镜像自地址
https://github.com/binary-husky/gpt_academic.git
已同步 2025-12-06 14:36:48 +00:00
again
这个提交包含在：
binary-husky
44
.github/workflows/build-with-latex.yml
vendored
普通文件
44
.github/workflows/build-with-latex.yml
vendored
普通文件
@@ -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 }}
|
||||
10
Dockerfile
10
Dockerfile
@@ -10,12 +10,16 @@ RUN echo '[global]' > /etc/pip.conf && \
|
||||
|
||||
WORKDIR /gpt
|
||||
|
||||
# 装载项目文件
|
||||
COPY . .
|
||||
|
||||
|
||||
|
||||
# 安装依赖
|
||||
COPY requirements.txt ./
|
||||
COPY ./docs/gradio-3.32.2-py3-none-any.whl ./docs/gradio-3.32.2-py3-none-any.whl
|
||||
RUN pip3 install -r requirements.txt
|
||||
# 装载项目文件
|
||||
COPY . .
|
||||
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()'
|
||||
|
||||
132
README.md
132
README.md
@@ -12,9 +12,9 @@ pinned: false
|
||||
# ChatGPT 学术优化
|
||||
> **Note**
|
||||
>
|
||||
> 5月27日对gradio依赖进行了较大的修复和调整，fork并解决了官方Gradio的一系列bug。但如果27日当天进行了更新，可能会导致代码报错（依赖缺失，卡在loading界面等），请及时更新到**最新版代码**并重新安装pip依赖即可。若给您带来困扰还请谅解。安装依赖时，请严格选择requirements.txt中**指定的版本**：
|
||||
> 2023.5.27 对Gradio依赖进行了调整，Fork并解决了官方Gradio的若干Bugs。请及时**更新代码**并重新更新pip依赖。安装依赖时，请严格选择`requirements.txt`中**指定的版本**：
|
||||
>
|
||||
> `pip install -r requirements.txt -i https://pypi.org/simple`
|
||||
> `pip install -r requirements.txt`
|
||||
>
|
||||
|
||||
# <img src="docs/logo.png" width="40" > GPT 学术优化 (GPT Academic)
|
||||
@@ -28,7 +28,7 @@ To translate this project to arbitary language with GPT, read and run [`multi_la
|
||||
>
|
||||
> 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。[安装方法](#installation)。
|
||||
> 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/gpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)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/gpt_academic/wiki/%E5%B8%B8%E8%A7%81%E9%97%AE%E9%A2%98)当中。[安装方法](#installation)。
|
||||
>
|
||||
> 3.本项目兼容并鼓励尝试国产大语言模型chatglm和RWKV, 盘古等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,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。
|
||||
|
||||
@@ -43,22 +43,23 @@ To translate this project to arbitary language with GPT, read and run [`multi_la
|
||||
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
|
||||
[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
|
||||
模块化设计 | 支持自定义强大的[函数插件](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
|
||||
[自我程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] [一键读懂](https://github.com/binary-husky/gpt_academic/wiki/chatgpt-academic%E9%A1%B9%E7%9B%AE%E8%87%AA%E8%AF%91%E8%A7%A3%E6%8A%A5%E5%91%8A)本项目的源代码
|
||||
[程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [函数插件] 一键可以剖析其他Python/C/C++/Java/Lua/...项目树
|
||||
读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [函数插件] 一键解读latex/pdf论文全文并生成摘要
|
||||
Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [函数插件] 一键翻译或润色latex论文
|
||||
批量注释生成 | [函数插件] 一键批量生成函数注释
|
||||
Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/chatgpt_academic/blob/master/docs/README_EN.md)了吗？
|
||||
Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？
|
||||
chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
|
||||
[PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [函数插件] PDF论文提取题目&摘要+翻译全文（多线程）
|
||||
[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
|
||||
[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
|
||||
互联网信息聚合+GPT | [函数插件] 一键[让GPT先从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)，再回答问题，让信息永不过时
|
||||
⭐Arxiv论文精细翻译 | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，迄今为止最好的论文翻译工具⭐
|
||||
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```/?__theme=dark```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、[清华ChatGLM](https://github.com/THUDM/ChatGLM-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？
|
||||
启动暗色gradio[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ChatGLM](https://github.com/THUDM/ChatGLM-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时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)，[RWKV](https://github.com/BlinkDL/ChatRWKV)和[盘古α](https://openi.org.cn/pangu/)
|
||||
更多新功能展示(图像生成等) …… | 见本文档结尾处 ……
|
||||
|
||||
@@ -102,13 +103,13 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
|
||||
|
||||
1. 下载项目
|
||||
```sh
|
||||
git clone https://github.com/binary-husky/chatgpt_academic.git
|
||||
cd chatgpt_academic
|
||||
git clone https://github.com/binary-husky/gpt_academic.git
|
||||
cd gpt_academic
|
||||
```
|
||||
|
||||
2. 配置API_KEY
|
||||
|
||||
在`config.py`中，配置API KEY等设置，[特殊网络环境设置](https://github.com/binary-husky/gpt_academic/issues/1) 。
|
||||
在`config.py`中，配置API KEY等设置，[点击查看特殊网络环境设置方法](https://github.com/binary-husky/gpt_academic/issues/1) 。
|
||||
|
||||
(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。P.S.项目同样支持通过`环境变量`配置大多数选项，环境变量的书写格式参考`docker-compose`文件。读取优先级: `环境变量` > `config_private.py` > `config.py`)
|
||||
|
||||
@@ -124,6 +125,7 @@ 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ChatGLM/复旦MOSS作为后端，请点击展开此处</summary>
|
||||
<p>
|
||||
|
||||
@@ -150,19 +152,13 @@ AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-
|
||||
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2：使用Docker
|
||||
|
||||
1. 仅ChatGPT（推荐大多数人选择）
|
||||
1. 仅ChatGPT（推荐大多数人选择，等价于docker-compose方案1）
|
||||
|
||||
``` sh
|
||||
git clone https://github.com/binary-husky/chatgpt_academic.git # 下载项目
|
||||
cd chatgpt_academic # 进入路径
|
||||
git clone https://github.com/binary-husky/gpt_academic.git # 下载项目
|
||||
cd gpt_academic # 进入路径
|
||||
nano config.py # 用任意文本编辑器编辑config.py, 配置 “Proxy”， “API_KEY” 以及 “WEB_PORT” (例如50923) 等
|
||||
docker build -t gpt-academic . # 安装
|
||||
|
||||
@@ -171,37 +167,45 @@ 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 -e WEB_PORT=50923 -p 50923:50923 gpt-academic
|
||||
```
|
||||
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docker-compose获取Latex功能（修改docker-compose.yml，保留方案4并删除其他方案）。
|
||||
|
||||
2. ChatGPT + ChatGLM + MOSS（需要熟悉Docker）
|
||||
|
||||
``` sh
|
||||
# 修改docker-compose.yml，删除方案1和方案3，保留方案2。修改docker-compose.yml中方案2的配置，参考其中注释即可
|
||||
# 修改docker-compose.yml，保留方案2并删除其他方案。修改docker-compose.yml中方案2的配置，参考其中注释即可
|
||||
docker-compose up
|
||||
```
|
||||
|
||||
3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉Docker）
|
||||
``` sh
|
||||
# 修改docker-compose.yml，删除方案1和方案2，保留方案3。修改docker-compose.yml中方案3的配置，参考其中注释即可
|
||||
# 修改docker-compose.yml，保留方案3并删除其他方案。修改docker-compose.yml中方案3的配置，参考其中注释即可
|
||||
docker-compose up
|
||||
```
|
||||
|
||||
|
||||
## 安装-方法3：其他部署姿势
|
||||
1. 一键运行脚本。
|
||||
完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。
|
||||
脚本的贡献来源是[oobabooga](https://github.com/oobabooga/one-click-installers)。
|
||||
|
||||
1. 如何使用反代URL/微软云AzureAPI
|
||||
2. 使用docker-compose运行。
|
||||
请阅读docker-compose.yml后，按照其中的提示操作即可
|
||||
|
||||
3. 如何使用反代URL
|
||||
按照`config.py`中的说明配置API_URL_REDIRECT即可。
|
||||
|
||||
