.append(path + '.polish.tex')
+                f.write(res)
+        return manifest
+
+
+def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='proofread', switch_prompt=None, opts=[]):
+    import time, os, re
+    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 ----------> 
+    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 ----------> 
+    main_tex_basename = os.path.basename(maintex)
+    assert main_tex_basename.endswith('.tex')
+    main_tex_basename_bare = main_tex_basename[:-4]
+    may_exist_bbl = pj(project_folder, f'{main_tex_basename_bare}.bbl')
+    if os.path.exists(may_exist_bbl):
+        shutil.copyfile(may_exist_bbl, pj(project_folder, f'merge.bbl'))
+        shutil.copyfile(may_exist_bbl, pj(project_folder, f'merge_{mode}.bbl'))
+        shutil.copyfile(may_exist_bbl, pj(project_folder, f'merge_diff.bbl'))
+
+    with open(maintex, 'r', encoding='utf-8', errors='replace') as f:
+        content = f.read()
+        merged_content = merge_tex_files(project_folder, content, mode)
+
+    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 ----------> 
+    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 ----------> 
+    pfg = LatexPaperFileGroup()
+    for index, r in enumerate(res):
+        pfg.file_paths.append('segment-' + str(index))
+        pfg.file_contents.append(r)
+
+    pfg.run_file_split(max_token_limit=1024)
+    n_split = len(pfg.sp_file_contents)
+
+    #  <-------- 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 ----------> 
+        pfg = objload(file=pj(project_folder,'temp.pkl'))
+
+    else:
+        #  <-------- 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=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 ----------> 
+        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 ----------> 
+        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 ----------> 
+    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 ----------> 
+    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 ----------> 
+    return project_folder + f'/merge_{mode}.tex'
+
+
+def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified, fixed_line=[]):
+    try:
+        with open(log_path, 'r', encoding='utf-8', errors='replace') as f:
+            log = f.read()
+        import re
+        buggy_lines = re.findall(tex_name+':([0-9]{1,5}):', log)
+        buggy_lines = [int(l) for l in buggy_lines]
+        buggy_lines = sorted(buggy_lines)
+        buggy_line = buggy_lines[0]-1
+        print("reversing tex line that has errors", buggy_line)
+
+        # 重组，逆转出错的段落
+        if buggy_line not in fixed_line:
+            fixed_line.append(buggy_line)
+
+        lps, file_result, mode, msg = objload(file=pj(work_folder_modified,'merge_result.pkl'))
+        final_tex = lps.merge_result(file_result, mode, msg, buggy_lines=fixed_line, buggy_line_surgery_n_lines=5*n_fix)
+
+        with open(pj(work_folder_modified, f"{tex_name_pure}_fix_{n_fix}.tex"), 'w', encoding='utf-8', errors='replace') as f:
+            f.write(final_tex)
+
+        return True, f"{tex_name_pure}_fix_{n_fix}", buggy_lines
+    except:
+        print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
+        return False, -1, [-1]
+
+
+def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder, mode='default'):
+    import os, time
+    n_fix = 1
+    fixed_line = []
+    max_try = 32
+    chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
+    chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
+    yield from update_ui_lastest_msg('编译已经开始...', chatbot, history)   # 刷新Gradio前端界面
+
+    while True:
+        import os
+        may_exist_bbl = pj(work_folder_modified, f'merge.bbl')
+        target_bbl = pj(work_folder_modified, f'{main_file_modified}.bbl')
+        if os.path.exists(may_exist_bbl) and not os.path.exists(target_bbl):
+            shutil.copyfile(may_exist_bbl, target_bbl)
+
+        # https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
+        yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history)   # 刷新Gradio前端界面
+        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+
+        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
+            if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux', work_folder_original)
+            if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux', work_folder_modified)
+
+            yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history)  # 刷新Gradio前端界面
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+
+            if mode!='translate_zh':
+                yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
+                print(    f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
+                ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
+
+                yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux', work_folder)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+
+        # <---------- 检查结果 ----------->
+        results_ = ""
+        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};" 
+        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, 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: 
+                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'), 
+                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}',
+                n_fix=n_fix,
+                work_folder_modified=work_folder_modified,
+                fixed_line=fixed_line
+            )
+            yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history)   # 刷新Gradio前端界面
+            if not can_retry: break
+
+    return False # 失败啦
+
+
+def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
+    # write html
+    try:
+        import shutil
+        from crazy_functions.pdf_fns.report_gen_html import construct_html
+        from toolbox import gen_time_str
+        ch = construct_html() 
+        orig = ""
+        trans = ""
+        final = []
+        for c,r in zip(sp_file_contents, sp_file_result): 
+            final.append(c)
+            final.append(r)
+        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"{gen_time_str()}.trans.html"
+        res = ch.save_file(create_report_file_name)
+        shutil.copyfile(res, pj(project_folder, create_report_file_name))
+        promote_file_to_downloadzone(file=res, chatbot=chatbot)
+    except:
+        from toolbox import trimmed_format_exc
+        print('writing html result failed:', trimmed_format_exc())

crazy_functions/latex_fns/latex_toolbox.py

@@ -0,0 +1,694 @@
+import os, shutil
+import re
+import numpy as np
+
+PRESERVE = 0
+TRANSFORM = 1
+
+pj = os.path.join
+
+
+class LinkedListNode:
+    """
+    Linked List Node
+    """
+
+    def __init__(self, string, preserve=True) -> None:
+        self.string = string
+        self.preserve = preserve
+        self.next = None
+        self.range = None
+        # 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
+        ):
+            # add
+            current_node.string += c
+        else:
+            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:
+            node = node.next
+            if node is None:
+                break
+            continue
+
+        def break_check(string):
+            str_stack = [""]  # (lv, index)
+            for i, c in enumerate(string):
+                if c == "{":
+                    str_stack.append("{")
+                elif c == "}":
+                    if len(str_stack) == 1:
+                        print("stack fix")
+                        return i
+                    str_stack.pop(-1)
+                else:
+                    str_stack[-1] += c
+            return -1
+
+        bp = break_check(string)
+
+        if bp == -1:
+            pass
+        elif bp == 0:
+            node.string = string[:1]
+            q = LinkedListNode(string[1:], False)
+            q.next = node.next
+            node.next = q
+        else:
+            node.string = string[:bp]
+            q = LinkedListNode(string[bp:], False)
+            q.next = node.next
+            node.next = q
+
+        node = node.next
+        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
+        node = node.next
+        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
+
+    # 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_)]
+                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
+                node.string = rstriped_
+        # =-=-=
+        prev_node = node
+        node = node.next
+        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
+        node = node.next
+        if node is None:
+            break
+    return root
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+"""
+
+
+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)
+    everything between "\begin{equation}" and "\end{equation}"
+    """
+    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
+    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.
+    e.g.
+    \begin{abstract} blablablablablabla. \end{abstract}
+    """
+    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
+        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
+    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.
+    e.g.
+    \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
+            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
+):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area.
+    e.g.
+    \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
+            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
+    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, this_mask = search_with_line_limit(this, this_mask)
+                mask[res.regs[2][0] : res.regs[2][1]] = this_mask
+            else:
+                mask[res.regs[0][0] : res.regs[0][1]] = PRESERVE
+        return text, mask
+
+    return search_with_line_limit(text, mask)
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+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。
+    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
+    """
+    canidates = []
+    for texf in file_manifest:
+        if os.path.basename(texf).startswith("merge"):
+            continue
+        with open(texf, "r", encoding="utf8", errors="ignore") as f:
+            file_content = f.read()
+        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）")
+    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
+        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"]
+        for texf in canidates:
+            canidates_score.append(0)
+            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:
+                if uw in file_content:
+                    canidates_score[-1] -= 1
+            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
+        return canidates[select]
+
+
+def rm_comments(main_file):
+    new_file_remove_comment_lines = []
+    for l in main_file.splitlines():
+        # 删除整行的空注释
+        if l.lstrip().startswith("%"):
+            pass
+        else:
+            new_file_remove_comment_lines.append(l)
+    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
+    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.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.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"):
+        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
+        # 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
+    return None
+
+
+def merge_tex_files_(project_foler, main_file, mode):
+    """
+    Merge Tex project recrusively
+    """
+    main_file = rm_comments(main_file)
+    for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
+        f = s.group(1)
+        fp = os.path.join(project_foler, f)
+        fp_ = find_tex_file_ignore_case(fp)
+        if fp_:
+            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！")
+        c = merge_tex_files_(project_foler, c, mode)
+        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
+    P.S. 顺便把CTEX塞进去以支持中文
+    P.S. 顺便把Latex的注释去除
+    """
+    main_file = merge_tex_files_(project_foler, main_file, mode)
+    main_file = rm_comments(main_file)
+
+    if mode == "translate_zh":
+        # find paper documentclass
+        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 ""
+        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,
+        )
+        # find paper abstract
+        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)
+        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
+    """
+    # 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 = 'BOOM'
+    return "\\" + cmd + "{" + str_to_modify + "}"
+
+
+def fix_content(final_tex, node_string):
+    """
+    Fix common GPT errors to increase success rate
+    """
+    final_tex = re.sub(r"(?<!\\)%", "\\%", final_tex)
+    final_tex = re.sub(r"\\([a-z]{2,10})\ \{", r"\\\1{", string=final_tex)
+    final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
+    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("\_"):
+        # walk and replace any _ without \
+        final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
+
+    def compute_brace_level(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
+        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]
+                p += 1
+            return None, None
+
+        while True:
+            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
+            p_o = res1 + 1
+            p_t = res2 + 1
+        return tex_t[:p_t] + tex_o[p_o:]
+
+    if compute_brace_level(final_tex) != compute_brace_level(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
+    )
+    try:
+        stdout, stderr = process.communicate(timeout=timeout)
+    except subprocess.TimeoutExpired:
+        process.kill()
+        stdout, stderr = process.communicate()
+        print("Process timed out!")
+        return False
+    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
+
+    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:
+        pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
+        # Open the second PDF 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()
+            # Determine the number of pages in each PDF file
+            num_pages = max(pdf1_reader.numPages, pdf2_reader.numPages)
+            # Merge the pages from the two PDF files
+            for page_num in range(num_pages):
+                # Add the page from the first PDF file
+                if page_num < pdf1_reader.numPages:
+                    page1 = pdf1_reader.getPage(page_num)
+                else:
+                    page1 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
+                # Add the page from the second PDF file
+                if page_num < pdf2_reader.numPages:
+                    page2 = pdf2_reader.getPage(page_num)
+                else:
+                    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()),
+                )
+                new_page.mergeTranslatedPage(page1, 0, 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:
+                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/latex_utils.py