2. 远程云服务器部署（需要云服务器知识与经验）
|
||||
请访问[部署wiki-1](https://github.com/binary-husky/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)
|
||||
4. 微软云AzureAPI
|
||||
按照`config.py`中的说明配置即可（AZURE_ENDPOINT等四个配置）
|
||||
|
||||
3. 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)
|
||||
5. 远程云服务器部署（需要云服务器知识与经验）。
|
||||
请访问[部署wiki-1](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
|
||||
|
||||
4. 如何在二级网址（如`http://localhost/subpath`）下运行
|
||||
6. 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)
|
||||
|
||||
7. 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)
|
||||
|
||||
5. 使用docker-compose运行
|
||||
请阅读docker-compose.yml后，按照其中的提示操作即可
|
||||
---
|
||||
# Advanced Usage
|
||||
## 自定义新的便捷按钮 / 自定义函数插件
|
||||
@@ -226,7 +230,7 @@ docker-compose up
|
||||
|
||||
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)。
|
||||
|
||||
---
|
||||
# Latest Update
|
||||
@@ -234,38 +238,33 @@ docker-compose up
|
||||
|
||||
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，点击 `删除所有本地对话历史记录` 可以删除所有html存档缓存。
|
||||
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. 生成报告。大部分插件都会在执行结束后，生成工作报告
|
||||
2. ⭐Latex/Arxiv论文翻译功能⭐
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/227503770-fe29ce2c-53fd-47b0-b0ff-93805f0c2ff4.png" height="300" >
|
||||
<img src="https://user-images.githubusercontent.com/96192199/227504617-7a497bb3-0a2a-4b50-9a8a-95ae60ea7afd.png" height="300" >
|
||||
<img src="https://user-images.githubusercontent.com/96192199/227504005-efeaefe0-b687-49d0-bf95-2d7b7e66c348.png" height="300" >
|
||||
<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. 模块化功能设计，简单的接口却能支持强大的功能
|
||||
3. 生成报告。大部分插件都会在执行结束后，生成工作报告
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/227503770-fe29ce2c-53fd-47b0-b0ff-93805f0c2ff4.png" height="250" >
|
||||
<img src="https://user-images.githubusercontent.com/96192199/227504617-7a497bb3-0a2a-4b50-9a8a-95ae60ea7afd.png" height="250" >
|
||||
</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>
|
||||
|
||||
4. 这是一个能够“自我译解”的开源项目
|
||||
5. 译解其他开源项目
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/226936850-c77d7183-0749-4c1c-9875-fd4891842d0c.png" width="500" >
|
||||
</div>
|
||||
|
||||
5. 译解其他开源项目，不在话下
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="500" >
|
||||
</div>
|
||||
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" width="500" >
|
||||
<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`）
|
||||
@@ -290,13 +289,15 @@ Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史h
|
||||
|
||||
10. 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" width="500" >
|
||||
<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>
|
||||
|
||||
|
||||
|
||||
## 版本:
|
||||
- version 3.5(Todo): 使用自然语言调用本项目的所有函数插件（高优先级）
|
||||
- version 3.4(Todo): 完善chatglm本地大模型的多线支持
|
||||
- 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
|
||||
@@ -314,29 +315,32 @@ gpt_academic开发者QQ群-2：610599535
|
||||
|
||||
- 已知问题
|
||||
- 某些浏览器翻译插件干扰此软件前端的运行
|
||||
- 官方Gradio目前有很多兼容性Bug，请务必使用requirement.txt安装Gradio
|
||||
- 官方Gradio目前有很多兼容性Bug，请务必使用`requirement.txt`安装Gradio
|
||||
|
||||
## 参考与学习
|
||||
|
||||
```
|
||||
代码中参考了很多其他优秀项目中的设计，主要包括：
|
||||
代码中参考了很多其他优秀项目中的设计，顺序不分先后：
|
||||
|
||||
# 项目1：清华ChatGLM-6B:
|
||||
# 清华ChatGLM-6B:
|
||||
https://github.com/THUDM/ChatGLM-6B
|
||||
|
||||
# 项目2：清华JittorLLMs:
|
||||
# 清华JittorLLMs:
|
||||
https://github.com/Jittor/JittorLLMs
|
||||
|
||||
# 项目3：Edge-GPT:
|
||||
https://github.com/acheong08/EdgeGPT
|
||||
|
||||
# 项目4：ChuanhuChatGPT:
|
||||
https://github.com/GaiZhenbiao/ChuanhuChatGPT
|
||||
|
||||
# 项目5：ChatPaper:
|
||||
# ChatPaper:
|
||||
https://github.com/kaixindelele/ChatPaper
|
||||
|
||||
# 更多：
|
||||
# Edge-GPT:
|
||||
https://github.com/acheong08/EdgeGPT
|
||||
|
||||
# ChuanhuChatGPT:
|
||||
https://github.com/GaiZhenbiao/ChuanhuChatGPT
|
||||
|
||||
# Oobabooga one-click installer:
|
||||
https://github.com/oobabooga/one-click-installers
|
||||
|
||||
# More：
|
||||
https://github.com/gradio-app/gradio
|
||||
https://github.com/fghrsh/live2d_demo
|
||||
```
|
||||
|
||||
6
app.py
6
app.py
@@ -2,7 +2,7 @@ import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||
|
||||
def main():
|
||||
import subprocess, sys
|
||||
subprocess.check_call([sys.executable, '-m', 'pip', 'install', '-r', 'requirements.txt'])
|
||||
subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'gradio-stable-fork'])
|
||||
import gradio as gr
|
||||
if gr.__version__ not in ['3.28.3','3.32.3']: assert False, "请用 pip install -r requirements.txt 安装依赖"
|
||||
from request_llm.bridge_all import predict
|
||||
@@ -158,7 +158,7 @@ def main():
|
||||
for k in crazy_fns:
|
||||
if not crazy_fns[k].get("AsButton", True): continue
|
||||
click_handle = crazy_fns[k]["Button"].click(ArgsGeneralWrapper(crazy_fns[k]["Function"]), [*input_combo, gr.State(PORT)], output_combo)
|
||||
click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot])
|
||||
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):
|
||||
@@ -178,7 +178,7 @@ def main():
|
||||
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(crazy_fns[k]["Function"])(*args, **kwargs)
|
||||
click_handle = switchy_bt.click(route,[switchy_bt, *input_combo, gr.State(PORT)], output_combo)
|
||||
click_handle.then(on_report_generated, [file_upload, chatbot], [file_upload, chatbot])
|
||||
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)
|
||||
|
||||
80
colorful.py
80
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"
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
# [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"
|
||||
|
||||
|
||||
# [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
|
||||
USE_PROXY = False
|
||||
if USE_PROXY:
|
||||
@@ -80,3 +81,10 @@ your bing cookies here
|
||||
# 如果需要使用Slack Claude，使用教程详情见 request_llm/README.md
|
||||
SLACK_CLAUDE_BOT_ID = ''
|
||||
SLACK_CLAUDE_USER_TOKEN = ''
|
||||
|
||||
|
||||
# 如果需要使用AZURE 详情请见额外文档 docs\use_azure.md
|
||||
AZURE_ENDPOINT = "https://你的api名称.openai.azure.com/"
|
||||
AZURE_API_KEY = "填入azure openai api的密钥"
|
||||
AZURE_API_VERSION = "填入api版本"
|
||||
AZURE_ENGINE = "填入ENGINE"
|
||||
|
||||
@@ -112,11 +112,11 @@ def get_crazy_functions():
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(解析项目本身)
|
||||
},
|
||||
"[老旧的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)
|
||||
},
|
||||
# "[老旧的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)
|
||||
# },
|
||||
"[插件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)
|
||||
@@ -126,7 +126,7 @@ def get_crazy_functions():
|
||||
###################### 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
|
||||
@@ -152,17 +152,16 @@ def get_crazy_functions():
|
||||
# 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)
|
||||
},
|
||||
# "[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)
|
||||
# },
|
||||
"谷歌学术检索助手（输入谷歌学术搜索页url）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"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
|
||||
"Color": "stop",
|
||||
@@ -181,7 +180,7 @@ def get_crazy_functions():
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(Latex英文纠错)
|
||||
},
|
||||
"[测试功能] 中文Latex项目全文润色（输入路径或上传压缩包）": {
|
||||
"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
|
||||
@@ -210,7 +209,9 @@ def get_crazy_functions():
|
||||
})
|
||||
|
||||
###################### 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
|
||||
# [第三组插件]: 尚未充分测试的函数插件
|
||||
|
||||
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）": {
|
||||
@@ -219,16 +220,30 @@ def get_crazy_functions():
|
||||
"Function": HotReload(下载arxiv论文并翻译摘要)
|
||||
}
|
||||
})
|
||||
except:
|
||||
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（先输入问题，再点击按钮，需要访问谷歌）": {
|
||||
"连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"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）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False, # 加入下拉菜单中
|
||||
"Function": HotReload(连接bing搜索回答问题)
|
||||
}
|
||||
})
|
||||
except:
|
||||
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）": {
|
||||
@@ -239,6 +254,10 @@ def get_crazy_functions():
|
||||
"Function": HotReload(解析任意code项目)
|
||||
},
|
||||
})
|
||||
except:
|
||||
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）": {
|
||||
@@ -249,6 +268,10 @@ def get_crazy_functions():
|
||||
"Function": HotReload(同时问询_指定模型)
|
||||
},
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
try:
|
||||
from crazy_functions.图片生成 import 图片生成
|
||||
function_plugins.update({
|
||||
"图片生成（先切换模型到openai或api2d）": {
|
||||
@@ -259,6 +282,10 @@ def get_crazy_functions():
|
||||
"Function": HotReload(图片生成)
|
||||
},
|
||||
})
|
||||
except:
|
||||
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）": {
|
||||
@@ -269,6 +296,9 @@ def get_crazy_functions():
|
||||
"Function": HotReload(总结音视频)
|
||||
}
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
try:
|
||||
from crazy_functions.数学动画生成manim import 动画生成
|
||||
function_plugins.update({
|
||||
@@ -295,5 +325,83 @@ def get_crazy_functions():
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
###################### 第n组插件 ###########################
|
||||
try:
|
||||
from crazy_functions.Langchain知识库 import 知识库问答
|
||||
function_plugins.update({
|
||||
"[功能尚不稳定] 构建知识库（请先上传文件素材）": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "待注入的知识库名称id, 默认为default",
|
||||
"Function": HotReload(知识库问答)
|
||||
}
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
try:
|
||||
from crazy_functions.Langchain知识库 import 读取知识库作答
|
||||
function_plugins.update({
|
||||
"[功能尚不稳定] 知识库问答": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "待提取的知识库名称id, 默认为default, 您需要首先调用构建知识库",
|
||||
"Function": HotReload(读取知识库作答)
|
||||
}
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
try:
|
||||
from crazy_functions.Latex输出PDF结果 import Latex英文纠错加PDF对比
|
||||
function_plugins.update({
|
||||
"Latex英文纠错+高亮修正位置 [需Latex]": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder": "如果有必要, 请在此处追加更细致的矫错指令（使用英文）。",
|
||||
"Function": HotReload(Latex英文纠错加PDF对比)
|
||||
}
|
||||
})
|
||||
from crazy_functions.Latex输出PDF结果 import Latex翻译中文并重新编译PDF
|
||||
function_plugins.update({
|
||||
"Arixv翻译（输入arxivID）[需Latex]": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder":
|
||||
"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+
|
||||
"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF)
|
||||
}
|
||||
})
|
||||
function_plugins.update({
|
||||
"本地论文翻译（上传Latex压缩包）[需Latex]": {
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"AdvancedArgs": True,
|
||||
"ArgsReminder":
|
||||
"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "+
|
||||
"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: " + 'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF)
|
||||
}
|
||||
})
|
||||
except:
|
||||
print('Load function plugin failed')
|
||||
|
||||
# try:
|
||||
# from crazy_functions.虚空终端 import 终端
|
||||
# function_plugins.update({
|
||||
# "超级终端": {
|
||||
# "Color": "stop",
|
||||
# "AsButton": False,
|
||||
# # "AdvancedArgs": True,
|
||||
# # "ArgsReminder": "",
|
||||
# "Function": HotReload(终端)
|
||||
# }
|
||||
# })
|
||||
# except:
|
||||
# print('Load function plugin failed')
|
||||
|
||||
return function_plugins
|
||||
|
||||
107
crazy_functions/Langchain知识库.py
普通文件
107
crazy_functions/Langchain知识库.py
普通文件
@@ -0,0 +1,107 @@
|
||||
from toolbox import CatchException, update_ui, ProxyNetworkActivate
|
||||
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
|
||||
chatbot.append(("这是什么功能？", "[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'])
|
||||
|
||||
# < --------------------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')
|
||||
|
||||
# < --------------------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(): # 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(): # 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'])
|
||||
|
||||
# < ------------------- --------------- >
|
||||
kai = knowledge_archive_interface()
|
||||
|
||||
if 'langchain_plugin_embedding' in chatbot._cookies:
|
||||
resp, prompt = kai.answer_with_archive_by_id(txt, chatbot._cookies['langchain_plugin_embedding'])
|
||||
else:
|
||||
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, '[Local Message] ' + 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
|
||||
@@ -238,3 +238,6 @@ def Latex英文纠错(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
|
||||
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')
|
||||
|
||||
|
||||
|
||||
|
||||
300
crazy_functions/Latex输出PDF结果.py
普通文件
300
crazy_functions/Latex输出PDF结果.py
普通文件
@@ -0,0 +1,300 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, objdump, objload, promote_file_to_downloadzone
|
||||
from toolbox import CatchException, report_execption, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
import glob, os, requests, time
|
||||
pj = os.path.join
|
||||
ARXIV_CACHE_DIR = os.path.expanduser(f"~/arxiv_cache/")
|
||||
|
||||
# =================================== 工具函数 ===============================================
|
||||
专业词汇声明 = 'If the term "agent" is used in this section, it should be translated to "智能体". '
|
||||
def switch_prompt(pfg, mode, more_requirement):
|
||||
"""
|
||||
Generate prompts and system prompts based on the mode for proofreading or translating.
|
||||
Args:
|
||||
- pfg: Proofreader or Translator instance.
|
||||
- mode: A string specifying the mode, either 'proofread' or 'translate_zh'.
|
||||
|
||||
Returns:
|
||||
- inputs_array: A list of strings containing prompts for users to respond to.
|
||||
- sys_prompt_array: A list of strings containing prompts for system prompts.