@@ -0,0 +1,788 @@
+from toolbox import update_ui, update_ui_lastest_msg    # 刷新Gradio前端界面
+from toolbox import zip_folder, objdump, objload, promote_file_to_downloadzone
+import os, shutil
+import re
+import numpy as np
+pj = os.path.join
+
+"""
+========================================================================
+Part One
+Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
+========================================================================
+"""
+PRESERVE = 0
+TRANSFORM = 1
+
+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) 
+    everything between "\begin{equation}" and "\end{equation}"
+    """
+    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
+    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. 
+    e.g.
+    \begin{abstract} blablablablablabla. \end{abstract} 
+    """
+    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
+        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
+    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. 
+    e.g.
+    \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
+            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):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \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
+            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
+    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, this_mask = search_with_line_limit(this, this_mask)
+                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
+            else:
+                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
+        return text, mask
+    return search_with_line_limit(text, mask) 
+
+class LinkedListNode():
+    """
+    Linked List Node
+    """
+    def __init__(self, string, preserve=True) -> None:
+        self.string = string
+        self.preserve = preserve
+        self.next = None
+        # 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):
+            # add
+            current_node.string += c
+        else:
+            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
+            current_node = current_node.next
+    return root
+"""
+========================================================================
+Latex Merge File
+========================================================================
+"""
+
+def 寻找Latex主文件(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。
+    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
+    """
+    canidates = []
+    for texf in file_manifest:
+        if os.path.basename(texf).startswith('merge'):
+            continue
+        with open(texf, 'r', encoding='utf8') as f:
+            file_content = f.read()
+        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）')
+    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
+        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']
+        for texf in canidates:
+            canidates_score.append(0)
+            with open(texf, 'r', encoding='utf8') as f:
+                file_content = f.read()
+            for uw in unexpected_words:
+                if uw in file_content:
+                    canidates_score[-1] -= 1
+            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
+        return canidates[select]
+    
+def rm_comments(main_file):
+    new_file_remove_comment_lines = []
+    for l in main_file.splitlines():
+        # 删除整行的空注释
+        if l.lstrip().startswith("%"):
+            pass
+        else:
+            new_file_remove_comment_lines.append(l)
+    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
+    return main_file
+
+def merge_tex_files_(project_foler, main_file, mode):
+    """
+    Merge Tex project recrusively
+    """
+    main_file = rm_comments(main_file)
+    for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
+        f = s.group(1)
+        fp = os.path.join(project_foler, f)
+        if os.path.exists(fp):  
+            # e.g., \input{srcs/07_appendix.tex}
+            with open(fp, 'r', encoding='utf-8', errors='replace') as fx:
+                c = fx.read()
+        else:  
+            # e.g., \input{srcs/07_appendix}
+            with open(fp+'.tex', 'r', encoding='utf-8', errors='replace') as fx:
+                c = fx.read()
+        c = merge_tex_files_(project_foler, c, mode)
+        main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
+    return main_file
+
+def merge_tex_files(project_foler, main_file, mode):
+    """
+    Merge Tex project recrusively
+    P.S. 顺便把CTEX塞进去以支持中文
+    P.S. 顺便把Latex的注释去除
+    """
+    main_file = merge_tex_files_(project_foler, main_file, mode)
+    main_file = rm_comments(main_file)
+
+    if mode == 'translate_zh':
+        # find paper documentclass
+        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 ''
+        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)
+        # find paper abstract
+        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!"
+    return main_file
+
+
+
+"""
+========================================================================
+Post process
+========================================================================
+"""
+def mod_inbraket(match):
+    """
+    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 = 'BOOM'
+    return "\\" + cmd + "{" + str_to_modify + "}"
+
+def fix_content(final_tex, node_string):
+    """
+    Fix common GPT errors to increase success rate
+    """
+    final_tex = re.sub(r"(?<!\\)%", "\\%", final_tex)
+    final_tex = re.sub(r"\\([a-z]{2,10})\ \{", r"\\\1{", string=final_tex)
+    final_tex = re.sub(r"\\\ ([a-z]{2,10})\{", r"\\\1{", string=final_tex)
+    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('\_'):
+        # walk and replace any _ without \
+        final_tex = re.sub(r"(?<!\\)_", "\\_", final_tex)
+
+    def compute_brace_level(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
+        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]
+                p += 1
+            return None, None
+        while True:
+            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
+            p_o = res1 + 1
+            p_t = res2 + 1
+        return tex_t[:p_t] + tex_o[p_o:]
+
+    if compute_brace_level(final_tex) != compute_brace_level(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 split_subprocess(txt, project_folder, return_dict, opts):
+    """
+    break down latex file to a linked list,
+    each node use a preserve flag to indicate whether it should
+    be proccessed by GPT.
+    """
+    text = txt
+    mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
+
+    # 吸收title与作者以上的部分
+    text, mask = set_forbidden_text(text, mask, r"(.*?)\\maketitle", re.DOTALL)
+    # 吸收iffalse注释
+    text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
+    # 吸收在42行以内的begin-end组合
+    text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
+    # 吸收匿名公式
+    text, mask = set_forbidden_text(text, mask, [ r"\$\$(.*?)\$\$",  r"\\\[.*?\\\]" ], re.DOTALL)
+    # 吸收其他杂项
+    text, mask = set_forbidden_text(text, mask, [ r"\\section\{(.*?)\}", r"\\section\*\{(.*?)\}", r"\\subsection\{(.*?)\}", r"\\subsubsection\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, [ r"\\bibliography\{(.*?)\}", r"\\bibliographystyle\{(.*?)\}" ])
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{thebibliography\}.*?\\end\{thebibliography\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{lstlisting\}(.*?)\\end\{lstlisting\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{wraptable\}(.*?)\\end\{wraptable\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{wrapfigure\}(.*?)\\end\{wrapfigure\}", r"\\begin\{wrapfigure\*\}(.*?)\\end\{wrapfigure\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{figure\}(.*?)\\end\{figure\}", r"\\begin\{figure\*\}(.*?)\\end\{figure\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{multline\}(.*?)\\end\{multline\}", r"\\begin\{multline\*\}(.*?)\\end\{multline\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{table\}(.*?)\\end\{table\}", r"\\begin\{table\*\}(.*?)\\end\{table\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{minipage\}(.*?)\\end\{minipage\}", r"\\begin\{minipage\*\}(.*?)\\end\{minipage\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{align\*\}(.*?)\\end\{align\*\}", r"\\begin\{align\}(.*?)\\end\{align\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\begin\{equation\}(.*?)\\end\{equation\}", r"\\begin\{equation\*\}(.*?)\\end\{equation\*\}"], re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, [r"\\includepdf\[(.*?)\]\{(.*?)\}", r"\\clearpage", r"\\newpage", r"\\appendix", r"\\tableofcontents", r"\\include\{(.*?)\}"])
+    text, mask = set_forbidden_text(text, mask, [r"\\vspace\{(.*?)\}", r"\\hspace\{(.*?)\}", r"\\label\{(.*?)\}", r"\\begin\{(.*?)\}", r"\\end\{(.*?)\}", r"\\item "])
+    text, mask = set_forbidden_text_careful_brace(text, mask, r"\\hl\{(.*?)\}", re.DOTALL)
+    # reverse 操作必须放在最后
+    text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\caption\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    text, mask = reverse_forbidden_text_careful_brace(text, mask, r"\\abstract\{(.*?)\}", re.DOTALL, forbid_wrapper=True)
+    text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
+    root = convert_to_linklist(text, mask)
+
+    # 修复括号
+    node = root
+    while True:
+        string = node.string
+        if node.preserve: 
+            node = node.next
+            if node is None: break
+            continue
+        def break_check(string):
+            str_stack = [""] # (lv, index)
+            for i, c in enumerate(string):
+                if c == '{':
+                    str_stack.append('{')
+                elif c == '}':
+                    if len(str_stack) == 1:
+                        print('stack fix')
+                        return i
+                    str_stack.pop(-1)
+                else:
+                    str_stack[-1] += c
+            return -1
+        bp = break_check(string)
+
+        if bp == -1:
+            pass
+        elif bp == 0:
+            node.string = string[:1]
+            q = LinkedListNode(string[1:], False)
+            q.next = node.next
+            node.next = q
+        else:
+            node.string = string[:bp]
+            q = LinkedListNode(string[bp:], False)
+            q.next = node.next
+            node.next = q
+
+        node = node.next
+        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
+        node = node.next
+        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
+
+    # 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_)]
+                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
+                node.string = rstriped_
+        # =====
+        prev_node = node
+        node = node.next
+        if node is None: break
+    # 输出html调试文件，用红色标注处保留区（PRESERVE），用黑色标注转换区（TRANSFORM）
+    with open(pj(project_folder, 'debug_log.html'), 'w', encoding='utf8') as f:
+        segment_parts_for_gpt = []
+        nodes = []
+        node = root
+        while True:
+            nodes.append(node)
+            show_html = node.string.replace('\n','<br/>')
+            if not node.preserve:
+                segment_parts_for_gpt.append(node.string)
+                f.write(f'<p style="color:black;">#{show_html}#</p>')
+            else:
+                f.write(f'<p style="color:red;">{show_html}</p>')
+            node = node.next
+            if node is None: break
+
+    for n in nodes: n.next = None   # break
+    return_dict['nodes'] = nodes
+    return_dict['segment_parts_for_gpt'] = segment_parts_for_gpt
+    return return_dict
+
+
+
+class LatexPaperSplit():
+    """
+    break down latex file to a linked list,
+    each node use a preserve flag to indicate whether it should
+    be proccessed by GPT.
+    """
+    def __init__(self) -> None:
+        self.nodes = None
+        self.msg = "*{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
+            "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。}}\\\\" 
+
+    def merge_result(self, arr, mode, msg):
+        """
+        Merge the result after the GPT process completed
+        """
+        result_string = ""
+        p = 0
+        for node in self.nodes:
+            if node.preserve:
+                result_string += node.string
+            else:
+                result_string += fix_content(arr[p], node.string)
+                p += 1
+        if mode == 'translate_zh':
+            pattern = re.compile(r'\\begin\{abstract\}.*\n')
+            match = pattern.search(result_string)
+            if not match:
+                # match \abstract{xxxx}
+                pattern_compile = re.compile(r"\\abstract\{(.*?)\}", flags=re.DOTALL)
+                match = pattern_compile.search(result_string)
+                position = match.regs[1][0]
+            else:
+                # match \begin{abstract}xxxx\end{abstract}
+                position = match.end()
+            result_string = result_string[:position] + self.msg + msg + self.msg_declare + result_string[position:]
+        return result_string
+
+    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
+        be proccessed by GPT.
+        P.S. use multiprocessing to avoid timeout error
+        """
+        import multiprocessing
+        manager = multiprocessing.Manager()
+        return_dict = manager.dict()
+        p = multiprocessing.Process(
+            target=split_subprocess, 
+            args=(txt, project_folder, return_dict, opts))
+        p.start()
+        p.join()
+        p.close()
+        self.nodes = return_dict['nodes']
+        self.sp = return_dict['segment_parts_for_gpt']
+        return self.sp
+
+
+
+class LatexPaperFileGroup():
+    """
+    use tokenizer to break down text according to max_token_limit
+    """
+    def __init__(self):
+        self.file_paths = []
+        self.file_contents = []
+        self.sp_file_contents = []
+        self.sp_file_index = []
+        self.sp_file_tag = []
+
+        # count_token
+        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=()))
+        self.get_token_num = get_token_num
+
+    def run_file_split(self, max_token_limit=1900):
+        """
+        use tokenizer to break down text according to max_token_limit
+        """
+        for index, file_content in enumerate(self.file_contents):
+            if self.get_token_num(file_content) < max_token_limit:
+                self.sp_file_contents.append(file_content)
+                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)
+                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))]
+        for r, k in zip(self.sp_file_result, self.sp_file_index):
+            self.file_result[k] += r
+
+    def write_result(self):
+        manifest = []
+        for path, res in zip(self.file_paths, self.file_result):
+            with open(path + '.polish.tex', 'w', encoding='utf8') as f:
+                manifest.append(path + '.polish.tex')
+                f.write(res)
+        return manifest
+
+def write_html(sp_file_contents, sp_file_result, chatbot, project_folder):
+
+    # write html
+    try:
+        import shutil
+        from .crazy_utils import construct_html
+        from toolbox import gen_time_str
+        ch = construct_html() 
+        orig = ""
+        trans = ""
+        final = []
+        for c,r in zip(sp_file_contents, sp_file_result): 
+            final.append(c)
+            final.append(r)
+        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"{gen_time_str()}.trans.html"
+        ch.save_file(create_report_file_name)
+        shutil.copyfile(pj('./gpt_log/', create_report_file_name), pj(project_folder, create_report_file_name))
+        promote_file_to_downloadzone(file=f'./gpt_log/{create_report_file_name}', chatbot=chatbot)
+    except:
+        from toolbox import trimmed_format_exc
+        print('writing html result failed:', trimmed_format_exc())
+
+def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, mode='proofread', switch_prompt=None, opts=[]):
+    import time, os, re
+    from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from .latex_utils import LatexPaperFileGroup, merge_tex_files, LatexPaperSplit, 寻找Latex主文件
+
+    #  <-------- 寻找主tex文件 ----------> 
+    maintex = 寻找Latex主文件(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 ----------> 
+    main_tex_basename = os.path.basename(maintex)
+    assert main_tex_basename.endswith('.tex')
+    main_tex_basename_bare = main_tex_basename[:-4]
+    may_exist_bbl = pj(project_folder, f'{main_tex_basename_bare}.bbl')
+    if os.path.exists(may_exist_bbl):
+        shutil.copyfile(may_exist_bbl, pj(project_folder, f'merge.bbl'))
+        shutil.copyfile(may_exist_bbl, pj(project_folder, f'merge_{mode}.bbl'))
+        shutil.copyfile(may_exist_bbl, pj(project_folder, f'merge_diff.bbl'))
+
+    with open(maintex, 'r', encoding='utf-8', errors='replace') as f:
+        content = f.read()
+        merged_content = merge_tex_files(project_folder, content, mode)
+
+    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 ----------> 
+    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()
+    res = lps.split(merged_content, project_folder, opts) # 消耗时间的函数
+
+    #  <-------- 拆分过长的latex片段 ----------> 
+    pfg = LatexPaperFileGroup()
+    for index, r in enumerate(res):
+        pfg.file_paths.append('segment-' + str(index))
+        pfg.file_contents.append(r)
+
+    pfg.run_file_split(max_token_limit=1024)
+    n_split = len(pfg.sp_file_contents)
+
+    #  <-------- 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 ----------> 
+        pfg = objload(file=pj(project_folder,'temp.pkl'))
+
+    else:
+        #  <-------- gpt 多线程请求 ----------> 
+        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)],
+            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 ----------> 
+        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 ----------> 
+        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 ----------> 
+    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)
+    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 ----------> 
+    chatbot.append((f"完成了吗？", 'GPT结果已输出, 正在编译PDF'))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    #  <-------- 返回 ----------> 
+    return project_folder + f'/merge_{mode}.tex'
+
+
+
+def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified):
+    try:
+        with open(log_path, 'r', encoding='utf-8', errors='replace') as f:
+            log = f.read()
+        with open(file_path, 'r', encoding='utf-8', errors='replace') as f:
+            file_lines = f.readlines()
+        import re
+        buggy_lines = re.findall(tex_name+':([0-9]{1,5}):', log)
+        buggy_lines = [int(l) for l in buggy_lines]
+        buggy_lines = sorted(buggy_lines)
+        print("removing lines that has errors", buggy_lines)
+        file_lines.pop(buggy_lines[0]-1)
+        with open(pj(work_folder_modified, f"{tex_name_pure}_fix_{n_fix}.tex"), 'w', encoding='utf-8', errors='replace') as f:
+            f.writelines(file_lines)
+        return True, f"{tex_name_pure}_fix_{n_fix}", buggy_lines
+    except:
+        print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
+        return False, -1, [-1]
+    
+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)
+    try:
+        stdout, stderr = process.communicate(timeout=timeout)
+    except subprocess.TimeoutExpired:
+        process.kill()
+        stdout, stderr = process.communicate()
+        print("Process timed out!")
+        return False
+    return True
+
+def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder, mode='default'):
+    import os, time
+    current_dir = os.getcwd()
+    n_fix = 1
+    max_try = 32
+    chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
+    chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
+    yield from update_ui_lastest_msg('编译已经开始...', chatbot, history)   # 刷新Gradio前端界面
+
+    while True:
+        import os
+
+        # https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
+        yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history)   # 刷新Gradio前端界面
+        ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+
+        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
+            if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_original}.aux', work_folder_original)
+            if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
+                ok = compile_latex_with_timeout(f'bibtex  {main_file_modified}.aux', work_folder_modified)
+
+            yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history)  # 刷新Gradio前端界面
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
+            ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
+
+            if mode!='translate_zh':
+                yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
+                print(    f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
+                ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
+
+                yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux', work_folder)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+                ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
+
+
+        # <---------- 检查结果 ----------->
+        results_ = ""
+        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};" 
+        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
+            result_pdf = pj(work_folder_modified, f'{main_file_modified}.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
+            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'), 
+                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}',
+                n_fix=n_fix,
+                work_folder_modified=work_folder_modified,
+            )
+            yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history)   # 刷新Gradio前端界面
+            if not can_retry: break
+
+    return False # 失败啦
+
+
+

crazy_functions/live_audio/aliyunASR.py

@@ -0,0 +1,261 @@
+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():
+
+    def test_on_sentence_begin(self, message, *args):
+        # print("test_on_sentence_begin:{}".format(message))
+        pass
+
+    def test_on_sentence_end(self, message, *args):
+        # print("test_on_sentence_end:{}".format(message))
+        message = json.loads(message)
+        self.parsed_sentence = message['payload']['result']
+        self.event_on_entence_end.set()
+        # print(self.parsed_sentence)
+
+    def test_on_start(self, message, *args):
+        # print("test_on_start:{}".format(message))
+        pass
+
+    def test_on_error(self, message, *args):
+        logging.error("on_error args=>{}".format(args))
+        pass
+
+    def test_on_close(self, *args):
+        self.aliyun_service_ok = False
+        pass
+
+    def test_on_result_chg(self, message, *args):
+        # print("test_on_chg:{}".format(message))
+        message = json.loads(message)
+        self.parsed_text = message['payload']['result']
+        self.event_on_result_chg.set()
+
+    def test_on_completed(self, message, *args):
+        # print("on_completed:args=>{} message=>{}".format(args, message))
+        pass
+
+    def audio_convertion_thread(self, uuid):
+        # 在一个异步线程中采集音频
+        import nls  # pip install git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+        import tempfile
+        from scipy import io
+        from toolbox import get_conf
+        from .audio_io import change_sample_rate
+        from .audio_io import RealtimeAudioDistribution
+        NEW_SAMPLERATE = 16000
+        rad = RealtimeAudioDistribution()
+        rad.clean_up()
+        temp_folder = tempfile.gettempdir()
+        TOKEN, APPKEY = get_conf('ALIYUN_TOKEN', 'ALIYUN_APPKEY')
+        if len(TOKEN) == 0:
+            TOKEN = self.get_token()
+        self.aliyun_service_ok = True
+        URL="wss://nls-gateway.aliyuncs.com/ws/v1"
+        sr = nls.NlsSpeechTranscriber(
+                    url=URL,
+                    token=TOKEN,
+                    appkey=APPKEY,
+                    on_sentence_begin=self.test_on_sentence_begin,
+                    on_sentence_end=self.test_on_sentence_end,
+                    on_start=self.test_on_start,
+                    on_result_changed=self.test_on_result_chg,
+                    on_completed=self.test_on_completed,
+                    on_error=self.test_on_error,
+                    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) 
+            if audio is not None:
+                # convert to pcm file
+                temp_file = f'{temp_folder}/{uuid.hex}.pcm' # 
+                dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
+                write_numpy_to_wave(temp_file, NEW_SAMPLERATE, dsdata)
+                # read pcm binary
+                with open(temp_file, "rb") as f: data = f.read()
+                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)
+
+            if not self.aliyun_service_ok:
+                self.stop = True
+                self.stop_msg = 'Aliyun音频服务异常，请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期。'
+        r = sr.stop()
+
+    def get_token(self):
+        from toolbox import get_conf
+        import json
+        from aliyunsdkcore.request import CommonRequest
+        from aliyunsdkcore.client import AcsClient
+        AccessKey_ID, AccessKey_secret = get_conf('ALIYUN_ACCESSKEY', 'ALIYUN_SECRET')
+
+        # 创建AcsClient实例
+        client = AcsClient(
+            AccessKey_ID,
+            AccessKey_secret,
+            "cn-shanghai"
+        )
+
+        # 创建request，并设置参数。
+        request = CommonRequest()
+        request.set_method('POST')
+        request.set_domain('nls-meta.cn-shanghai.aliyuncs.com')
+        request.set_version('2019-02-28')
+        request.set_action_name('CreateToken')
+
+        try:
+            response = client.do_action_with_exception(request)
+            print(response)
+            jss = json.loads(response)
+            if 'Token' in jss and 'Id' in jss['Token']:
+                token = jss['Token']['Id']
+                expireTime = jss['Token']['ExpireTime']
+                print("token = " + token)
+                print("expireTime = " + str(expireTime))
+        except Exception as e:
+            print(e)
+
+        return token

crazy_functions/live_audio/audio_io.py

@@ -0,0 +1,51 @@
+import numpy as np
+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
+
+
+@Singleton
+class RealtimeAudioDistribution():
+    def __init__(self) -> None:
+        self.data = {}
+        self.max_len = 1024*1024
+        self.rate = 48000   # 只读，每秒采样数量
+
+    def clean_up(self):
+        self.data = {}
+
+    def feed(self, uuid, audio):
+        self.rate, audio_ = audio
+        # print('feed', len(audio_), audio_[-25:])
+        if uuid not in self.data:
+            self.data[uuid] = audio_
+        else:
+            new_arr = np.concatenate((self.data[uuid], audio_))
+            if len(new_arr) > self.max_len: new_arr = new_arr[-self.max_len:]
+            self.data[uuid] = new_arr
+
+    def read(self, uuid):
+        if uuid in self.data:
+            res = self.data.pop(uuid)
+            # 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
+
+    time_old  = np.linspace(0, duration, audio.shape[0])
+    time_new  = np.linspace(0, duration, int(audio.shape[0] * new_sr / old_sr))
+
+    interpolator = interpolate.interp1d(time_old, audio.T)
+    new_audio = interpolator(time_new).T
+    return new_audio.astype(np.int16)