|
||||
"""
|
||||
n_split = len(pfg.sp_file_contents)
|
||||
if mode == 'proofread_en':
|
||||
inputs_array = [r"Below is a section from an academic paper, proofread this section." +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " + more_requirement +
|
||||
r"Answer me only with the revised text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional academic paper writer." for _ in range(n_split)]
|
||||
elif mode == 'translate_zh':
|
||||
inputs_array = [r"Below is a section from an English academic paper, translate it into Chinese. " + more_requirement +
|
||||
r"Do not modify any latex command such as \section, \cite, \begin, \item and equations. " +
|
||||
r"Answer me only with the translated text:" +
|
||||
f"\n\n{frag}" for frag in pfg.sp_file_contents]
|
||||
sys_prompt_array = ["You are a professional translator." for _ in range(n_split)]
|
||||
else:
|
||||
assert False, "未知指令"
|
||||
return inputs_array, sys_prompt_array
|
||||
|
||||
def desend_to_extracted_folder_if_exist(project_folder):
|
||||
"""
|
||||
Descend into the extracted folder if it exists, otherwise return the original folder.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the extracted folder, or the original folder if there is no extracted folder.
|
||||
"""
|
||||
maybe_dir = [f for f in glob.glob(f'{project_folder}/*') if os.path.isdir(f)]
|
||||
if len(maybe_dir) == 0: return project_folder
|
||||
if maybe_dir[0].endswith('.extract'): return maybe_dir[0]
|
||||
return project_folder
|
||||
|
||||
def move_project(project_folder, arxiv_id=None):
|
||||
"""
|
||||
Create a new work folder and copy the project folder to it.
|
||||
|
||||
Args:
|
||||
- project_folder: A string specifying the folder path of the project.
|
||||
|
||||
Returns:
|
||||
- A string specifying the path to the new work folder.
|
||||
"""
|
||||
import shutil, time
|
||||
time.sleep(2) # avoid time string conflict
|
||||
if arxiv_id is not None:
|
||||
new_workfolder = pj(ARXIV_CACHE_DIR, arxiv_id, 'workfolder')
|
||||
else:
|
||||
new_workfolder = f'gpt_log/{gen_time_str()}'
|
||||
try:
|
||||
shutil.rmtree(new_workfolder)
|
||||
except:
|
||||
pass
|
||||
|
||||
# align subfolder if there is a folder wrapper
|
||||
items = glob.glob(pj(project_folder,'*'))
|
||||
if len(glob.glob(pj(project_folder,'*.tex'))) == 0 and len(items) == 1:
|
||||
if os.path.isdir(items[0]): project_folder = items[0]
|
||||
|
||||
shutil.copytree(src=project_folder, dst=new_workfolder)
|
||||
return new_workfolder
|
||||
|
||||
def arxiv_download(chatbot, history, txt):
|
||||
def check_cached_translation_pdf(arxiv_id):
|
||||
translation_dir = pj(ARXIV_CACHE_DIR, arxiv_id, 'translation')
|
||||
if not os.path.exists(translation_dir):
|
||||
os.makedirs(translation_dir)
|
||||
target_file = pj(translation_dir, 'translate_zh.pdf')
|
||||
if os.path.exists(target_file):
|
||||
promote_file_to_downloadzone(target_file, rename_file=None, chatbot=chatbot)
|
||||
return target_file
|
||||
return False
|
||||
def is_float(s):
|
||||
try:
|
||||
float(s)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt.strip()
|
||||
if ('.' in txt) and ('/' not in txt) and is_float(txt[:10]): # is arxiv ID
|
||||
txt = 'https://arxiv.org/abs/' + txt[:10]
|
||||
if not txt.startswith('https://arxiv.org'):
|
||||
return txt, None
|
||||
|
||||
# <-------------- inspect format ------------->
|
||||
chatbot.append([f"检测到arxiv文档连接", '尝试下载 ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
time.sleep(1) # 刷新界面
|
||||
|
||||
url_ = txt # https://arxiv.org/abs/1707.06690
|
||||
if not txt.startswith('https://arxiv.org/abs/'):
|
||||
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}"
|
||||
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
if 'v' in arxiv_id: arxiv_id = arxiv_id[:10]
|
||||
cached_translation_pdf = check_cached_translation_pdf(arxiv_id)
|
||||
if cached_translation_pdf: 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_utils import Latex精细分解与转化, 编译Latex
|
||||
except Exception as e:
|
||||
chatbot.append([ f"解析项目: {txt}",
|
||||
f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- clear history and read input ------------->
|
||||
history = []
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id=None)
|
||||
|
||||
|
||||
# <-------------- if merge_translate_zh is already generated, skip gpt req ------------->
|
||||
if not os.path.exists(project_folder + '/merge_proofread_en.tex'):
|
||||
yield from Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin_kwargs,
|
||||
chatbot, history, system_prompt, mode='proofread_en', switch_prompt=_switch_prompt_)
|
||||
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge', main_file_modified='merge_proofread_en',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder, work_folder=project_folder)
|
||||
|
||||
|
||||
# <-------------- zip PDF ------------->
|
||||
zip_res = zip_result(project_folder)
|
||||
if success:
|
||||
chatbot.append((f"成功啦", '请查收结果（压缩包）...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
else:
|
||||
chatbot.append((f"失败了", '虽然PDF生成失败了, 但请查收结果（压缩包）, 内含已经翻译的Tex文档, 也是可读的, 您可以到Github Issue区, 用该压缩包+对话历史存档进行反馈 ...'))
|
||||
yield from update_ui(chatbot=chatbot, history=history); time.sleep(1) # 刷新界面
|
||||
promote_file_to_downloadzone(file=zip_res, chatbot=chatbot)
|
||||
|
||||
# <-------------- we are done ------------->
|
||||
return success
|
||||
|
||||
|
||||
# ========================================= 插件主程序2 =====================================================
|
||||
|
||||
@CatchException
|
||||
def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
# <-------------- information about this plugin ------------->
|
||||
chatbot.append([
|
||||
"函数插件功能？",
|
||||
"对整个Latex项目进行翻译, 生成中文PDF。函数插件贡献者: Binary-Husky。注意事项: 此插件Windows支持最佳，Linux下必须使用Docker安装，详见项目主README.md。目前仅支持GPT3.5/GPT4，其他模型转化效果未知。目前对机器学习类文献转化效果最好，其他类型文献转化效果未知。"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# <-------------- more requirements ------------->
|
||||
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
|
||||
more_req = plugin_kwargs.get("advanced_arg", "")
|
||||
_switch_prompt_ = partial(switch_prompt, more_requirement=more_req)
|
||||
|
||||
# <-------------- check deps ------------->
|
||||
try:
|
||||
import glob, os, time, subprocess
|
||||
subprocess.Popen(['pdflatex', '-version'])
|
||||
from .latex_utils 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)
|
||||
if txt.endswith('.pdf'):
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"发现已经存在翻译好的PDF文档")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
if os.path.exists(txt):
|
||||
project_folder = txt
|
||||
else:
|
||||
if txt == "": txt = '空空如也的输入栏'
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到本地项目或无权访问: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_execption(chatbot, history, a = f"解析项目: {txt}", b = f"找不到任何.tex文件: {txt}")
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
project_folder = move_project(project_folder, arxiv_id)
|
||||
|
||||
|
||||
# <-------------- 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, 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
|
||||
@@ -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"
|
||||
@@ -116,6 +160,56 @@ def test_Markdown多语言():
|
||||
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()
|
||||
@@ -129,7 +223,9 @@ def test_Markdown多语言():
|
||||
# test_联网回答问题()
|
||||
# test_解析ipynb文件()
|
||||
# test_数学动画生成manim()
|
||||
test_Markdown多语言()
|
||||
|
||||
# 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。")
|
||||
@@ -1,4 +1,5 @@
|
||||
from toolbox import update_ui, get_conf, trimmed_format_exc
|
||||
import threading
|
||||
|
||||
def input_clipping(inputs, history, max_token_limit):
|
||||
import numpy as np
|
||||
@@ -606,3 +607,142 @@ def get_files_from_everything(txt, type): # type='.md'
|
||||
success = False
|
||||
|
||||
return success, file_manifest, project_folder
|
||||
|
||||
|
||||
|
||||
|
||||
def Singleton(cls):
|
||||
_instance = {}
|
||||
|
||||
def _singleton(*args, **kargs):
|
||||
if cls not in _instance:
|
||||
_instance[cls] = cls(*args, **kargs)
|
||||
return _instance[cls]
|
||||
|
||||
return _singleton
|
||||
|
||||
|
||||
@Singleton
|
||||
class knowledge_archive_interface():
|
||||
def __init__(self) -> None:
|
||||
self.threadLock = threading.Lock()
|
||||
self.current_id = ""
|
||||
self.kai_path = None
|
||||
self.qa_handle = None
|
||||
self.text2vec_large_chinese = None
|
||||
|
||||
def get_chinese_text2vec(self):
|
||||
if self.text2vec_large_chinese is None:
|
||||
# < -------------------预热文本向量化模组--------------- >
|
||||
from toolbox import ProxyNetworkActivate
|
||||
print('Checking Text2vec ...')
|
||||
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
|
||||
with ProxyNetworkActivate(): # 临时地激活代理网络
|
||||
self.text2vec_large_chinese = HuggingFaceEmbeddings(model_name="GanymedeNil/text2vec-large-chinese")
|
||||
|
||||
return self.text2vec_large_chinese
|
||||
|
||||
|
||||
def feed_archive(self, file_manifest, id="default"):
|
||||
self.threadLock.acquire()
|
||||
# import uuid
|
||||
self.current_id = id
|
||||
from zh_langchain import construct_vector_store
|
||||
self.qa_handle, self.kai_path = construct_vector_store(
|
||||
vs_id=self.current_id,
|
||||
files=file_manifest,
|
||||
sentence_size=100,
|
||||
history=[],
|
||||
one_conent="",
|
||||
one_content_segmentation="",
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
)
|
||||
self.threadLock.release()
|
||||
|
||||
def get_current_archive_id(self):
|
||||
return self.current_id
|
||||
|
||||
def get_loaded_file(self):
|
||||
return self.qa_handle.get_loaded_file()
|
||||
|
||||
def answer_with_archive_by_id(self, txt, id):
|
||||
self.threadLock.acquire()
|
||||
if not self.current_id == id:
|
||||
self.current_id = id
|
||||
from zh_langchain import construct_vector_store
|
||||
self.qa_handle, self.kai_path = construct_vector_store(
|
||||
vs_id=self.current_id,
|
||||
files=[],
|
||||
sentence_size=100,
|
||||
history=[],
|
||||
one_conent="",
|
||||
one_content_segmentation="",
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
)
|
||||
VECTOR_SEARCH_SCORE_THRESHOLD = 0
|
||||
VECTOR_SEARCH_TOP_K = 4
|
||||
CHUNK_SIZE = 512
|
||||
resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
|
||||
query = txt,
|
||||
vs_path = self.kai_path,
|
||||
score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
|
||||
vector_search_top_k=VECTOR_SEARCH_TOP_K,
|
||||
chunk_conent=True,
|
||||
chunk_size=CHUNK_SIZE,
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
)
|
||||
self.threadLock.release()
|
||||
return resp, prompt
|
||||
|
||||
def try_install_deps(deps):
|
||||
for dep in deps:
|
||||
import subprocess, sys
|
||||
subprocess.check_call([sys.executable, '-m', 'pip', 'install', '--user', dep])
|
||||
|
||||
|
||||
class construct_html():
|
||||
def __init__(self) -> None:
|
||||
self.css = """
|
||||
.row {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.column {
|
||||
flex: 1;
|
||||
padding: 10px;
|
||||
}
|
||||
|
||||
.table-header {
|
||||
font-weight: bold;
|
||||
border-bottom: 1px solid black;
|
||||
}
|
||||
|
||||
.table-row {
|
||||
border-bottom: 1px solid lightgray;
|
||||
}
|
||||
|
||||
.table-cell {
|
||||
padding: 5px;
|
||||
}
|
||||
"""
|
||||
self.html_string = f'<!DOCTYPE html><head><meta charset="utf-8"><title>翻译结果</title><style>{self.css}</style></head>'
|
||||
|
||||
|
||||
def add_row(self, a, b):
|
||||
tmp = """
|
||||
<div class="row table-row">
|
||||
<div class="column table-cell">REPLACE_A</div>
|
||||
<div class="column table-cell">REPLACE_B</div>
|
||||
</div>
|
||||
"""
|
||||
from toolbox import markdown_convertion
|
||||
tmp = tmp.replace('REPLACE_A', markdown_convertion(a))
|
||||
tmp = tmp.replace('REPLACE_B', markdown_convertion(b))
|
||||
self.html_string += tmp
|
||||
|
||||
|
||||
def save_file(self, file_name):
|
||||
with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
|
||||
f.write(self.html_string.encode('utf-8', 'ignore').decode())
|
||||
|
||||
|
||||
773
crazy_functions/latex_utils.py
普通文件
773
crazy_functions/latex_utils.py
普通文件
@@ -0,0 +1,773 @@
|
||||
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 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)
|
||||
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, timeout=60):
|
||||
import subprocess
|
||||
process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
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
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
|
||||
|
||||
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
|
||||
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
|
||||
|
||||
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')):
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'bibtex {main_file_original}.aux'); os.chdir(current_dir)
|
||||
if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
|
||||
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'bibtex {main_file_modified}.aux'); os.chdir(current_dir)
|
||||
|
||||
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
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
|
||||
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
|
||||
os.chdir(work_folder_original); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex'); os.chdir(current_dir)
|
||||
os.chdir(work_folder_modified); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex'); os.chdir(current_dir)
|
||||
|
||||
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
|
||||
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
|
||||
os.chdir(work_folder); ok = compile_latex_with_timeout(f'bibtex merge_diff.aux'); os.chdir(current_dir)
|
||||
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
|
||||
os.chdir(work_folder); ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex'); os.chdir(current_dir)
|
||||
|
||||
# <--------------------->
|
||||
os.chdir(current_dir)
|
||||
|
||||
# <---------- 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
|
||||
|
||||
os.chdir(current_dir)
|
||||
return False # 失败啦
|
||||
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from toolbox import CatchException, update_ui
|
||||
from toolbox import CatchException, update_ui, promote_file_to_downloadzone
|
||||
from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
import re
|
||||
|
||||
@@ -29,9 +29,8 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
|
||||
for h in history:
|
||||
f.write("\n>>>" + h)
|
||||
f.write('</code>')
|
||||
res = '对话历史写入：' + os.path.abspath(f'./gpt_log/{file_name}')
|
||||
print(res)
|
||||
return res
|
||||
promote_file_to_downloadzone(f'./gpt_log/{file_name}', rename_file=file_name, chatbot=chatbot)
|
||||
return '对话历史写入：' + os.path.abspath(f'./gpt_log/{file_name}')
|
||||
|
||||
def gen_file_preview(file_name):
|
||||
try:
|
||||
|
||||
@@ -8,7 +8,7 @@ def inspect_dependency(chatbot, history):
|
||||
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 manimgl```"])
|
||||
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
|
||||
|
||||
|
||||
@@ -13,6 +13,8 @@ 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
|
||||
|
||||
|
||||
102
crazy_functions/联网的ChatGPT_bing版.py
普通文件
102
crazy_functions/联网的ChatGPT_bing版.py
普通文件
@@ -0,0 +1,102 @@
|
||||
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
|
||||
|
||||
|
||||
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, 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
|
||||
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 = []
|
||||
|
||||
# ------------- < 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
|
||||
|
||||
131
crazy_functions/虚空终端.py
普通文件
131
crazy_functions/虚空终端.py
普通文件
@@ -0,0 +1,131 @@
|
||||
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
|
||||
|
||||
|
||||
prompt = """
|
||||
I have to achieve some functionalities by calling one of the functions below.