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

@@ -0,0 +1,171 @@
+from functools import lru_cache
+from toolbox import gen_time_str
+from toolbox import promote_file_to_downloadzone
+from toolbox import write_history_to_file, promote_file_to_downloadzone
+from toolbox import get_conf
+from toolbox import ProxyNetworkActivate
+from colorful import *
+import requests
+import random
+import copy
+import os
+import math
+
+class GROBID_OFFLINE_EXCEPTION(Exception): pass
+
+def get_avail_grobid_url():
+    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
+        if _grobid_url.endswith('/'): _grobid_url = _grobid_url.rstrip('/')
+        with ProxyNetworkActivate('Connect_Grobid'):
+            res = requests.get(_grobid_url+'/api/isalive')
+        if res.text=='true': return _grobid_url
+        else: return None
+    except:
+        return None
+
+@lru_cache(maxsize=32)
+def parse_pdf(pdf_path, grobid_url):
+    import scipdf   # pip install scipdf_parser
+    if grobid_url.endswith('/'): grobid_url = grobid_url.rstrip('/')
+    try:
+        with ProxyNetworkActivate('Connect_Grobid'):
+            article_dict = scipdf.parse_pdf_to_dict(pdf_path, grobid_url=grobid_url)
+    except GROBID_OFFLINE_EXCEPTION:
+        raise GROBID_OFFLINE_EXCEPTION("GROBID服务不可用，请修改config中的GROBID_URL，可修改成本地GROBID服务。")
+    except:
+        raise RuntimeError("解析PDF失败，请检查PDF是否损坏。")
+    return article_dict
+
+
+def produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files):
+    # -=-=-=-=-=-=-=-= 写出第1个文件：翻译前后混合 -=-=-=-=-=-=-=-=
+    res_path = write_history_to_file(meta +  ["# Meta Translation" , paper_meta_info] + gpt_response_collection, file_basename=f"{gen_time_str()}translated_and_original.md", file_fullname=None)
+    promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
+    generated_conclusion_files.append(res_path)
+
+    # -=-=-=-=-=-=-=-= 写出第2个文件：仅翻译后的文本 -=-=-=-=-=-=-=-=
+    translated_res_array = []
+    # 记录当前的大章节标题：
+    last_section_name = ""
+    for index, value in enumerate(gpt_response_collection):
+        # 先挑选偶数序列号：
+        if index % 2 != 0:
+            # 先提取当前英文标题：
+            cur_section_name = gpt_response_collection[index-1].split('\n')[0].split(" Part")[0]
+            # 如果index是1的话，则直接使用first section name：
+            if cur_section_name != last_section_name:
+                cur_value = cur_section_name + '\n'
+                last_section_name = copy.deepcopy(cur_section_name)
+            else:
+                cur_value = ""
+            # 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", 
+                                     file_fullname = None,
+                                     auto_caption = False)
+    promote_file_to_downloadzone(res_path, rename_file=os.path.basename(res_path)+'.md', chatbot=chatbot)
+    generated_conclusion_files.append(res_path)
+    return res_path
+
+def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_files, TOKEN_LIMIT_PER_FRAGMENT, DST_LANG):
+    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
+
+    prompt = "以下是一篇学术论文的基本信息:\n"
+    # 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')[: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
+    prompt += f"请将题目和摘要翻译为{DST_LANG}。"
+    meta = [f'# Title:\n\n', title, f'# Abstract:\n\n', abstract ]
+
+    # 单线，获取文章meta信息
+    paper_meta_info = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=prompt,
+        inputs_show_user=prompt,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot, history=[],
+        sys_prompt="You are an academic paper reader。",
+    )
+
+    # 多线，翻译
+    inputs_array = []
+    inputs_show_user_array = []
+
+    # get_token_num
+    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=()))
+
+    def break_down(txt):
+        raw_token_num = get_token_num(txt)
+        if raw_token_num <= TOKEN_LIMIT_PER_FRAGMENT:
+            return [txt]
+        else:
+            # raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
+            # 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_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
+        section_frags = break_down(section['text'])
+        for i, fragment in enumerate(section_frags):
+            heading = section['heading']
+            if len(section_frags) > 1: heading += f' Part-{i+1}'
+            inputs_array.append(
+                f"你需要翻译{heading}章节，内容如下: \n\n{fragment}"
+            )
+            inputs_show_user_array.append(
+                f"# {heading}\n\n{fragment}"
+            )
+
+    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=[meta for _ in inputs_array],
+        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 inputs_array],
+    )
+    # -=-=-=-=-=-=-=-= 写出Markdown文件 -=-=-=-=-=-=-=-=
+    produce_report_markdown(gpt_response_collection, meta, paper_meta_info, chatbot, fp, generated_conclusion_files)
+
+    # -=-=-=-=-=-=-=-= 写出HTML文件 -=-=-=-=-=-=-=-=
+    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] = inputs_show_user_array[i//2]
+        else:
+            # 先提取当前英文标题：
+            cur_section_name = gpt_response_collection[i-1].split('\n')[0].split(" Part")[0]
+            cur_value = cur_section_name + "\n" + gpt_response_collection_html[i]
+            gpt_response_collection_html[i] = cur_value
+
+    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): 
+        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"
+    html_file = ch.save_file(create_report_file_name)
+    generated_conclusion_files.append(html_file)
+    promote_file_to_downloadzone(html_file, rename_file=os.path.basename(html_file), chatbot=chatbot)

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/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

@@ -0,0 +1,114 @@
+from pydantic import BaseModel, Field
+from typing import List
+from toolbox import update_ui_lastest_msg, disable_auto_promotion
+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
+
+
+def read_avail_plugin_enum():
+    from crazy_functional import get_crazy_functions
+    plugin_arr = get_crazy_functions()
+    # remove plugins with out explaination
+    plugin_arr = {k:v for k, v in plugin_arr.items() if 'Info' in v}
+    plugin_arr_info = {"F_{:04d}".format(i):v["Info"] for i, v in enumerate(plugin_arr.values(), start=1)}
+    plugin_arr_dict = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
+    plugin_arr_dict_parse = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
+    plugin_arr_dict_parse.update({f"F_{i}":v for i, v in enumerate(plugin_arr.values(), start=1)})
+    prompt = json.dumps(plugin_arr_info, ensure_ascii=False, indent=2)
+    prompt = "\n\nThe defination of PluginEnum:\nPluginEnum=" + prompt
+    return prompt, plugin_arr_dict, plugin_arr_dict_parse
+
+def wrap_code(txt):
+    txt = txt.replace('```','')
+    return f"\n```\n{txt}\n```\n"
+
+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']
+    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." 
+    return prompt
+
+def get_inputs_show_user(inputs, plugin_arr_enum_prompt):
+    # remove plugin_arr_enum_prompt from inputs string
+    inputs_show_user = inputs.replace(plugin_arr_enum_prompt, "")
+    inputs_show_user += plugin_arr_enum_prompt[:200] + '...'
+    inputs_show_user += '\n...\n'
+    inputs_show_user += '...\n'
+    inputs_show_user += '...}'
+    return inputs_show_user
+
+def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
+    plugin_arr_enum_prompt, plugin_arr_dict, plugin_arr_dict_parse = read_avail_plugin_enum()
+    class Plugin(BaseModel):
+        plugin_selection: str = Field(description="The most related plugin from one of the PluginEnum.", default="F_0000")
+        reason_of_selection: str = Field(description="The reason why you should select this plugin.", default="This plugin satisfy user requirement most")
+    # ⭐ ⭐ ⭐ 选择插件
+    yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n查找可用插件中...", chatbot=chatbot, history=history, delay=0)
+    gpt_json_io = GptJsonIO(Plugin)
+    gpt_json_io.format_instructions = "The format of your output should be a json that can be parsed by json.loads.\n"
+    gpt_json_io.format_instructions += """Output example: {"plugin_selection":"F_1234", "reason_of_selection":"F_1234 plugin satisfy user requirement most"}\n"""
+    gpt_json_io.format_instructions += "The plugins you are authorized to use are listed below:\n"
+    gpt_json_io.format_instructions += plugin_arr_enum_prompt
+    inputs = "Choose the correct plugin according to user requirements, the user requirement is: \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=[])
+    try:
+        gpt_reply = run_gpt_fn(inputs, "")
+        plugin_sel = gpt_json_io.generate_output_auto_repair(gpt_reply, run_gpt_fn)
+    except JsonStringError:
+        msg = f"抱歉, {llm_kwargs['llm_model']}无法理解您的需求。"
+        msg += "请求的Prompt为：\n" + wrap_code(get_inputs_show_user(inputs, plugin_arr_enum_prompt))
+        msg += "语言模型回复为：\n" + wrap_code(gpt_reply)
+        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
+    if plugin_sel.plugin_selection not in plugin_arr_dict_parse:
+        msg = f"抱歉, 找不到合适插件执行该任务, 或者{llm_kwargs['llm_model']}无法理解您的需求。"
+        msg += f"语言模型{llm_kwargs['llm_model']}选择了不存在的插件：\n" + wrap_code(gpt_reply)
+        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 = ""
+    else:
+        appendix_info = get_recent_file_prompt_support(chatbot)
+
+    plugin = plugin_arr_dict_parse[plugin_sel.plugin_selection]
+    yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n提取插件参数...", chatbot=chatbot, history=history, delay=0)
+    class PluginExplicit(BaseModel):
+        plugin_selection: str = plugin_sel.plugin_selection
+        plugin_arg: str = Field(description="The argument of the plugin.", default="")
+    gpt_json_io = GptJsonIO(PluginExplicit)
+    gpt_json_io.format_instructions += "The information about this plugin is:" + plugin["Info"]
+    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 
+    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)
+
+
+    # ⭐ ⭐ ⭐ 执行插件
+    fn = plugin['Function']
+    fn_name = fn.__name__
+    msg = f'{llm_kwargs["llm_model"]}为您选择了插件: `{fn_name}`\n\n插件说明：{plugin["Info"]}\n\n插件参数：{plugin_sel.plugin_arg}\n\n假如偏离了您的要求，按停止键终止。'
+    yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
+    yield from fn(plugin_sel.plugin_arg, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, -1)
+    return

crazy_functions/vt_fns/vt_modify_config.py

@@ -0,0 +1,81 @@
+from pydantic import BaseModel, Field
+from typing import List
+from toolbox import update_ui_lastest_msg, get_conf
+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')
+    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。", 
+            chatbot=chatbot, history=history, delay=2
+        )
+        return
+
+    # ⭐ ⭐ ⭐ 读取可配置项目条目
+    names = {}
+    from enum import Enum
+    import config
+    for k, v in config.__dict__.items():
+        if k.startswith('__'): continue
+        names.update({k:k})
+        # if len(names) > 20: break   # 限制最多前10个配置项，如果太多了会导致gpt无法理解
+
+    ConfigOptions = Enum('ConfigOptions', names)
+    class ModifyConfigurationIntention(BaseModel):
+        which_config_to_modify: ConfigOptions = Field(description="the name of the configuration to modify, you must choose from one of the ConfigOptions enum.", default=None)
+        new_option_value: str = Field(description="the new value of the option", default=None)
+
+    # ⭐ ⭐ ⭐ 分析用户意图
+    yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n读取新配置中", chatbot=chatbot, history=history, delay=0)
+    gpt_json_io = GptJsonIO(ModifyConfigurationIntention)
+    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)
+
+    explicit_conf = user_intention.which_config_to_modify.value
+
+    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}", 
+            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", 
+            chatbot=chatbot, history=history, delay=2
+        )
+
+        # ⭐ ⭐ ⭐ 立即应用配置
+        from toolbox import set_conf
+        set_conf(explicit_conf, user_intention.new_option_value)
+
+        yield from update_ui_lastest_msg(
+            lastmsg=f"正在执行任务: {txt}\n\n配置修改完成，重新页面即可生效。", chatbot=chatbot, history=history, delay=1
+        )
+    else:
+        yield from update_ui_lastest_msg(
+            lastmsg=f"失败，如果需要配置{explicit_conf}，您需要明确说明并在指令中提到它。", chatbot=chatbot, history=history, delay=5
+        )
+
+def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
+    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。", 
+            chatbot=chatbot, history=history, delay=2
+        )
+        return
+
+    yield from modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention)
+    yield from update_ui_lastest_msg(
+        lastmsg=f"正在执行任务: {txt}\n\n配置修改完成，五秒后即将重启！若出现报错请无视即可。", chatbot=chatbot, history=history, delay=5
+    )
+    os.execl(sys.executable, sys.executable, *sys.argv)

crazy_functions/vt_fns/vt_state.py

@@ -0,0 +1,28 @@
+import pickle
+
+class VoidTerminalState():
+    def __init__(self):
+        self.reset_state()
+
+    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)
+
+    def unlock_plugin(self, chatbot):
+        self.reset_state()
+        chatbot._cookies['lock_plugin'] = None
+        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):
+        state = chatbot._cookies.get('plugin_state', None)
+        if state is not None:   state = pickle.loads(state)
+        else:                   state = VoidTerminalState()
+        state.chatbot = chatbot
+        return state

crazy_functions/下载arxiv论文翻译摘要.py

@@ -1,5 +1,6 @@
-from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file, get_conf
+from toolbox import update_ui, get_log_folder
+from toolbox import write_history_to_file, promote_file_to_downloadzone
+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):
@@ -28,7 +29,7 @@ def download_arxiv_(url_pdf):
         if k in other_info['comment']:
             title = k + ' ' + title
 
-    download_dir = './gpt_log/arxiv/'
+    download_dir = get_log_folder(plugin_name='arxiv')
     os.makedirs(download_dir, exist_ok=True)
 
     title_str = title.replace('?', '？')\
@@ -40,12 +41,9 @@ def download_arxiv_(url_pdf):
 
     requests_pdf_url = url_pdf
     file_path = download_dir+title_str
-    # if os.path.exists(file_path):
-    #     print('返回缓存文件')
-    #     return './gpt_log/arxiv/'+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)
@@ -61,7 +59,7 @@ def download_arxiv_(url_pdf):
         .replace('\n', '')\
         .replace('  ', ' ')\
         .replace('  ', ' ')
-    return './gpt_log/arxiv/'+title_str, other_info
+    return file_path, other_info
 
 
 def get_name(_url_):
@@ -79,7 +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')
@@ -132,7 +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
@@ -144,11 +142,11 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
-        import pdfminer, bs4
+        import bs4
     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 pdfminer beautifulsoup4```。")
+            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
 