|
||||
Your job is to find the correct funtion to use to satisfy my requirement,
|
||||
and then write python code to call this function with correct parameters.
|
||||
|
||||
These are functions you are allowed to choose from:
|
||||
1.
|
||||
功能描述: 总结音视频内容
|
||||
调用函数: ConcludeAudioContent(txt, llm_kwargs)
|
||||
参数说明:
|
||||
txt: 音频文件的路径
|
||||
llm_kwargs: 模型参数, 永远给定None
|
||||
2.
|
||||
功能描述: 将每次对话记录写入Markdown格式的文件中
|
||||
调用函数: WriteMarkdown()
|
||||
3.
|
||||
功能描述: 将指定目录下的PDF文件从英文翻译成中文
|
||||
调用函数: BatchTranslatePDFDocuments_MultiThreaded(txt, llm_kwargs)
|
||||
参数说明:
|
||||
txt: PDF文件所在的路径
|
||||
llm_kwargs: 模型参数, 永远给定None
|
||||
4.
|
||||
功能描述: 根据文本使用GPT模型生成相应的图像
|
||||
调用函数: ImageGeneration(txt, llm_kwargs)
|
||||
参数说明:
|
||||
txt: 图像生成所用到的提示文本
|
||||
llm_kwargs: 模型参数, 永远给定None
|
||||
5.
|
||||
功能描述: 对输入的word文档进行摘要生成
|
||||
调用函数: SummarizingWordDocuments(input_path, output_path)
|
||||
参数说明:
|
||||
input_path: 待处理的word文档路径
|
||||
output_path: 摘要生成后的文档路径
|
||||
|
||||
|
||||
You should always anwser with following format:
|
||||
----------------
|
||||
Code:
|
||||
```
|
||||
class AutoAcademic(object):
|
||||
def __init__(self):
|
||||
self.selected_function = "FILL_CORRECT_FUNCTION_HERE" # e.g., "GenerateImage"
|
||||
self.txt = "FILL_MAIN_PARAMETER_HERE" # e.g., "荷叶上的蜻蜓"
|
||||
self.llm_kwargs = None
|
||||
```
|
||||
Explanation:
|
||||
只有GenerateImage和生成图像相关, 因此选择GenerateImage函数。
|
||||
----------------
|
||||
|
||||
Now, this is my requirement:
|
||||
|
||||
"""
|
||||
def get_fn_lib():
|
||||
return {
|
||||
"BatchTranslatePDFDocuments_MultiThreaded": ("crazy_functions.批量翻译PDF文档_多线程", "批量翻译PDF文档"),
|
||||
"SummarizingWordDocuments": ("crazy_functions.总结word文档", "总结word文档"),
|
||||
"ImageGeneration": ("crazy_functions.图片生成", "图片生成"),
|
||||
"TranslateMarkdownFromEnglishToChinese": ("crazy_functions.批量Markdown翻译", "Markdown中译英"),
|
||||
"SummaryAudioVideo": ("crazy_functions.总结音视频", "总结音视频"),
|
||||
}
|
||||
|
||||
def inspect_dependency(chatbot, history):
|
||||
return True
|
||||
|
||||
def eval_code(code, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
|
||||
import subprocess, sys, os, shutil, importlib
|
||||
|
||||
with open('gpt_log/void_terminal_runtime.py', 'w', encoding='utf8') as f:
|
||||
f.write(code)
|
||||
|
||||
try:
|
||||
AutoAcademic = getattr(importlib.import_module('gpt_log.void_terminal_runtime', 'AutoAcademic'), 'AutoAcademic')
|
||||
# importlib.reload(AutoAcademic)
|
||||
auto_dict = AutoAcademic()
|
||||
selected_function = auto_dict.selected_function
|
||||
txt = auto_dict.txt
|
||||
fp, fn = get_fn_lib()[selected_function]
|
||||
fn_plugin = getattr(importlib.import_module(fp, fn), fn)
|
||||
yield from fn_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
except:
|
||||
from toolbox import trimmed_format_exc
|
||||
chatbot.append(["执行错误", f"\n```\n{trimmed_format_exc()}\n```\n"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
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 终端(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
|
||||
"""
|
||||
# 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？", "根据自然语言执行插件命令, 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 = prompt + 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=""
|
||||
)
|
||||
|
||||
# 将代码转为动画
|
||||
code = get_code_block(gpt_say)
|
||||
yield from eval_code(code, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port)
|
||||
@@ -103,3 +103,30 @@ services:
|
||||
echo '[jittorllms] 正在从github拉取最新代码...' &&
|
||||
git --git-dir=request_llm/jittorllms/.git --work-tree=request_llm/jittorllms pull --force &&
|
||||
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
|
||||
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"
|
||||
|
||||
|
||||
27
docs/Dockerfile+NoLocal+Latex
普通文件
27
docs/Dockerfile+NoLocal+Latex
普通文件
@@ -0,0 +1,27 @@
|
||||
# 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/Dockerfile+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
|
||||
|
||||
# 指定路径
|
||||
WORKDIR /gpt
|
||||
|
||||
ARG useProxyNetwork=''
|
||||
|
||||
RUN $useProxyNetwork pip3 install gradio openai numpy arxiv rich -i https://pypi.douban.com/simple/
|
||||
RUN $useProxyNetwork pip3 install colorama Markdown pygments pymupdf -i https://pypi.douban.com/simple/
|
||||
|
||||
# 装载项目文件
|
||||
COPY . .
|
||||
|
||||
|
||||
# 安装依赖
|
||||
RUN $useProxyNetwork pip3 install -r requirements.txt -i https://pypi.douban.com/simple/
|
||||
|
||||
# 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"]
|
||||
25
docs/GithubAction+NoLocal+Latex
普通文件
25
docs/GithubAction+NoLocal+Latex
普通文件
@@ -0,0 +1,25 @@
|
||||
# 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/Dockerfile+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
|
||||
|
||||
# 指定路径
|
||||
WORKDIR /gpt
|
||||
|
||||
RUN pip3 install gradio openai numpy arxiv rich
|
||||
RUN pip3 install colorama Markdown pygments pymupdf
|
||||
|
||||
# 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"]
|
||||
@@ -2,11 +2,11 @@
|
||||
>
|
||||
> Durante l'installazione delle dipendenze, selezionare rigorosamente le **versioni specificate** nel file requirements.txt.
|
||||
>
|
||||
> ` pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/`
|
||||
> ` pip install -r requirements.txt`
|
||||
|
||||
# <img src="docs/logo.png" width="40" > GPT Ottimizzazione Accademica (GPT Academic)
|
||||
# <img src="logo.png" width="40" > GPT Ottimizzazione Accademica (GPT Academic)
|
||||
|
||||
**Se ti piace questo progetto, ti preghiamo di dargli una stella. Se hai sviluppato scorciatoie accademiche o plugin funzionali più utili, non esitare ad aprire una issue o pull request. Abbiamo anche una README in [Inglese|](docs/README_EN.md)[Giapponese|](docs/README_JP.md)[Coreano|](https://github.com/mldljyh/ko_gpt_academic)[Russo|](docs/README_RS.md)[Francese](docs/README_FR.md) tradotta da questo stesso progetto.
|
||||
**Se ti piace questo progetto, ti preghiamo di dargli una stella. Se hai sviluppato scorciatoie accademiche o plugin funzionali più utili, non esitare ad aprire una issue o pull request. Abbiamo anche una README in [Inglese|](README_EN.md)[Giapponese|](README_JP.md)[Coreano|](https://github.com/mldljyh/ko_gpt_academic)[Russo|](README_RS.md)[Francese](README_FR.md) tradotta da questo stesso progetto.
|
||||
Per tradurre questo progetto in qualsiasi lingua con GPT, leggere e eseguire [`multi_language.py`](multi_language.py) (sperimentale).
|
||||
|
||||
> **Nota**
|
||||
@@ -17,7 +17,9 @@ Per tradurre questo progetto in qualsiasi lingua con GPT, leggere e eseguire [`m
|
||||
>
|
||||
> 3. Questo progetto è compatibile e incoraggia l'utilizzo di grandi modelli di linguaggio di produzione nazionale come chatglm, RWKV, Pangu ecc. Supporta la coesistenza di più api-key e può essere compilato nel file di configurazione come `API_KEY="openai-key1,openai-key2,api2d-key3"`. Per sostituire temporaneamente `API_KEY`, inserire `API_KEY` temporaneo nell'area di input e premere Invio per renderlo effettivo.
|
||||
|
||||
<div align="center">Funzione | Descrizione
|
||||
<div align="center">
|
||||
|
||||
Funzione | Descrizione
|
||||
--- | ---
|
||||
Correzione immediata | Supporta correzione immediata e ricerca degli errori di grammatica del documento con un solo clic
|
||||
Traduzione cinese-inglese immediata | Traduzione cinese-inglese immediata con un solo clic
|
||||
@@ -41,6 +43,8 @@ Avvia il tema di gradio [scuro](https://github.com/binary-husky/chatgpt_academic
|
||||
Supporto per maggiori modelli LLM, supporto API2D | Sentirsi serviti simultaneamente da GPT3.5, GPT4, [Tsinghua ChatGLM](https://github.com/THUDM/ChatGLM-6B), [Fudan MOSS](https://github.com/OpenLMLab/MOSS) deve essere una grande sensazione, giusto?
|
||||
Ulteriori modelli LLM supportat,i supporto per l'implementazione di Huggingface | Aggiunta di un'interfaccia Newbing (Nuovo Bing), introdotta la compatibilità con Tsinghua [Jittorllms](https://github.com/Jittor/JittorLLMs), [LLaMA](https://github.com/facebookresearch/llama), [RWKV](https://github.com/BlinkDL/ChatRWKV) e [PanGu-α](https://openi.org.cn/pangu/)
|
||||
Ulteriori dimostrazioni di nuove funzionalità (generazione di immagini, ecc.)... | Vedere la fine di questo documento...
|
||||
</div>
|
||||
|
||||
|
||||
- Nuova interfaccia (modificare l'opzione LAYOUT in `config.py` per passare dal layout a sinistra e a destra al layout superiore e inferiore)
|
||||
<div align="center">
|
||||
@@ -206,7 +210,9 @@ La difficoltà di scrittura e debug dei plugin del nostro progetto è molto bass
|
||||
|
||||
---
|
||||
# Ultimo aggiornamento
|
||||
## Nuove funzionalità dinamiche1. Funzionalità di salvataggio della conversazione. Nell'area dei plugin della funzione, fare clic su "Salva la conversazione corrente" per salvare la conversazione corrente come file html leggibile e ripristinabile, inoltre, nell'area dei plugin della funzione (menu a discesa), fare clic su "Carica la cronologia della conversazione archiviata" per ripristinare la conversazione precedente. Suggerimento: fare clic su "Carica la cronologia della conversazione archiviata" senza specificare il file consente di visualizzare la cache degli archivi html di cronologia, fare clic su "Elimina tutti i record di cronologia delle conversazioni locali" per eliminare tutte le cache degli archivi html.
|
||||
## Nuove funzionalità dinamiche
|
||||
|
||||
1. Funzionalità di salvataggio della conversazione. Nell'area dei plugin della funzione, fare clic su "Salva la conversazione corrente" per salvare la conversazione corrente come file html leggibile e ripristinabile, inoltre, nell'area dei plugin della funzione (menu a discesa), fare clic su "Carica la cronologia della conversazione archiviata" per ripristinare la conversazione precedente. Suggerimento: fare clic su "Carica la cronologia della conversazione archiviata" senza specificare il file consente di visualizzare la cache degli archivi html di cronologia, fare clic su "Elimina tutti i record di cronologia delle conversazioni locali" per eliminare tutte le cache degli archivi html.
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
|
||||
</div>
|
||||
|
||||
@@ -17,7 +17,9 @@ GPT를 이용하여 프로젝트를 임의의 언어로 번역하려면 [`multi_
|
||||
>
|
||||
> 3. 이 프로젝트는 국내 언어 모델 chatglm과 RWKV, 판고 등의 시도와 호환 가능합니다. 여러 개의 api-key를 지원하며 설정 파일에 "API_KEY="openai-key1,openai-key2,api2d-key3""와 같이 작성할 수 있습니다. `API_KEY`를 임시로 변경해야하는 경우 입력 영역에 임시 `API_KEY`를 입력 한 후 엔터 키를 누르면 즉시 적용됩니다.
|
||||
|
||||
<div align="center">기능 | 설명
|
||||
<div align="center">
|
||||
|
||||
기능 | 설명
|
||||
--- | ---
|
||||
원 키워드 | 원 키워드 및 논문 문법 오류를 찾는 기능 지원
|
||||
한-영 키워드 | 한-영 키워드 지원
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
>
|
||||
> Ao instalar as dependências, por favor, selecione rigorosamente as versões **especificadas** no arquivo requirements.txt.
|
||||
>
|
||||
> `pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/`
|
||||
> `pip install -r requirements.txt`
|
||||
>
|
||||
|
||||
# <img src="logo.png" width="40" > Otimização acadêmica GPT (GPT Academic)
|
||||
@@ -18,7 +18,9 @@ Para traduzir este projeto para qualquer idioma com o GPT, leia e execute [`mult
|
||||
>
|
||||
> 3. Este projeto é compatível com e incentiva o uso de modelos de linguagem nacionais, como chatglm e RWKV, Pangolin, etc. Suporta a coexistência de várias chaves de API e pode ser preenchido no arquivo de configuração como `API_KEY="openai-key1,openai-key2,api2d-key3"`. Quando precisar alterar temporariamente o `API_KEY`, basta digitar o `API_KEY` temporário na área de entrada e pressionar Enter para que ele entre em vigor.
|
||||
|
||||
<div align="center">Funcionalidade | Descrição
|
||||
<div align="center">
|
||||
|
||||
Funcionalidade | Descrição
|
||||
--- | ---
|
||||
Um clique de polimento | Suporte a um clique polimento, um clique encontrar erros de gramática no artigo
|
||||
Tradução chinês-inglês de um clique | Tradução chinês-inglês de um clique
|
||||
@@ -216,7 +218,9 @@ Para mais detalhes, consulte o [Guia do plug-in de função.](https://github.com
|
||||
|
||||
---
|
||||
# Última atualização
|
||||
## Novas funções dinâmicas.1. Função de salvamento de diálogo. Ao chamar o plug-in de função "Salvar diálogo atual", é possível salvar o diálogo atual em um arquivo html legível e reversível. Além disso, ao chamar o plug-in de função "Carregar arquivo de histórico de diálogo" no menu suspenso da área de plug-in, é possível restaurar uma conversa anterior. Dica: clicar em "Carregar arquivo de histórico de diálogo" sem especificar um arquivo permite visualizar o cache do arquivo html de histórico. Clicar em "Excluir todo o registro de histórico de diálogo local" permite excluir todo o cache de arquivo html.