@@ -159,7 +157,7 @@ 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, 
+        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
@@ -184,11 +182,10 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
     chatbot[-1] = (i_say_show_user, gpt_say)
     history.append(i_say_show_user); history.append(gpt_say)
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-    # 写入文件
-    import shutil
-    # 重置文件的创建时间
-    shutil.copyfile(pdf_path, f'./gpt_log/{os.path.basename(pdf_path)}'); os.remove(pdf_path)
-    res = write_results_to_file(history)
+    res = write_history_to_file(history)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
+    promote_file_to_downloadzone(pdf_path, chatbot=chatbot)
+
     chatbot.append(("完成了吗？", res + "\n\nPDF文件也已经下载"))
     yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
 

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

@@ -0,0 +1,63 @@
+from toolbox import CatchException, update_ui
+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, 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, 如温度和top_p等, 一般原样传递下去就行
+    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(("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。"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    state = chatbot._cookies.get('plugin_state_0001', None) # 初始化插件状态
+
+    if state is None:
+        chatbot._cookies['lock_plugin'] = 'crazy_functions.交互功能函数模板->交互功能模板函数'      # 赋予插件锁定 锁定插件回调路径，当下一次用户提交时，会直接转到该函数
+        chatbot._cookies['plugin_state_0001'] = 'wait_user_keyword'                              # 赋予插件状态
+
+        chatbot.append(("第一次调用：", "请输入关键词, 我将为您查找相关壁纸, 建议使用英文单词, 插件锁定中，请直接提交即可。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    if state == 'wait_user_keyword':
+        chatbot._cookies['lock_plugin'] = None          # 解除插件锁定，避免遗忘导致死锁
+        chatbot._cookies['plugin_state_0001'] = None    # 解除插件状态，避免遗忘导致死锁
+
+        # 解除插件锁定
+        chatbot.append((f"获取关键词：{txt}", ""))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        page_return = get_image_page_by_keyword(txt)
+        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=[], 
+            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]
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+
+
+# ---------------------------------------------------------------------------------
+
+def get_image_page_by_keyword(keyword):
+    import requests
+    from bs4 import BeautifulSoup
+    response = requests.get(f'https://wallhaven.cc/search?q={keyword}', timeout=2)
+    res = "image urls: \n"
+    for image_element in BeautifulSoup(response.content, 'html.parser').findAll("img"):
+        try:
+            res += image_element["data-src"]
+            res += "\n"
+        except:
+            pass
+    return res

crazy_functions/函数动态生成.py

@@ -0,0 +1,252 @@
+# 本源代码中, ⭐ = 关键步骤
+"""
+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
+
+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.
+"""
+
+
+from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
+from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
+from .crazy_utils import input_clipping, try_install_deps
+from crazy_functions.gen_fns.gen_fns_shared import is_function_successfully_generated
+from crazy_functions.gen_fns.gen_fns_shared import get_class_name
+from crazy_functions.gen_fns.gen_fns_shared import subprocess_worker
+from crazy_functions.gen_fns.gen_fns_shared import try_make_module
+import os
+import time
+import glob
+import multiprocessing
+
+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 world-class 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. 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, 
+    #     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 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 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 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
+    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
+    user_request    当前用户的请求信息（IP地址等）
+    """
+
+    # 清空历史
+    history = []
+
+    # 基本信息：功能、贡献者
+    chatbot.append(["正在启动: 插件动态生成插件", "插件动态生成, 执行开始, 作者Binary-Husky."])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # ⭐ 文件上传区是否有东西
+    # 1. 如果有文件: 作为函数参数
+    # 2. 如果没有文件：需要用GPT提取参数 （太懒了，以后再写，虚空终端已经实现了类似的代码）
+    file_list = []
+    if get_plugin_arg(plugin_kwargs, key="file_path_arg", default=False):
+        file_path = get_plugin_arg(plugin_kwargs, key="file_path_arg", default=None)
+        file_list.append(file_path)
+        yield from update_ui_lastest_msg(f"当前文件: {file_path}", chatbot, history, 1)
+    elif have_any_recent_upload_files(chatbot):
+        file_dir = get_recent_file_prompt_support(chatbot)
+        file_list = glob.glob(os.path.join(file_dir, '**/*'), recursive=True)
+        yield from update_ui_lastest_msg(f"当前文件处理列表: {file_list}", chatbot, history, 1)
+    else:
+        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
+    if len(file_list) == 0:
+        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]
+
+    # 粗心检查
+    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
+        traceback = ""
+        try:
+            # ⭐ 开始啦 ！
+            code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
+                yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
+            chatbot.append(["代码生成阶段结束", ""])
+            yield from update_ui_lastest_msg(f"正在验证上述代码的有效性 ...", chatbot, history, 1)
+            # ⭐ 分离代码块
+            code = get_code_block(code)
+            # ⭐ 检查模块
+            ok, traceback = try_make_module(code, chatbot)
+            # 搞定代码生成
+            if ok: break
+        except Exception as e:
+            if not traceback: traceback = trimmed_format_exc()
+        # 处理异常
+        if not traceback: traceback = trimmed_format_exc()
+        yield from update_ui_lastest_msg(f"第 {j+1}/{MAX_TRY} 次代码生成尝试, 失败了~ 别担心, 我们5秒后再试一次... \n\n此次我们的错误追踪是\n```\n{traceback}\n```\n", chatbot, history, 5)
+
+    # 代码生成结束, 开始执行
+    TIME_LIMIT = 15
+    yield from update_ui_lastest_msg(f"开始创建新进程并执行代码! 时间限制 {TIME_LIMIT} 秒. 请等待任务完成... ", chatbot, history, 1)
+    manager = multiprocessing.Manager()
+    return_dict = manager.dict()
+
+    # ⭐ 到最后一步了，开始逐个文件进行处理
+    for file_path in file_list:
+        if os.path.exists(file_path):
+            chatbot.append([f"正在处理文件: {file_path}", f"请稍等..."])
+            chatbot = for_immediate_show_off_when_possible(file_type, file_path, chatbot)
+            yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+        else:
+            continue
+
+        # ⭐⭐⭐ subprocess_worker ⭐⭐⭐
+        p = multiprocessing.Process(target=subprocess_worker, args=(code, file_path, return_dict))
+        # ⭐ 开始执行，时间限制TIME_LIMIT
+        p.start(); p.join(timeout=TIME_LIMIT)
+        if p.is_alive(): p.terminate(); p.join()
+        p.close()
+        res = return_dict['result']
+        success = return_dict['success']
+        traceback = return_dict['traceback']
+        if not success:
+            if not traceback: traceback = trimmed_format_exc()
+            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   
+

crazy_functions/命令行助手.py

@@ -0,0 +1,31 @@
+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 copy, json
+
+@CatchException
+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
+    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
+    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 = []
+
+    # 输入
+    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=[], 
+        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

@@ -0,0 +1,276 @@
+from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log_folder
+from crazy_functions.multi_stage.multi_stage_utils import GptAcademicState
+
+
+def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", quality=None, style=None):
+    import requests, json, time, os
+    from request_llms.bridge_all import model_info
+
+    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'
+    img_endpoint = chat_endpoint.replace('chat/completions','images/generations')
+    # # Generate the image
+    url = img_endpoint
+    headers = {
+        'Authorization': f"Bearer {api_key}",
+        'Content-Type': 'application/json'
+    }
+    data = {
+        '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:
+        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
+
+
+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_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
+    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
+    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", '1024x1024')
+    image_url, image_path = gen_image(llm_kwargs, prompt, 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
+
+
+@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

@@ -1,32 +1,75 @@
-from toolbox import CatchException, update_ui
-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
 
-def write_chat_to_file(chatbot, file_name=None):
+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。
     """
     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'
-    os.makedirs('./gpt_log/', exist_ok=True)
-    with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
+        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>')
         for i, contents in enumerate(chatbot):
-            for content in contents:
+            for j, content in enumerate(contents):
                 try:    # 这个bug没找到触发条件，暂时先这样顶一下
                     if type(content) != str: content = str(content)
                 except:
                     continue
                 f.write(content)
-                f.write('\n\n')
+                if j == 0:
+                    f.write('<hr style="border-top: dotted 3px #ccc;">')
             f.write('<hr color="red"> \n\n')
+        f.write('<hr color="blue"> \n\n raw chat context:\n')
+        f.write('<code>')
+        for h in history:
+            f.write("\n>>>" + h)
+        f.write('</code>')
+    promote_file_to_downloadzone(fp, rename_file=file_name, chatbot=chatbot)
+    return '对话历史写入：' + fp
 
-    res = '对话历史写入：' + os.path.abspath(f'./gpt_log/{file_name}')
-    print(res)
-    return res
+def gen_file_preview(file_name):
+    try:
+        with open(file_name, 'r', encoding='utf8') as f:
+            file_content = f.read()
+        # pattern to match the text between <head> and </head>
+        pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
+        file_content = re.sub(pattern, '', file_content)
+        html, history = file_content.split('<hr color="blue"> \n\n raw chat context:\n')
+        history = history.strip('<code>')
+        history = history.strip('</code>')
+        history = history.split("\n>>>")
+        return list(filter(lambda x:x!="", history))[0][:100]
+    except:
+        return ""
+
+def read_file_to_chat(chatbot, history, file_name):
+    with open(file_name, 'r', encoding='utf8') as f:
+        file_content = f.read()
+    # pattern to match the text between <head> and </head>
+    pattern = re.compile(r'<head>.*?</head>', flags=re.DOTALL)
+    file_content = re.sub(pattern, '', file_content)
+    html, history = file_content.split('<hr color="blue"> \n\n raw chat context:\n')
+    history = history.strip('<code>')
+    history = history.strip('</code>')
+    history = history.split("\n>>>")
+    history = list(filter(lambda x:x!="", history))
+    html = html.split('<hr color="red"> \n\n')
+    html = list(filter(lambda x:x!="", html))
+    chatbot.clear()
+    for i, h in enumerate(html):
+        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    
 
 @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
@@ -34,9 +77,76 @@ 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)}"))
+    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):
+    import os
+    current_path = os.getcwd()
+    replace_path = "."
+    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, 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
+    system_prompt   给gpt的静默提醒
+    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')
+
+    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(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
+
+    try:
+        chatbot, history = read_file_to_chat(chatbot, history, file_manifest[0])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    except:
+        chatbot.append([f"载入对话历史文件", f"对话历史文件损坏！"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+@CatchException
+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
+    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
+    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(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
+    return
+
+

crazy_functions/总结word文档.py

@@ -1,5 +1,6 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+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
 
@@ -14,29 +15,26 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             doc = Document(fp)
             file_content = "\n".join([para.text for para in doc.paragraphs])
         else:
-            import win32com.client
-            word = win32com.client.Dispatch("Word.Application")
-            word.visible = False
-            # 打开文件
-            print('fp', os.getcwd())
-            doc = word.Documents.Open(os.getcwd() + '/' + fp)
-            # file_content = doc.Content.Text
-            doc = word.ActiveDocument
-            file_content = doc.Range().Text
-            doc.Close()
-            word.Quit()
+            try:
+                import win32com.client
+                word = win32com.client.Dispatch("Word.Application")
+                word.visible = False
+                # 打开文件
+                doc = word.Documents.Open(os.getcwd() + '/' + fp)
+                # file_content = doc.Content.Text
+                doc = word.ActiveDocument
+                file_content = doc.Range().Text
+                doc.Close()
+                word.Quit()
+            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}```'
@@ -69,30 +67,32 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             history.extend([i_say,gpt_say])
             this_paper_history.extend([i_say,gpt_say])
 
-        res = write_results_to_file(history)
+        res = write_history_to_file(history)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
         chatbot.append(("完成了吗？", res))
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-    res = write_results_to_file(history)
+    res = write_history_to_file(history)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
     chatbot.append(("所有文件都总结完成了吗？", res))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
 
 @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
     chatbot.append([
         "函数插件功能？",
-        "批量总结Word文档。函数插件贡献者: JasonGuo1"])
+        "批量总结Word文档。函数插件贡献者: JasonGuo1。注意, 如果是.doc文件, 请先转化为.docx格式。"])
     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:
         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
@@ -106,7 +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
 
@@ -119,7 +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

@@ -0,0 +1,186 @@
+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
+
+def split_audio_file(filename, split_duration=1000):
+    """
+    根据给定的切割时长将音频文件切割成多个片段。
+
+    Args:
+        filename (str): 需要被切割的音频文件名。
+        split_duration (int, optional): 每个切割音频片段的时长（以秒为单位）。默认值为1000。
+
+    Returns:
+        filelist (list): 一个包含所有切割音频片段文件路径的列表。
+
+    """
+    from moviepy.editor import AudioFileClip
+    import os
+    os.makedirs(f"{get_log_folder(plugin_name='audio')}/mp3/cut/", exist_ok=True)  # 创建存储切割音频的文件夹
+
+    # 读取音频文件
+    audio = AudioFileClip(filename)
+
+    # 计算文件总时长和切割点
+    total_duration = audio.duration
+    split_points = list(range(0, int(total_duration), split_duration))
+    split_points.append(int(total_duration))
+    filelist = []
+
+    # 切割音频文件
+    for i in range(len(split_points) - 1):
+        start_time = split_points[i]
+        end_time = split_points[i + 1]
+        split_audio = audio.subclip(start_time, end_time)
+        split_audio.write_audiofile(f"{get_log_folder(plugin_name='audio')}/mp3/cut/{filename[0]}_{i}.mp3")
+        filelist.append(f"{get_log_folder(plugin_name='audio')}/mp3/cut/{filename[0]}_{i}.mp3")
+
+    audio.close()
+    return filelist
+
+def AnalyAudio(parse_prompt, file_manifest, llm_kwargs, chatbot, history):
+    import os, requests
+    from moviepy.editor import AudioFileClip
+    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'])
+    chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+
+    whisper_endpoint = chat_endpoint.replace('chat/completions', 'audio/transcriptions')
+    url = whisper_endpoint
+    headers = {
+        'Authorization': f"Bearer {api_key}"
+    }
+
+    os.makedirs(f"{get_log_folder(plugin_name='audio')}/mp3/", exist_ok=True)
+    for index, fp in enumerate(file_manifest):
+        audio_history = []
+        # 提取文件扩展名
+        ext = os.path.splitext(fp)[1]
+        # 提取视频中的音频
+        if ext not in [".mp3", ".wav", ".m4a", ".mpga"]:
+            audio_clip = AudioFileClip(fp)
+            audio_clip.write_audiofile(f"{get_log_folder(plugin_name='audio')}/mp3/output{index}.mp3")
+            fp = f"{get_log_folder(plugin_name='audio')}/mp3/output{index}.mp3"
+        # 调用whisper模型音频转文字
+        voice = split_audio_file(fp)
+        for j, i in enumerate(voice):
+            with open(i, 'rb') as f:
+                file_content = f.read()  # 读取文件内容到内存
+                files = {
+                    'file': (os.path.basename(i), file_content),
+                }
+                data = {
+                    "model": "whisper-1",
+                    "prompt": parse_prompt,
+                    'response_format': "text"
+                }
+
+            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')
+            response = requests.post(url, headers=headers, files=files, data=data, proxies=proxies).text
+
+            chatbot.append(["音频解析结果", response])
+            history.extend(["音频解析结果", response])
+            yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+            i_say = f'请对下面的音频片段做概述，音频内容是 ```{response}```'
+            i_say_show_user = f'第{index + 1}段音频的第{j + 1} / {len(voice)}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,
+                llm_kwargs=llm_kwargs,
+                chatbot=chatbot,
+                history=[],
+                sys_prompt=f"总结音频。音频文件名{fp}"
+            )
+
+            chatbot[-1] = (i_say_show_user, gpt_say)
+            history.extend([i_say_show_user, gpt_say])
+            audio_history.extend([i_say_show_user, gpt_say])
+
+        # 已经对该文章的所有片段总结完毕，如果文章被切分了
+        result = "".join(audio_history)
+        if len(audio_history) > 1:
+            i_say = f"根据以上的对话，使用中文总结音频“{result}”的主要内容。"
+            i_say_show_user = f'第{index + 1}段音频的主要内容：'
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+                inputs=i_say,
+                inputs_show_user=i_say_show_user,
+                llm_kwargs=llm_kwargs,
+                chatbot=chatbot,
+                history=audio_history,
+                sys_prompt="总结文章。"
+            )
+            history.extend([i_say, gpt_say])
+            audio_history.extend([i_say, gpt_say])
+
+        res = write_history_to_file(history)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
+        chatbot.append((f"第{index + 1}段音频完成了吗？", res))
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    # 删除中间文件夹
+    import shutil
+    shutil.rmtree(f"{get_log_folder(plugin_name='audio')}/mp3")
+    res = write_history_to_file(history)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
+    chatbot.append(("所有音频都总结完成了吗？", res))
+    yield from update_ui(chatbot=chatbot, history=history)
+
+
+@CatchException
+def 总结音视频(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, WEB_PORT):
+    import glob, os
+
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "总结音视频内容，函数插件贡献者: dalvqw & BinaryHusky"])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+    try:
+        from moviepy.editor import AudioFileClip
+    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 moviepy```。")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # 清空历史，以免输入溢出
+    history = []
+
+    # 检测输入参数，如没有给定输入参数，直接退出
+    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
+
+    # 搜索需要处理的文件清单
+    extensions = ['.mp4', '.m4a', '.wav', '.mpga', '.mpeg', '.mp3', '.avi', '.mkv', '.flac', '.aac']
+
+    if txt.endswith(tuple(extensions)):
+        file_manifest = [txt]
+    else:
+        file_manifest = []
+        for extension in extensions:
+            file_manifest.extend(glob.glob(f'{project_folder}/**/*{extension}', recursive=True))
+
+    # 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"找不到任何音频或视频文件: {txt}")
+        yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+        return
+
+    # 开始正式执行任务
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    parse_prompt = plugin_kwargs.get("advanced_arg", '将音频解析为简体中文')
+    yield from AnalyAudio(parse_prompt, file_manifest, llm_kwargs, chatbot, history)
+
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面

crazy_functions/批量Markdown翻译.py

@@ -1,5 +1,7 @@
-from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+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_exception, get_log_folder
+from toolbox import write_history_to_file, promote_file_to_downloadzone
 fast_debug = False
 
 class PaperFileGroup():
@@ -11,7 +13,7 @@ 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
@@ -26,17 +28,29 @@ 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)
                     self.sp_file_tag.append(self.file_paths[index] + f".part-{j}.md")
+        logging.info('Segmentation: done')
 
-        print('Segmentation: done')
+    def merge_result(self):
+        self.file_result = ["" for _ in range(len(self.file_paths))]
+        for r, k in zip(self.sp_file_result, self.sp_file_index):
+            self.file_result[k] += r
+
+    def write_result(self, language):
+        manifest = []
+        for path, res in zip(self.file_paths, self.file_result):
+            dst_file = os.path.join(get_log_folder(), f'{gen_time_str()}.md')
+            with open(dst_file, 'w', encoding='utf8') as f:
+                manifest.append(dst_file)
+                f.write(res)
+        return manifest
 
 def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, language='en'):
-    import time, os, re
     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 ----------> 
@@ -53,7 +67,7 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
     pfg.run_file_split(max_token_limit=1500)
     n_split = len(pfg.sp_file_contents)
 
-    #  <-------- 多线程润色开始 ----------> 
+    #  <-------- 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:" + 
                         f"\n\n{frag}" for frag in pfg.sp_file_contents]
@@ -64,6 +78,11 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
                         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:" + 
+                        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)]
 
     gpt_response_collection = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         inputs_array=inputs_array,
@@ -75,30 +94,48 @@ def 多文件翻译(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
         # max_workers=5,  # OpenAI所允许的最大并行过载
         scroller_max_len = 80
     )
+    try:
+        pfg.sp_file_result = []
+        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)
+    except:
+        logging.error(trimmed_format_exc())
 
     #  <-------- 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_results_to_file(gpt_response_collection, file_name=create_report_file_name)
+    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)
     history = gpt_response_collection
     chatbot.append((f"{fp}完成了吗？", res))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
 
-def get_files_from_everything(txt):
-    import glob, os
-
+def get_files_from_everything(txt, preference=''):
+    if txt == "": return False, None, None
     success = True
     if txt.startswith('http'):
-        # 网络的远程文件
-        txt = txt.replace("https://github.com/", "https://raw.githubusercontent.com/")
-        txt = txt.replace("/blob/", "/")
         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 ...')
+            if not txt.endswith('.md'):
+                # Make a request to the GitHub API to retrieve the repository information
+                url = txt.replace("https://github.com/", "https://api.github.com/repos/") + '/readme'
+                response = requests.get(url, proxies=proxies)
+                txt = response.json()['download_url']
+            else:
+                txt = txt.replace("https://github.com/", "https://raw.githubusercontent.com/")
+                txt = txt.replace("/blob/", "/")
+
         r = requests.get(txt, proxies=proxies)
-        with open('./gpt_log/temp.md', 'wb+') as f: f.write(r.content)
-        project_folder = './gpt_log/'
-        file_manifest = ['./gpt_log/temp.md']
+        download_local = f'{get_log_folder(plugin_name="批量Markdown翻译")}/raw-readme-{gen_time_str()}.md'
+        project_folder = f'{get_log_folder(plugin_name="批量Markdown翻译")}'
+        with open(download_local, 'wb+') as f: f.write(r.content)
+        file_manifest = [download_local]
     elif txt.endswith('.md'):
         # 直接给定文件
         file_manifest = [txt]
@@ -108,42 +145,44 @@ def get_files_from_everything(txt):
         project_folder = txt
         file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.md', recursive=True)]
     else:
+        project_folder = None
+        file_manifest = []
         success = False
 
     return success, file_manifest, project_folder
 
 
 @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
-        import glob, os
     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
         return
     history = []    # 清空历史，以免输入溢出
 
-    success, file_manifest, project_folder = get_files_from_everything(txt)
+    success, file_manifest, project_folder = get_files_from_everything(txt, preference="Github")
 
     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
 
@@ -154,19 +193,19 @@ 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
-        import glob, os
     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
@@ -176,11 +215,47 @@ 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, 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_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
+        return
+    history = []    # 清空历史，以免输入溢出
+    success, file_manifest, project_folder = get_files_from_everything(txt)
+    if not success:
+        # 什么都没有
+        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
+    if len(file_manifest) == 0:
+        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

@@ -1,125 +1,107 @@
-from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
-import re
-import unicodedata
-fast_debug = False
+from toolbox import update_ui, promote_file_to_downloadzone, gen_time_str
+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
+from .crazy_utils import input_clipping
 
-def is_paragraph_break(match):
-    """
-    根据给定的匹配结果来判断换行符是否表示段落分隔。
-    如果换行符前为句子结束标志（句号，感叹号，问号），且下一个字符为大写字母，则换行符更有可能表示段落分隔。
-    也可以根据之前的内容长度来判断段落是否已经足够长。
-    """
-    prev_char, next_char = match.groups()
 
-    # 句子结束标志
-    sentence_endings = ".!?"
-
-    # 设定一个最小段落长度阈值
-    min_paragraph_length = 140
-
-    if prev_char in sentence_endings and next_char.isupper() and len(match.string[:match.start(1)]) > min_paragraph_length:
-        return "\n\n" 
-    else:
-        return " "
-
-def normalize_text(text):
-    """
-    通过把连字（ligatures）等文本特殊符号转换为其基本形式来对文本进行归一化处理。
-    例如，将连字 "fi" 转换为 "f" 和 "i"。
-    """
-    # 对文本进行归一化处理，分解连字
-    normalized_text = unicodedata.normalize("NFKD", text)
-
-    # 替换其他特殊字符
-    cleaned_text = re.sub(r'[^\x00-\x7F]+', '', normalized_text)
-
-    return cleaned_text
-
-def clean_text(raw_text):
-    """
-    对从 PDF 提取出的原始文本进行清洗和格式化处理。
-    1. 对原始文本进行归一化处理。
-    2. 替换跨行的连词，例如 “Espe-\ncially” 转换为 “Especially”。
-    3. 根据 heuristic 规则判断换行符是否是段落分隔，并相应地进行替换。
-    """
-    # 对文本进行归一化处理
-    normalized_text = normalize_text(raw_text)
-
-    # 替换跨行的连词
-    text = re.sub(r'(\w+-\n\w+)', lambda m: m.group(1).replace('-\n', ''), normalized_text)
-
-    # 根据前后相邻字符的特点，找到原文本中的换行符
-    newlines = re.compile(r'(\S)\n(\S)')
-
-    # 根据 heuristic 规则，用空格或段落分隔符替换原换行符
-    final_text = re.sub(newlines, lambda m: m.group(1) + is_paragraph_break(m) + m.group(2), text)
-
-    return final_text.strip()
 
 def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    import time, glob, os, fitz
-    print('begin analysis on:', file_manifest)
-    for index, fp in enumerate(file_manifest):
-        with fitz.open(fp) as doc:
-            file_content = ""
-            for page in doc:
-                file_content += page.get_text()
-            file_content = clean_text(file_content)
-            print(file_content)
+    file_write_buffer = []
+    for file_name in file_manifest:
+        print('begin analysis on:', file_name)
+        ############################## <第 0 步，切割PDF> ##################################
+        # 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
+        # 的长度必须小于 2500 个 Token
+        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
         
-        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
-        i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
-        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        TOKEN_LIMIT_PER_FRAGMENT = 2500
 
-        if not fast_debug: 
-            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, 
-                llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
-                history=[],
-                sys_prompt="总结文章。"
-            )  # 带超时倒计时
+        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)
 
-            chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-            if not fast_debug: time.sleep(2)
+        ############################## <第 2 步，迭代地历遍整个文章，提取精炼信息> ##################################
+        i_say_show_user = f'首先你在中文语境下通读整篇论文。'; 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
 
-    all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
-    i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
-    chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        iteration_results = []
+        last_iteration_result = paper_meta  # 初始值是摘要
+        MAX_WORD_TOTAL = 4096 * 0.7
+        n_fragment = len(paper_fragments)
+        if n_fragment >= 20: print('文章极长，不能达到预期效果')
+        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} 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, 
+                                                                                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
 
-    if not fast_debug: 
-        msg = '正常'
-        # ** gpt request **
+        ############################## <第 3 步，整理history，提取总结> ##################################
+        final_results.extend(iteration_results)
+        final_results.append(f'Please conclude this paper discussed above。')
+        # This prompt is from https://github.com/kaixindelele/ChatPaper/blob/main/chat_paper.py
+        NUM_OF_WORD = 1000
+        i_say = """
+1. Mark the title of the paper (with Chinese translation)
+2. list all the authors' names (use English)
+3. mark the first author's affiliation (output Chinese translation only)
+4. mark the keywords of this article (use English)
+5. link to the paper, Github code link (if available, fill in Github:None if not)
+6. summarize according to the following four points.Be sure to use Chinese answers (proper nouns need to be marked in English)
+    - (1):What is the research background of this article?
+    - (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:                  
+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 
+    - (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,
+do not have too much repetitive information, numerical values using the original numbers.
+        """
+        # This prompt is from https://github.com/kaixindelele/ChatPaper/blob/main/chat_paper.py
+        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=i_say, 
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot, 
-            history=history,
-            sys_prompt="总结文章。"
-        )  # 带超时倒计时
+            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)
+        file_write_buffer.extend([i_say, gpt_say])
+        ############################## <第 4 步，设置一个token上限> ##################################
+        _, final_results = input_clipping("", final_results, max_token_limit=3200)
+        yield from update_ui(chatbot=chatbot, history=final_results) # 注意这里的历史记录被替代了
 
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-        res = write_results_to_file(history)
-        chatbot.append(("完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+    res = write_history_to_file(file_write_buffer)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
+    yield from update_ui(chatbot=chatbot, history=final_results) # 刷新界面
 
 
 @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
@@ -132,7 +114,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     try:
         import fitz
     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 pymupdf```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
@@ -146,19 +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)] # + \
-                    # [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)]
+    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

@@ -1,6 +1,7 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+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
 
 fast_debug = False
 
@@ -115,14 +116,15 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
         chatbot[-1] = (i_say, gpt_say)
         history.append(i_say); history.append(gpt_say)
         yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-        res = write_results_to_file(history)
+        res = write_history_to_file(history)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
         chatbot.append(("完成了吗？", res))
         yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
 
 
 
 @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
 
@@ -136,7 +138,7 @@ 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, 
+        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
@@ -145,7 +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)] + \
@@ -153,7 +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

@@ -0,0 +1,125 @@
+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
+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
+import logging
+
+def markdown_to_dict(article_content):
+    import markdown
+    from bs4 import BeautifulSoup
+    cur_t = ""
+    cur_c = ""
+    results = {}
+    for line in article_content:
+        if line.startswith('#'):
+            if cur_t!="":
+                if cur_t not in results:
+                    results.update({cur_t:cur_c.lstrip('\n')})
+                else:
+                    # 处理重名的章节
+                    results.update({cur_t + " " + gen_time_str():cur_c.lstrip('\n')})
+            cur_t = line.rstrip('\n')
+            cur_c = ""
+        else:
+            cur_c += line
+    results_final = {}
+    for k in list(results.keys()):
+        if k.startswith('# '):
+            results_final['title'] = k.split('# ')[-1]
+            results_final['authors'] = results.pop(k).lstrip('\n')
+        if k.startswith('###### Abstract'):
+            results_final['abstract'] = results.pop(k).lstrip('\n')
+
+    results_final_sections = []
+    for k,v in results.items():
+        results_final_sections.append({
+            'heading':k.lstrip("# "),
+            'text':v if len(v) > 0 else f"The beginning of {k.lstrip('# ')} section."
+        })
+    results_final['sections'] = results_final_sections
+    return results_final
+
+
+@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([
+        "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
+
+    # 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_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
+    yield from 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+
+
+
+
+def 解析PDF_基于NOUGAT(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+    import copy
+    import tiktoken
+    TOKEN_LIMIT_PER_FRAGMENT = 1024
+    generated_conclusion_files = []
+    generated_html_files = []
+    DST_LANG = "中文"
+    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):
+        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)
+        logging.info(article_dict)
+        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
+
+

crazy_functions/批量翻译PDF文档_多线程.py

@@ -1,15 +1,18 @@
-from toolbox import CatchException, report_execption, write_results_to_file
-from toolbox import update_ui
+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
 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 os
+
 
 @CatchException
-def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt, web_port):
-    import glob
-    import os
+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([
         "函数插件功能？",
@@ -18,63 +21,79 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, sys_
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
-        import fitz
-        import tiktoken
+        check_packages(["fitz", "tiktoken", "scipdf"])
     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 pymupdf tiktoken```。")
+                         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 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
-
-    # 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)]
+    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
 
     # 开始正式执行任务
-    yield from 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt)
+    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(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, sys_prompt):
-    import os
-    import tiktoken
-    TOKEN_LIMIT_PER_FRAGMENT = 1280
+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_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=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]
@@ -100,32 +119,59 @@ def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot,
                 "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): 
+        for i,k in enumerate(gpt_response_collection_md): 
             if i%2==0:
-                gpt_response_collection[i] = f"\n\n---\n\n ## 原文[{i//2}/{len(gpt_response_collection)//2}]： \n\n {paper_fragments[i//2].replace('#', '')}  \n\n---\n\n ## 翻译[{i//2}/{len(gpt_response_collection)//2}]：\n "
+                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[i] = gpt_response_collection[i]
+                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)
+        final.extend(gpt_response_collection_md)
         create_report_file_name = f"{os.path.basename(fp)}.trans.md"
-        res = write_results_to_file(final, file_name=create_report_file_name)
+        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'./gpt_log/{create_report_file_name}')
+        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
-    import shutil
     for pdf_path in generated_conclusion_files:
         # 重命名文件
-        rename_file = f'./gpt_log/总结论文-{os.path.basename(pdf_path)}'
-        if os.path.exists(rename_file):
-            os.remove(rename_file)
-        shutil.copyfile(pdf_path, rename_file)
-        if os.path.exists(pdf_path):
-            os.remove(pdf_path)
-    chatbot.append(("给出输出文件清单", str(generated_conclusion_files)))
+        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

@@ -0,0 +1,191 @@
+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
+    try:
+        import manim
+        return True
+    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 manim manimgl```"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return False
+
+def eval_manim(code):
+    import subprocess, sys, os, shutil
+
+    with open('gpt_log/MyAnimation.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)
+
+    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(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: 
+        print('generating mp4 failed')
+        return "Generating mp4 failed."
+
+
+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: 
+        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, 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
+    system_prompt   给gpt的静默提醒
+    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 = []    
+
+    # 基本信息：功能、贡献者
+    chatbot.append([
+        "函数插件功能？",
+        "生成数学动画, 此插件处于开发阶段, 建议暂时不要使用, 作者: binary-husky, 插件初始化中 ..."
+    ])
+    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
+    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, 
+        sys_prompt=
+        r"Write a animation script with 3blue1brown's manim. "+
+        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
+def examples_of_manim():
+    return r"""
+
+
+```
+
+class MovingGroupToDestination(Scene):
+    def construct(self):
+        group = VGroup(Dot(LEFT), Dot(ORIGIN), Dot(RIGHT, color=RED), Dot(2 * RIGHT)).scale(1.4)
+        dest = Dot([4, 3, 0], color=YELLOW)
+        self.add(group, dest)
+        self.play(group.animate.shift(dest.get_center() - group[2].get_center()))
+        self.wait(0.5)
+
+```
+
+
+```
+
+class LatexWithMovingFramebox(Scene):
+    def construct(self):
+        text=MathTex(
+            "\\frac{d}{dx}f(x)g(x)=","f(x)\\frac{d}{dx}g(x)","+",
+            "g(x)\\frac{d}{dx}f(x)"
+        )
+        self.play(Write(text))
+        framebox1 = SurroundingRectangle(text[1], buff = .1)
+        framebox2 = SurroundingRectangle(text[3], buff = .1)
+        self.play(
+            Create(framebox1),
+        )
+        self.wait()
+        self.play(
+            ReplacementTransform(framebox1,framebox2),
+        )
+        self.wait()
+
+```
+
+
+
+```
+
+class PointWithTrace(Scene):
+    def construct(self):
+        path = VMobject()
+        dot = Dot()
+        path.set_points_as_corners([dot.get_center(), dot.get_center()])
+        def update_path(path):
+            previous_path = path.copy()
+            previous_path.add_points_as_corners([dot.get_center()])
+            path.become(previous_path)
+        path.add_updater(update_path)
+        self.add(path, dot)
+        self.play(Rotating(dot, radians=PI, about_point=RIGHT, run_time=2))
+        self.wait()
+        self.play(dot.animate.shift(UP))
+        self.play(dot.animate.shift(LEFT))
+        self.wait()
+
+```
+
+```
+
+# do not use get_graph, this funciton is deprecated
+
+class ExampleFunctionGraph(Scene):
+    def construct(self):
+        cos_func = FunctionGraph(
+            lambda t: np.cos(t) + 0.5 * np.cos(7 * t) + (1 / 7) * np.cos(14 * t),
+            color=RED,
+        )
+
+        sin_func_1 = FunctionGraph(
+            lambda t: np.sin(t) + 0.5 * np.sin(7 * t) + (1 / 7) * np.sin(14 * t),
+            color=BLUE,
+        )
+
+        sin_func_2 = FunctionGraph(
+            lambda t: np.sin(t) + 0.5 * np.sin(7 * t) + (1 / 7) * np.sin(14 * t),
+            x_range=[-4, 4],
+            color=GREEN,
+        ).move_to([0, 1, 0])
+
+        self.add(cos_func, sin_func_1, sin_func_2)
+
+```
+"""

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
@@ -13,17 +13,14 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
     # 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
     # 的长度必须小于 2500 个 Token
     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]
     
@@ -43,11 +40,11 @@ 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, 
                                                                            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
@@ -66,7 +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
@@ -79,7 +76,7 @@ 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, 
+        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
@@ -94,7 +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
@@ -103,7 +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 +1,6 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+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
 
@@ -27,28 +28,29 @@ def 生成函数注释(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             if not fast_debug: time.sleep(2)
 
     if not fast_debug: 
-        res = write_results_to_file(history)
+        res = write_history_to_file(history)
+        promote_file_to_downloadzone(res, chatbot=chatbot)
         chatbot.append(("完成了吗？", res))
         yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
 
 
 
 @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

@@ -0,0 +1,117 @@
+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
+    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
+    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
+
+    # < --------------------读取参数--------------- >
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    kai_id = plugin_kwargs.get("advanced_arg", 'default')
+
+    chatbot.append((f"向`{kai_id}`知识库中添加文件。", "[Local Message] 从一批文件(txt, md, tex)中读取数据构建知识库, 然后进行问答。"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # resolve deps
+    try:
+        # 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", 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)
+        return
+
+    # < --------------------读取文件--------------- >
+    file_manifest = []
+    spl = ["txt", "doc", "docx", "email", "epub", "html", "json", "md", "msg", "pdf", "ppt", "pptx", "rtf"]
+    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
+    print('Checking Text2vec ...')
+    from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+    with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
+        HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
+
+    # < -------------------构建知识库--------------- >
+    chatbot.append(['<br/>'.join(file_manifest), "正在构建知识库..."])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    print('Establishing knowledge archive ...')
+    with ProxyNetworkActivate('Download_LLM'):    # 临时地激活代理网络
+        kai = knowledge_archive_interface()
+        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.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, user_request=-1):
+    # resolve deps
+    try:
+        # 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", 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)
+        return
+
+    # < -------------------  --------------- >
+    kai = knowledge_archive_interface()
+
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    kai_id = plugin_kwargs.get("advanced_arg", 'default')
+    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=[], 
+        sys_prompt=system_prompt
+    )
+    history.extend((prompt, gpt_say))
+    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

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
@@ -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
@@ -63,7 +63,7 @@ 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}", 
@@ -72,10 +72,14 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
 
     # ------------- < 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:
+        chatbot.append((f"结论：{txt}",
+                        "[Local Message] 受到google限制，无法从google获取信息！"))
+        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
+        return
     # ------------- < 第2步：依次访问网页 > -------------
     max_search_result = 5   # 最多收纳多少个网页的结果
     for index, url in enumerate(urls[:max_search_result]):

crazy_functions/联网的ChatGPT_bing版.py

@@ -0,0 +1,106 @@
+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_llms.bridge_all import model_info
+
+
+def bing_search(query, proxies=None):
+    query = query
+    url = f"https://cn.bing.com/search?q={query}"
+    headers = {'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'}
+    response = requests.get(url, headers=headers, proxies=proxies)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    results = []
+    for g in soup.find_all('li', class_='b_algo'):
+        anchors = g.find_all('a')
+        if anchors:
+            link = anchors[0]['href']
+            if not link.startswith('http'):
+                continue
+            title = g.find('h2').text
+            item = {'title': title, 'link': link}
+            results.append(item)
+
+    for r in results:
+        print(r['link'])
+    return results
+
+
+def scrape_text(url, proxies) -> str:
+    """Scrape text from a webpage
+
+    Args:
+        url (str): The URL to scrape text from
+
+    Returns:
+        str: The scraped text
+    """
+    headers = {
+        '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:
+        response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
+        if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
+    except:
+        return "无法连接到该网页"
+    soup = BeautifulSoup(response.text, "html.parser")
+    for script in soup(["script", "style"]):
+        script.extract()
+    text = soup.get_text()
+    lines = (line.strip() for line in text.splitlines())
+    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
+    text = "\n".join(chunk for chunk in chunks if chunk)
+    return text
+
+@CatchException
+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
+    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
+    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}",
+                    "[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')
+    urls = bing_search(txt, proxies)
+    history = []
+    if len(urls) == 0:
+        chatbot.append((f"结论：{txt}",
+                        "[Local Message] 受到bing限制，无法从bing获取信息！"))
+        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
+        return
+    # ------------- < 第2步：依次访问网页 > -------------
+    max_search_result = 8   # 最多收纳多少个网页的结果
+    for index, url in enumerate(urls[:max_search_result]):
+        res = scrape_text(url['link'], proxies)
+        history.extend([f"第{index}份搜索结果：", res])
+        chatbot.append([f"第{index}份搜索结果：", res[:500]+"......"])
+        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,
+        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,
+        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)
+    history.append(i_say);history.append(gpt_say)
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
+

crazy_functions/虚空终端.py

@@ -0,0 +1,180 @@
+"""
+Explanation of the Void Terminal Plugin:
+
+Please describe in natural language what you want to do.
+
+1. You can open the plugin's dropdown menu to explore various capabilities of this project, and then describe your needs in natural language, for example:
+- "Please call the plugin to translate a PDF paper for me. I just uploaded the paper to the upload area."
+- "Please use the plugin to translate a PDF paper, with the address being https://www.nature.com/articles/s41586-019-1724-z.pdf."
+- "Generate an image with blooming flowers and lush green grass using the plugin."
+- "Translate the README using the plugin. The GitHub URL is https://github.com/facebookresearch/co-tracker."
+- "Translate an Arxiv paper for me. The Arxiv ID is 1812.10695. Remember to use the plugin and don't do it manually!"
+- "I don't like the current interface color. Modify the configuration and change the theme to THEME="High-Contrast"."
+- "Could you please explain the structure of the Transformer network?"
+
+2. If you use keywords like "call the plugin xxx", "modify the configuration xxx", "please", etc., your intention can be recognized more accurately.
+
+3. Your intention can be recognized more accurately when using powerful models like GPT4. This plugin is relatively new, so please feel free to provide feedback on GitHub.
+
+4. Now, if you need to process a file, please upload the file (drag the file to the file upload area) or describe the path to the file.
+
+5. If you don't need to upload a file, you can simply repeat your command again.
+"""
+explain_msg = """
+## 虚空终端插件说明:
+
+1. 请用**自然语言**描述您需要做什么。例如：
+    - 「请调用插件，为我翻译PDF论文，论文我刚刚放到上传区了」
+    - 「请调用插件翻译PDF论文，地址为https://openreview.net/pdf?id=rJl0r3R9KX」
+    - 「把Arxiv论文翻译成中文PDF，arxiv论文的ID是1812.10695，记得用插件！」
+    - 「生成一张图片，图中鲜花怒放，绿草如茵，用插件实现」
+    - 「用插件翻译README，Github网址是https://github.com/facebookresearch/co-tracker」
+    - 「我不喜欢当前的界面颜色，修改配置，把主题THEME更换为THEME="High-Contrast"」
+    - 「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。    
+
+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。
+
+4. 建议使用 GPT3.5 或更强的模型，弱模型可能无法理解您的想法。该插件诞生时间不长，欢迎您前往Github反馈问题。
+
+5. 现在，如果需要处理文件，请您上传文件（将文件拖动到文件上传区），或者描述文件所在的路径。
+
+6. 如果不需要上传文件，现在您只需要再次重复一次您的指令即可。
+"""
+
+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_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
+from crazy_functions.vt_fns.vt_state import VoidTerminalState
+from crazy_functions.vt_fns.vt_modify_config import modify_configuration_hot
+from crazy_functions.vt_fns.vt_modify_config import modify_configuration_reboot
+from crazy_functions.vt_fns.vt_call_plugin import execute_plugin
+
+class UserIntention(BaseModel):
+    user_prompt: str = Field(description="the content of user input", default="")
+    intention_type: str = Field(description="the type of user intention, choose from ['ModifyConfiguration', 'ExecutePlugin', 'Chat']", default="ExecutePlugin")
+    user_provide_file: bool = Field(description="whether the user provides a path to a file", default=False)
+    user_provide_url: bool = Field(description="whether the user provides a url", default=False)
+
+
+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=[], 
+        sys_prompt=system_prompt
+    )
+    chatbot[-1] = [txt, gpt_say]
+    history.extend([txt, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    pass
+
+
+explain_intention_to_user = {
+    'Chat': "聊天对话",
+    'ExecutePlugin': "调用插件",
+    'ModifyConfiguration': "修改配置",
+}
+
+
+def analyze_intention_with_simple_rules(txt):
+    user_intention = UserIntention()
+    user_intention.user_prompt = txt
+    is_certain = False
+
+    if '请问' in txt:
+        is_certain = True
+        user_intention.intention_type = 'Chat'
+
+    if '用插件' in txt:
+        is_certain = True
+        user_intention.intention_type = 'ExecutePlugin'
+
+    if '修改配置' in txt:
+        is_certain = True
+        user_intention.intention_type = 'ModifyConfiguration'
+
+    return is_certain, user_intention
+
+
+@CatchException
+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)
+    appendix_msg = ""
+
+    # 用简单的关键词检测用户意图
+    is_certain, _ = analyze_intention_with_simple_rules(txt)
+    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, user_request)
+        return
+    else:
+        # 如果意图模糊，提示
+        state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
+        state.lock_plugin(chatbot=chatbot)
+        chatbot.append(("虚空终端状态:", explain_msg+appendix_msg))
+        yield from update_ui(chatbot=chatbot, history=history)
+        return
+
+
+
+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
+
+    # ⭐ ⭐ ⭐ 分析用户意图
+    is_certain, user_intention = analyze_intention_with_simple_rules(txt)
+    if not is_certain:
+        yield from update_ui_lastest_msg(
+            lastmsg=f"正在执行任务: {txt}\n\n分析用户意图中", chatbot=chatbot, history=history, delay=0)
+        gpt_json_io = GptJsonIO(UserIntention)
+        rf_req = "\nchoose from ['ModifyConfiguration', 'ExecutePlugin', 'Chat']"
+        inputs = "Analyze the intention of the user according to following user input: \n\n" + \
+            ">> " + (txt+rf_req).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=[])
+        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]}", 
+        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)
+            return
+    else:
+        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]}", 
+        chatbot=chatbot, history=history, delay=0)
+
+    # 用户意图: 修改本项目的配置
+    if user_intention.intention_type == 'ModifyConfiguration':
+        yield from modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention)
+
+    # 用户意图: 调度插件
+    if user_intention.intention_type == 'ExecutePlugin':
+        yield from execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention)
+
+    # 用户意图: 聊天
+    if user_intention.intention_type == 'Chat':
+        yield from chat(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention)
+
+    return
+

crazy_functions/解析JupyterNotebook.py

@@ -1,5 +1,6 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+from toolbox import CatchException, report_exception
+from toolbox import write_history_to_file, promote_file_to_downloadzone
 fast_debug = True
 
 
@@ -12,10 +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):
@@ -28,9 +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)
@@ -67,6 +66,7 @@ def parseNotebook(filename, enable_markdown=1):
 def ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
 
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
     enable_markdown = plugin_kwargs.get("advanced_arg", "1")
     try:
         enable_markdown = int(enable_markdown)
@@ -109,12 +109,13 @@ 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
 
     #  <-------- 写入文件，退出 ---------->
-    res = write_results_to_file(history)
+    res = write_history_to_file(history)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
     chatbot.append(("完成了吗？", res))
     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."])
@@ -128,7 +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
@@ -138,7 +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

@@ -1,12 +1,14 @@
-from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+from toolbox import update_ui, promote_file_to_downloadzone, disable_auto_promotion
+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):
     import os, copy
     from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
     from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-    msg = '正常'
+    disable_auto_promotion(chatbot=chatbot)
+
+    summary_batch_isolation = True
     inputs_array = []
     inputs_show_user_array = []
     history_array = []
@@ -21,7 +23,7 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
             file_content = f.read()
         prefix = "接下来请你逐文件分析下面的工程" if index==0 else ""
         i_say = prefix + f'请对下面的程序文件做一个概述文件名是{os.path.relpath(fp, project_folder)}，文件代码是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {os.path.abspath(fp)}'
+        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的程序文件做一个概述: {fp}'
         # 装载请求内容
         inputs_array.append(i_say)
         inputs_show_user_array.append(i_say_show_user)
@@ -42,7 +44,8 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
     # 全部文件解析完成，结果写入文件，准备对工程源代码进行汇总分析
     report_part_1 = copy.deepcopy(gpt_response_collection)
     history_to_return = report_part_1
-    res = write_results_to_file(report_part_1)
+    res = write_history_to_file(report_part_1)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
     chatbot.append(("完成？", "逐个文件分析已完成。" + res + "\n\n正在开始汇总。"))
     yield from update_ui(chatbot=chatbot, history=history_to_return) # 刷新界面
 
@@ -59,10 +62,17 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         # 把“请对下面的程序文件做一个概述” 替换成 精简的 "文件名：{all_file[index]}"
         for index, content in enumerate(this_iteration_gpt_response_collection):
             if index%2==0: this_iteration_gpt_response_collection[index] = f"{file_rel_path[index//2]}" # 只保留文件名节省token
-        previous_iteration_files.extend([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)])
+        this_iteration_files = [os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)]
+        previous_iteration_files.extend(this_iteration_files)
         previous_iteration_files_string = ', '.join(previous_iteration_files)
-        current_iteration_focus = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(this_iteration_file_manifest)])
-        i_say = f'用一张Markdown表格简要描述以下文件的功能：{previous_iteration_files_string}。根据以上分析，用一句话概括程序的整体功能。'
+        current_iteration_focus = ', '.join(this_iteration_files)
+        if summary_batch_isolation: focus = current_iteration_focus
+        else:                       focus = previous_iteration_files_string
+        i_say = f'用一张Markdown表格简要描述以下文件的功能：{focus}。根据以上分析，用一句话概括程序的整体功能。'
+        if last_iteration_result != "":
+            sys_prompt_additional = "已知某些代码的局部作用是:" + last_iteration_result + "\n请继续分析其他源代码，从而更全面地理解项目的整体功能。"
+        else:
+            sys_prompt_additional = ""
         inputs_show_user = f'根据以上分析，对程序的整体功能和构架重新做出概括，由于输入长度限制，可能需要分组处理，本组文件为 {current_iteration_focus} + 已经汇总的文件组。'
         this_iteration_history = copy.deepcopy(this_iteration_gpt_response_collection)
         this_iteration_history.append(last_iteration_result)
@@ -71,82 +81,112 @@ def 解析源代码新(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
         result = 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=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。")
-        report_part_2.extend([i_say, result])
-        last_iteration_result = result
+            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)
         
+        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, 
+            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)
+
+        report_part_2.extend([i_say, result])
+        last_iteration_result = summary_result
         file_manifest = file_manifest[batchsize:]
         gpt_response_collection = gpt_response_collection[batchsize*2:]
 
     ############################## <END> ##################################
     history_to_return.extend(report_part_2)
-    res = write_results_to_file(history_to_return)
+    res = write_history_to_file(history_to_return)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
     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') if ('test_project' not in f) and ('gpt_log' not in f)] + \
-                    [f for f in glob.glob('./crazy_functions/*.py') if ('test_project' not in f) and ('gpt_log' not in f)]+ \
-                    [f for f in glob.glob('./request_llm/*.py') if ('test_project' not in f) and ('gpt_log' not in f)]
+    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C项目的头文件(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_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, 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_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)]  + \
@@ -154,21 +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)] + \
@@ -176,44 +216,50 @@ 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Rect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)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.tsx', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.json', recursive=True)] + \
                     [f for f in glob.glob(f'{project_folder}/**/*.js', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.vue', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.less', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.sass', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.wxml', recursive=True)] + \
+                    [f for f in glob.glob(f'{project_folder}/**/*.wxss', recursive=True)] + \
+                    [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Rect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)] + \
@@ -221,21 +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, 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_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_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)] + \
@@ -243,34 +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)
@@ -291,7 +356,7 @@ 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
@@ -304,7 +369,7 @@ 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

@@ -1,23 +1,24 @@
-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
-    plugin_kwargs   插件模型的参数，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
+    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, 
@@ -31,22 +32,25 @@ 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
-    plugin_kwargs   插件模型的参数，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
+    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……"))
-    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")
     # 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'] = plugin_kwargs.get("advanced_arg", 'chatglm&gpt-3.5-turbo') # 'chatglm&gpt-3.5-turbo' # 支持任意数量的llm接口，用&符号分隔
+
+    chatbot.append((txt, f"正在同时咨询{llm_kwargs['llm_model']}"))
+    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, 

crazy_functions/语音助手.py

@@ -0,0 +1,192 @@
+from toolbox import update_ui
+from toolbox import CatchException, get_conf, markdown_convertion
+from crazy_functions.crazy_utils import input_clipping
+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
+
+
+def chatbot2history(chatbot):
+    history = []
+    for c in chatbot:
+        for q in c:
+            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 = []
+        self.observe_future_chatbot_index = []
+
+    def gpt_thread_worker(self, i_say, llm_kwargs, history, sys_prompt, observe_window, index):
+        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, 
+                                                            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)
+        except Exception as e:
+            print('至少一个线程任务意外失败', e)
+
+    def add_async_gpt_task(self, i_say, chatbot_index, llm_kwargs, history, system_prompt):
+        self.observe_future.append([""])
+        self.observe_future_chatbot_index.append(chatbot_index)
+        cur_index = len(self.observe_future)-1
+        th_new = threading.Thread(target=self.gpt_thread_worker, args=(i_say, llm_kwargs, history, system_prompt, self.observe_future, cur_index))
+        th_new.daemon = True
+        th_new.start()
+
+    def update_chatbot(self, chatbot):
+        for of, ofci in zip(self.observe_future, self.observe_future_chatbot_index):
+            try:
+                chatbot[ofci] = list(chatbot[ofci])
+                chatbot[ofci][1] = markdown_convertion(of[0])
+            except:
+                self.observe_future = []
+                self.observe_future_chatbot_index = []
+        return chatbot
+
+class InterviewAssistant(AliyunASR):
+    def __init__(self):
+        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.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()
+
+    def __del__(self):
+        self.stop = True
+        self.stop_msg = ""
+        self.commit_wd.kill_dog = True
+        self.plugin_wd.kill_dog = True
+
+    def init(self, chatbot):
+        # 初始化音频采集线程
+        self.captured_audio = np.array([])
+        self.keep_latest_n_second = 10
+        self.commit_after_pause_n_second = 2.0
+        self.ready_audio_flagment = None
+        self.stop = False
+        self.plugin_wd = WatchDog(timeout=5, bark_fn=self.__del__, msg="程序终止")
+        self.aut = threading.Thread(target=self.audio_convertion_thread, args=(chatbot._cookies['uuid'],))
+        self.aut.daemon = True
+        self.aut.start()
+        # th2 = threading.Thread(target=self.audio2txt_thread, args=(chatbot._cookies['uuid'],))
+        # th2.daemon = True
+        # th2.start()
+
+    def no_audio_for_a_while(self):
+        if len(self.buffered_sentence) < 7: # 如果一句话小于7个字，暂不提交
+            self.commit_wd.begin_watch()
+        else:
+            self.event_on_commit_question.set()
+
+    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 ]"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        self.plugin_wd.begin_watch()
+        self.agt = AsyncGptTask()
+        self.commit_wd = WatchDog(timeout=self.commit_after_pause_n_second, bark_fn=self.no_audio_for_a_while, interval=0.2)
+        self.commit_wd.begin_watch()
+
+        while not self.stop:
+            self.event_on_result_chg.wait(timeout=0.25)  # run once every 0.25 second
+            chatbot = self.agt.update_chatbot(chatbot)   # 将子线程的gpt结果写入chatbot
+            history = chatbot2history(chatbot)
+            yield from update_ui(chatbot=chatbot, history=history)      # 刷新界面
+            self.plugin_wd.feed()
+
+            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])
+                chatbot[-1][0] = self.buffered_sentence + self.parsed_text
+                history = chatbot2history(chatbot)
+                yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+                self.commit_wd.feed()
+
+            if self.event_on_entence_end.is_set():
+                # called when a sentence has ended
+                self.event_on_entence_end.clear()
+                self.parsed_text = self.parsed_sentence
+                self.buffered_sentence += self.parsed_text
+                chatbot[-1] = list(chatbot[-1])
+                chatbot[-1][0] = self.buffered_sentence
+                history = chatbot2history(chatbot)
+                yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+            if self.event_on_commit_question.is_set():
+                # called when a question should be commited
+                self.event_on_commit_question.clear()
+                if len(self.buffered_sentence) == 0: raise RuntimeError
+
+                self.commit_wd.begin_watch()
+                chatbot[-1] = list(chatbot[-1])
+                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 ]"])
+                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:
+            raise RuntimeError(self.stop_msg)
+
+
+
+@CatchException
+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
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        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 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
+
+    APPKEY = get_conf('ALIYUN_APPKEY')
+    if APPKEY == "":
+        chatbot.append(["导入依赖失败", "没有阿里云语音识别APPKEY和TOKEN, 详情见https://help.aliyun.com/document_detail/450255.html"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    ia = InterviewAssistant()
+    yield from ia.begin(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+

crazy_functions/读文章写摘要.py

@@ -1,7 +1,7 @@
 from toolbox import update_ui
-from toolbox import CatchException, report_execption, write_results_to_file
+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
 
 
 def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
@@ -17,51 +17,48 @@ def 解析Paper(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbo
         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: 
-            msg = '正常'
-            # ** gpt request **
-            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, llm_kwargs, chatbot, history=[], sys_prompt=system_prompt)   # 带超时倒计时
-
-            chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-            if not fast_debug: time.sleep(2)
+        msg = '正常'
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user, llm_kwargs, chatbot, history=[], sys_prompt=system_prompt)   # 带超时倒计时
+        chatbot[-1] = (i_say_show_user, gpt_say)
+        history.append(i_say_show_user); history.append(gpt_say)
+        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+        time.sleep(2)
 
     all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
     i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
     chatbot.append((i_say, "[Local Message] waiting gpt response."))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
-    if not fast_debug: 
-        msg = '正常'
-        # ** gpt request **
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say, llm_kwargs, chatbot, history=history, sys_prompt=system_prompt)   # 带超时倒计时
+    msg = '正常'
+    # ** gpt request **
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say, llm_kwargs, chatbot, history=history, sys_prompt=system_prompt)   # 带超时倒计时
 
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-        res = write_results_to_file(history)
-        chatbot.append(("完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+    chatbot[-1] = (i_say, gpt_say)
+    history.append(i_say); history.append(gpt_say)
+    yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+    res = write_history_to_file(history)
+    promote_file_to_downloadzone(res, chatbot=chatbot)
+    chatbot.append(("完成了吗？", res))
+    yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
 
 
 
 @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

@@ -1,26 +1,81 @@
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-from toolbox import CatchException, report_execption, write_results_to_file
-from toolbox import update_ui
+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
+import time
+import random
+
+ENABLE_ALL_VERSION_SEARCH = True
 
 def get_meta_information(url, chatbot, history):
-    import requests
     import arxiv
     import difflib
+    import re
     from bs4 import BeautifulSoup
     from toolbox import get_conf
-    proxies, = get_conf('proxies')
-    headers = {
-        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36',
-    }
-    # 发送 GET 请求
-    response = requests.get(url, proxies=proxies, headers=headers)
+    from urllib.parse import urlparse
+    session = requests.session()
 
+    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-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', 
+        'Connection': 'keep-alive'
+    }
+    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)
     # 解析网页内容
     soup = BeautifulSoup(response.text, "html.parser")
 
     def string_similar(s1, s2):
         return difflib.SequenceMatcher(None, s1, s2).quick_ratio()
 
+    if ENABLE_ALL_VERSION_SEARCH:
+        def search_all_version(url):
+            time.sleep(random.randint(1,5)) # 睡一会防止触发google反爬虫
+            response = session.get(url)
+            soup = BeautifulSoup(response.text, "html.parser")
+
+            for result in soup.select(".gs_ri"):
+                try:
+                    url = result.select_one(".gs_rt").a['href']
+                except:
+                    continue
+                arxiv_id = extract_arxiv_id(url)
+                if not arxiv_id:
+                    continue
+                search = arxiv.Search(
+                    id_list=[arxiv_id],
+                    max_results=1,
+                    sort_by=arxiv.SortCriterion.Relevance,
+                )
+                try: paper = next(search.results())
+                except: paper = None
+                return paper
+
+            return None
+
+        def extract_arxiv_id(url):
+            # 返回给定的url解析出的arxiv_id，如url未成功匹配返回None
+            pattern = r'arxiv.org/abs/([^/]+)'
+            match = re.search(pattern, url)
+            if match:
+                return match.group(1)
+            else:
+                return None
+
     profile = []
     # 获取所有文章的标题和作者
     for result in soup.select(".gs_ri"):
@@ -31,28 +86,45 @@ def get_meta_information(url, chatbot, history):
         except:
             citation = 'cited by 0'
         abstract = result.select_one(".gs_rs").text.strip()  # 摘要在 .gs_rs 中的文本，需要清除首尾空格
+
+        # 首先在arxiv上搜索，获取文章摘要
         search = arxiv.Search(
             query = title,
             max_results = 1,
             sort_by = arxiv.SortCriterion.Relevance,
         )
-        paper = next(search.results())
-        if string_similar(title, paper.title) > 0.90: # same paper
+        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
+        if not is_match and ENABLE_ALL_VERSION_SEARCH:
+            other_versions_page_url = [tag['href'] for tag in result.select_one('.gs_flb').select('.gs_nph') if 'cluster' in tag['href']]
+            if len(other_versions_page_url) > 0:
+                other_versions_page_url = other_versions_page_url[0]
+                paper = search_all_version('http://' + urlparse(url).netloc + other_versions_page_url)
+                is_match = paper is not None and string_similar(title, paper.title) > 0.90
+
+        if is_match:
+            # same paper
             abstract = paper.summary.replace('\n', ' ')
             is_paper_in_arxiv = True
-        else:   # different paper
+        else:
+            # different paper
             abstract = abstract
             is_paper_in_arxiv = False
-        paper = next(search.results())
-        print(title)
-        print(author)
-        print(citation)
+
+        logging.info('[title]:' + title)
+        logging.info('[author]:' + author)
+        logging.info('[citation]:' + citation)
+
         profile.append({
-            'title':title,
-            'author':author,
-            'citation':citation,
-            'abstract':abstract,
-            'is_paper_in_arxiv':is_paper_in_arxiv,
+            'title': title,
+            'author': author,
+            'citation': citation,
+            'abstract': abstract,
+            'is_paper_in_arxiv': is_paper_in_arxiv,
         })
 
         chatbot[-1] = [chatbot[-1][0], title + f'\n\n是否在arxiv中（不在arxiv中无法获取完整摘要）:{is_paper_in_arxiv}\n\n' + abstract]
@@ -60,7 +132,8 @@ 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([
         "函数插件功能？",
@@ -73,7 +146,7 @@ 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, 
+        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
@@ -82,6 +155,9 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
     # 清空历史，以免输入溢出
     history = []
     meta_paper_info_list = yield from get_meta_information(txt, chatbot, history)
+    if len(meta_paper_info_list) == 0:
+        yield from update_ui_lastest_msg(lastmsg='获取文献失败，可能触发了google反爬虫机制。',chatbot=chatbot, history=history, delay=0)
+        return
     batchsize = 5
     for batch in range(math.ceil(len(meta_paper_info_list)/batchsize)):
         if len(meta_paper_info_list[:batchsize]) > 0:
@@ -103,6 +179,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         "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
-    res = write_results_to_file(history)
-    chatbot.append(("完成了吗？", res)); 
+    path = write_history_to_file(history)
+    promote_file_to_downloadzone(path, chatbot=chatbot)
+    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

@@ -0,0 +1,54 @@
+# encoding: utf-8
+# @Time   : 2023/4/19
+# @Author : Spike
+# @Descr   :
+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, 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。'
+    else:
+        prompt = history[-1]+"\n分析上述回答，再列出用户可能提出的三个问题。"
+        show_say = '分析上述回答，再列出用户可能提出的三个问题。'
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=prompt,
+        inputs_show_user=show_say,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot,
+        history=history,
+        sys_prompt=system_prompt
+    )
+    chatbot[-1] = (show_say, gpt_say)
+    history.extend([show_say, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+
+
+@CatchException
+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
+
+    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/辅助回答.py

@@ -0,0 +1,28 @@
+# encoding: utf-8
+# @Time   : 2023/4/19
+# @Author : Spike
+# @Descr   :
+from toolbox import update_ui
+from toolbox import CatchException, report_execption, write_results_to_file
+from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
+
+@CatchException
+def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    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。'
+    else:
+        prompt = history[-1]+"\n分析上述回答，再列出用户可能提出的三个问题。"
+        show_say = '分析上述回答，再列出用户可能提出的三个问题。'
+    gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+        inputs=prompt,
+        inputs_show_user=show_say,
+        llm_kwargs=llm_kwargs,
+        chatbot=chatbot,
+        history=history,
+        sys_prompt=system_prompt
+    )
+    chatbot[-1] = (show_say, gpt_say)
+    history.extend([show_say, gpt_say])
+    yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面

crazy_functions/高级功能函数模板.py

@@ -1,19 +1,47 @@
 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，暂时没有用武之地
+    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
+    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((
+        "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
@@ -27,3 +55,45 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
         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
+    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(("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
+    
+    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

@@ -0,0 +1,231 @@
+## ===================================================
+# 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）
+## ===================================================
+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
+      API_KEY:                  '  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                        '
+      # 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                                                   '
+      BAIDU_CLOUD_SECRET_KEY :  '  jqXtLvXiVw6UNdjliATTS61rllG8Iuni                                           '
+      XFYUN_APPID:              '  53a8d816                                                                   '
+      XFYUN_API_SECRET:         '  MjMxNDQ4NDE4MzM0OSNlNjQ2NTlhMTkx                                           '
+      XFYUN_API_KEY:            '  95ccdec285364869d17b33e75ee96447                                           '
+      ENABLE_AUDIO:             '  False                                                                      '
+      DEFAULT_WORKER_NUM:       '  20                                                                         '
+      WEB_PORT:                 '  12345                                                                      '
+      ADD_WAIFU:                '  False                                                                      '
+      ALIYUN_APPKEY:            '  RxPlZrM88DnAFkZK                                                           '
+      THEME:                    '  Chuanhu-Small-and-Beautiful                                                '
+      ALIYUN_ACCESSKEY:         '  LTAI5t6BrFUzxRXVGUWnekh1                                                   '
+      ALIYUN_SECRET:            '  eHmI20SVWIwQZxCiTD2bGQVspP9i68                                             '
+      # LOCAL_MODEL_DEVICE:       '  cuda                                                                       '
+
+    # 加载英伟达显卡运行时
+    # runtime: nvidia
+    # deploy:
+    #     resources:
+    #       reservations:
+    #         devices:
+    #           - driver: nvidia
+    #             count: 1
+    #             capabilities: [gpu]
+
+    # 【WEB_PORT暴露方法1: 适用于Linux】与宿主的网络融合
+    network_mode: "host"
+
+    # 【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）
+## ===================================================
+version: '3'
+services:
+  gpt_academic_nolocalllms:
+    image: ghcr.io/binary-husky/gpt_academic_nolocal:master # (Auto Built by Dockerfile: docs/GithubAction+NoLocal)
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                                            '
+      USE_PROXY:                '    True                                                                                           '
+      proxies:                  '    { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", }                 '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                                                  '
+      AVAIL_LLM_MODELS:         '    ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "sparkv2", "qianfan"]         '
+      WEB_PORT:                 '    22303                                                                                          '
+      ADD_WAIFU:                '    True                                                                                           '
+      # THEME:                    '    Chuanhu-Small-and-Beautiful                                                                    '
+      # DEFAULT_WORKER_NUM:       '    10                                                                                             '
+      # AUTHENTICATION:           '    [("username", "passwd"), ("username2", "passwd2")]                                             '
+
+    # 与宿主的网络融合
+    network_mode: "host"
+
+    # 不使用代理网络拉取最新代码
+    command: >
+      bash -c "python3 -u main.py"
+
+
+### ===================================================
+### 【方案二】 如果需要运行ChatGLM + Qwen + MOSS等本地模型
+### ===================================================
+version: '3'
+services:
+  gpt_academic_with_chatglm:
+    image: ghcr.io/binary-husky/gpt_academic_chatglm_moss:master  # (Auto Built by Dockerfile: docs/Dockerfile+ChatGLM)
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                                            '
+      USE_PROXY:                '    True                                                                                           '
+      proxies:                  '    { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", }                 '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                                                  '
+      AVAIL_LLM_MODELS:         '    ["chatglm", "qwen", "moss", "gpt-3.5-turbo", "gpt-4", "newbing"]                               '
+      LOCAL_MODEL_DEVICE:       '    cuda                                                                                           '
+      DEFAULT_WORKER_NUM:       '    10                                                                                             '
+      WEB_PORT:                 '    12303                                                                                          '
+      ADD_WAIFU:                '    True                                                                                           '
+      # AUTHENTICATION:           '    [("username", "passwd"), ("username2", "passwd2")]                                             '
+
+    # 显卡的使用，nvidia0指第0个GPU
+    runtime: nvidia
+    devices:
+      - /dev/nvidia0:/dev/nvidia0
+
+    # 与宿主的网络融合
+    network_mode: "host"
+    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_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
+### ===================================================
+version: '3'
+services:
+  gpt_academic_with_rwkv:
+    image: ghcr.io/binary-husky/gpt_academic_jittorllms:master
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx  '
+      USE_PROXY:                '    True                                                                                           '
+      proxies:                  '    { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", }                 '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                                                  '
+      AVAIL_LLM_MODELS:         '    ["gpt-3.5-turbo", "newbing", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]   '
+      LOCAL_MODEL_DEVICE:       '    cuda                                                                                           '
+      DEFAULT_WORKER_NUM:       '    10                                                                                             '
+      WEB_PORT:                 '    12305                                                                                          '
+      ADD_WAIFU:                '    True                                                                                           '
+      # AUTHENTICATION:           '    [("username", "passwd"), ("username2", "passwd2")]                                             '
+
+    # 显卡的使用，nvidia0指第0个GPU
+    runtime: nvidia
+    devices:
+      - /dev/nvidia0:/dev/nvidia0
+
+    # 与宿主的网络融合
+    network_mode: "host"
+
+    # 不使用代理网络拉取最新代码
+    command: >
+      python3 -u main.py
+
+
+## ===================================================
+## 【方案四】 ChatGPT + Latex
+## ===================================================
+version: '3'
+services:
+  gpt_academic_with_latex:
+    image: ghcr.io/binary-husky/gpt_academic_with_latex:master  # (Auto Built by Dockerfile: docs/GithubAction+NoLocal+Latex)
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                              '
+      USE_PROXY:                '    True                                                                             '
+      proxies:                  '    { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", }   '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                                    '
+      AVAIL_LLM_MODELS:         '    ["gpt-3.5-turbo", "gpt-4"]                                                       '
+      LOCAL_MODEL_DEVICE:       '    cuda                                                                             '
+      DEFAULT_WORKER_NUM:       '    10                                                                               '
+      WEB_PORT:                 '    12303                                                                            '
+
+    # 与宿主的网络融合
+    network_mode: "host"
+
+    # 不使用代理网络拉取最新代码
+    command: >
+      bash -c "python3 -u main.py"
+
+
+## ===================================================
+## 【方案五】 ChatGPT + 语音助手 （请先阅读 docs/use_audio.md）
+## ===================================================
+version: '3'
+services:
+  gpt_academic_with_audio:
+    image: ghcr.io/binary-husky/gpt_academic_audio_assistant:master
+    environment:
+      # 请查阅 `config.py` 以查看所有的配置信息
+      API_KEY:                  '    fk195831-IdP0Pb3W6DCMUIbQwVX6MsSiyxwqybyS                        '
+      USE_PROXY:                '    False                                                            '
+      proxies:                  '    None                                                             '
+      LLM_MODEL:                '    gpt-3.5-turbo                                                    '
+      AVAIL_LLM_MODELS:         '    ["gpt-3.5-turbo", "gpt-4"]                                       '
+      ENABLE_AUDIO:             '    True                                                             '
+      LOCAL_MODEL_DEVICE:       '    cuda                                                             '
+      DEFAULT_WORKER_NUM:       '    20                                                               '
+      WEB_PORT:                 '    12343                                                            '
+      ADD_WAIFU:                '    True                                                             '
+      THEME:                    '    Chuanhu-Small-and-Beautiful                                      '
+      ALIYUN_APPKEY:            '    RoP1ZrM84DnAFkZK                                                 '
+      ALIYUN_TOKEN:             '    f37f30e0f9934c34a992f6f64f7eba4f                                 '
+      # (无需填写) ALIYUN_ACCESSKEY:         '    LTAI5q6BrFUzoRXVGUWnekh1                                         '
+      # (无需填写) ALIYUN_SECRET:            '    eHmI20AVWIaQZ0CiTD2bGQVsaP9i68                                   '
+
+    # 与宿主的网络融合
+    network_mode: "host"
+
+    # 不使用代理网络拉取最新代码
+    command: >
+      bash -c "python3 -u main.py"

docs/Dockerfile+ChatGLM

@@ -1,59 +1 @@
-# How to build | 如何构建: docker build -t gpt-academic --network=host  -f Dockerfile+ChatGLM .
-# How to run | 如何运行 (1) 直接运行（选择0号GPU）: docker run --rm -it --net=host --gpus="0" gpt-academic
-# How to run | 如何运行 (2) 我想运行之前进容器做一些调整: docker run --rm -it --net=host --gpus="0" gpt-academic bash
- 
-# 从NVIDIA源，从而支持显卡运损（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
-FROM nvidia/cuda:11.3.1-runtime-ubuntu20.04
-ARG useProxyNetwork=''
-RUN apt-get update
-RUN apt-get install -y curl proxychains curl 
-RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
-
-# 配置代理网络（构建Docker镜像时使用）
-# # comment out below if you do not need proxy network | 如果不需要翻墙 - 从此行向下删除
-RUN $useProxyNetwork curl cip.cc
-RUN sed -i '$ d' /etc/proxychains.conf
-RUN sed -i '$ d' /etc/proxychains.conf
-RUN echo "socks5 127.0.0.1 10880" >> /etc/proxychains.conf
-ARG useProxyNetwork=proxychains
-# # comment out above if you do not need proxy network | 如果不需要翻墙 - 从此行向上删除
-
-
-# use python3 as the system default python
-RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
-
-# 下载分支
-WORKDIR /gpt
-RUN $useProxyNetwork git clone https://github.com/binary-husky/chatgpt_academic.git
-WORKDIR /gpt/chatgpt_academic
-RUN $useProxyNetwork python3 -m pip install -r requirements.txt
-RUN $useProxyNetwork python3 -m pip install -r request_llm/requirements_chatglm.txt
-RUN $useProxyNetwork python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
-
-# 预热CHATGLM参数（非必要 可选步骤）
-RUN echo ' \n\
-from transformers import AutoModel, AutoTokenizer \n\
-chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) \n\
-chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float() ' >> warm_up_chatglm.py
-RUN python3 -u warm_up_chatglm.py
-
-# 禁用缓存，确保更新代码
-ADD "https://www.random.org/cgi-bin/randbyte?nbytes=10&format=h" skipcache
-RUN $useProxyNetwork git pull
-
-# 预热Tiktoken模块
-RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
-
-# 为chatgpt-academic配置代理和API-KEY （非必要 可选步骤）
-# 可同时填写多个API-KEY，支持openai的key和api2d的key共存，用英文逗号分割，例如API_KEY = "sk-openaikey1,fkxxxx-api2dkey2,........"
-# LLM_MODEL 是选择初始的模型
-# LOCAL_MODEL_DEVICE 是选择chatglm等本地模型运行的设备，可选 cpu 和 cuda
-RUN echo ' \n\
-API_KEY = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \n\
-USE_PROXY = True \n\
-LLM_MODEL = "chatglm" \n\
-LOCAL_MODEL_DEVICE = "cuda" \n\
-proxies = { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", } ' >> config_private.py
-
-# 启动
-CMD ["python3", "-u", "main.py"]
+# 此Dockerfile不再维护，请前往docs/GithubAction+ChatGLM+Moss

docs/Dockerfile+JittorLLM

@@ -0,0 +1 @@
+# 此Dockerfile不再维护，请前往docs/GithubAction+JittorLLMs

docs/Dockerfile+NoLocal+Latex

@@ -0,0 +1 @@
+# 此Dockerfile不再维护，请前往docs/GithubAction+NoLocal+Latex

docs/GithubAction+AllCapacity

@@ -0,0 +1,36 @@
+# 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 .
+
+# 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
+# 下载pytorch
+RUN python3 -m pip install torch --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()'
+
+# 启动
+CMD ["python3", "-u", "main.py"]

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

@@ -0,0 +1,30 @@
+
+# 从NVIDIA源，从而支持显卡运损（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
+FROM nvidia/cuda:11.3.1-runtime-ubuntu20.04
+RUN apt-get update
+RUN apt-get install -y curl proxychains curl gcc
+RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
+
+
+# use python3 as the system default python
+RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
+# 下载pytorch
+RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
+# 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 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
+
+
+
+# 预热Tiktoken模块
+RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/GithubAction+JittorLLMs

@@ -0,0 +1,34 @@
+# 从NVIDIA源，从而支持显卡运损（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
+FROM nvidia/cuda:11.3.1-runtime-ubuntu20.04
+ARG useProxyNetwork=''
+RUN apt-get update
+RUN apt-get install -y curl proxychains curl g++
+RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
+
+# use python3 as the system default python
+RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
+
+# 下载pytorch
+RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
+
+# 下载分支
+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_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_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
+RUN git pull
+
+# 预热Tiktoken模块
+RUN python3  -c 'from check_proxy import warm_up_modules; warm_up_modules()'
+
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/GithubAction+NoLocal

@@ -0,0 +1,20 @@
+# 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 -f docs/Dockerfile+NoLocal .
+# 如何运行: docker run --rm -it --net=host gpt-academic-nolocal
+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
+
+
+# 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/GithubAction+NoLocal+AudioAssistant

@@ -0,0 +1,22 @@
+# 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 -f docs/Dockerfile+NoLocal .
+# 如何运行: docker run --rm -it --net=host gpt-academic-nolocal
+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
+
+# 安装语音插件的额外依赖
+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()'
+
+# 启动
+CMD ["python3", "-u", "main.py"]

docs/GithubAction+NoLocal+Latex

@@ -0,0 +1,35 @@
+# 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
+# - 1 修改 `config.py`
+# - 2 构建 docker build -t gpt-academic-nolocal-latex -f docs/GithubAction+NoLocal+Latex .
+# - 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"
+
+# 删除文档文件以节约空间
+RUN rm -rf /usr/local/texlive/2023/texmf-dist/doc
+
+# 指定路径
+WORKDIR /gpt
+
+RUN pip3 install openai numpy arxiv rich
+RUN pip3 install colorama Markdown pygments pymupdf
+RUN pip3 install python-docx pdfminer
+RUN pip3 install nougat-ocr
+
+# 装载项目文件
+COPY . .
+
+
+# 安装依赖
+RUN pip3 install -r requirements.txt
+
+# 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"]