|
||||
## Novas funções dinâmicas.
|
||||
|
||||
1. Função de salvamento de diálogo. Ao chamar o plug-in de função "Salvar diálogo atual", é possível salvar o diálogo atual em um arquivo html legível e reversível. Além disso, ao chamar o plug-in de função "Carregar arquivo de histórico de diálogo" no menu suspenso da área de plug-in, é possível restaurar uma conversa anterior. Dica: clicar em "Carregar arquivo de histórico de diálogo" sem especificar um arquivo permite visualizar o cache do arquivo html de histórico. Clicar em "Excluir todo o registro de histórico de diálogo local" permite excluir todo o cache de arquivo html.
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
|
||||
</div>
|
||||
|
||||
@@ -58,6 +58,8 @@
|
||||
"连接网络回答问题": "ConnectToNetworkToAnswerQuestions",
|
||||
"联网的ChatGPT": "ChatGPTConnectedToNetwork",
|
||||
"解析任意code项目": "ParseAnyCodeProject",
|
||||
"读取知识库作答": "ReadKnowledgeArchiveAnswerQuestions",
|
||||
"知识库问答": "UpdateKnowledgeArchive",
|
||||
"同时问询_指定模型": "InquireSimultaneously_SpecifiedModel",
|
||||
"图片生成": "ImageGeneration",
|
||||
"test_解析ipynb文件": "Test_ParseIpynbFile",
|
||||
|
||||
152
docs/use_azure.md
普通文件
152
docs/use_azure.md
普通文件
@@ -0,0 +1,152 @@
|
||||
# 通过微软Azure云服务申请 Openai API
|
||||
|
||||
由于Openai和微软的关系，现在是可以通过微软的Azure云计算服务直接访问openai的api，免去了注册和网络的问题。
|
||||
|
||||
快速入门的官方文档的链接是：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)
|
||||
|
||||
# 申请API
|
||||
|
||||
按文档中的“先决条件”的介绍，出了编程的环境以外，还需要以下三个条件：
|
||||
|
||||
1. Azure账号并创建订阅
|
||||
|
||||
2. 为订阅添加Azure OpenAI 服务
|
||||
|
||||
3. 部署模型
|
||||
|
||||
## Azure账号并创建订阅
|
||||
|
||||
### Azure账号
|
||||
|
||||
创建Azure的账号时最好是有微软的账号，这样似乎更容易获得免费额度（第一个月的200美元，实测了一下，如果用一个刚注册的微软账号登录Azure的话，并没有这一个月的免费额度）。
|
||||
|
||||
创建Azure账号的网址是：[立即创建 Azure 免费帐户 | Microsoft Azure](https://azure.microsoft.com/zh-cn/free/)
|
||||
|
||||
|
||||
|
||||
打开网页后，点击 “免费开始使用” 会跳转到登录或注册页面，如果有微软的账户，直接登录即可，如果没有微软账户，那就需要到微软的网页再另行注册一个。
|
||||
|
||||
注意，Azure的页面和政策时不时会变化，已实际最新显示的为准就好。
|
||||
|
||||
### 创建订阅
|
||||
|
||||
注册好Azure后便可进入主页：
|
||||
|
||||
|
||||
|
||||
首先需要在订阅里进行添加操作，点开后即可进入订阅的页面：
|
||||
|
||||
|
||||
|
||||
第一次进来应该是空的，点添加即可创建新的订阅（可以是“免费”或者“即付即用”的订阅），其中订阅ID是后面申请Azure OpenAI需要使用的。
|
||||
|
||||
## 为订阅添加Azure OpenAI服务
|
||||
|
||||
之后回到首页，点Azure OpenAI即可进入OpenAI服务的页面（如果不显示的话，则在首页上方的搜索栏里搜索“openai”即可）。
|
||||
|
||||
|
||||
|
||||
不过现在这个服务还不能用。在使用前，还需要在这个网址申请一下：
|
||||
|
||||
[Request Access to Azure OpenAI Service (microsoft.com)](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOFA5Qk1UWDRBMjg0WFhPMkIzTzhKQ1dWNyQlQCN0PWcu)
|
||||
|
||||
这里有二十来个问题，按照要求和自己的实际情况填写即可。
|
||||
|
||||
其中需要注意的是
|
||||
|
||||
1. 千万记得填对"订阅ID"
|
||||
|
||||
2. 需要填一个公司邮箱（可以不是注册用的邮箱）和公司网址
|
||||
|
||||
之后，在回到上面那个页面，点创建，就会进入创建页面了：
|
||||
|
||||
|
||||
|
||||
需要填入“资源组”和“名称”，按照自己的需要填入即可。
|
||||
|
||||
完成后，在主页的“资源”里就可以看到刚才创建的“资源”了，点击进入后，就可以进行最后的部署了。
|
||||
|
||||
|
||||
|
||||
## 部署模型
|
||||
|
||||
进入资源页面后，在部署模型前，可以先点击“开发”，把密钥和终结点记下来。
|
||||
|
||||
|
||||
|
||||
之后，就可以去部署模型了，点击“部署”即可，会跳转到 Azure OpenAI Stuido 进行下面的操作：
|
||||
|
||||
|
||||
|
||||
进入 Azure OpenAi Studio 后，点击新建部署，会弹出如下对话框：
|
||||
|
||||
|
||||
|
||||
在这里选 gpt-35-turbo 或需要的模型并按需要填入“部署名”即可完成模型的部署。
|
||||
|
||||
|
||||
|
||||
这个部署名需要记下来。
|
||||
|
||||
到现在为止，申请操作就完成了，需要记下来的有下面几个东西：
|
||||
|
||||
● 密钥（1或2都可以）
|
||||
|
||||
● 终结点
|
||||
|
||||
● 部署名（不是模型名）
|
||||
|
||||
# 修改 config.py
|
||||
|
||||
```
|
||||
AZURE_ENDPOINT = "填入终结点"
|
||||
AZURE_API_KEY = "填入azure openai api的密钥"
|
||||
AZURE_API_VERSION = "2023-05-15" # 默认使用 2023-05-15 版本，无需修改
|
||||
AZURE_ENGINE = "填入部署名"
|
||||
|
||||
```
|
||||
# API的使用
|
||||
|
||||
接下来就是具体怎么使用API了，还是可以参考官方文档：[快速入门 - 开始通过 Azure OpenAI 服务使用 ChatGPT 和 GPT-4 - Azure OpenAI Service | Microsoft Learn](https://learn.microsoft.com/zh-cn/azure/cognitive-services/openai/chatgpt-quickstart?pivots=programming-language-python)
|
||||
|
||||
和openai自己的api调用有点类似，都需要安装openai库，不同的是调用方式
|
||||
|
||||
```
|
||||
import openai
|
||||
openai.api_type = "azure" #固定格式，无需修改
|
||||
openai.api_base = os.getenv("AZURE_OPENAI_ENDPOINT") #这里填入“终结点”
|
||||
openai.api_version = "2023-05-15" #固定格式，无需修改
|
||||
openai.api_key = os.getenv("AZURE_OPENAI_KEY") #这里填入“密钥1”或“密钥2”
|
||||
|
||||
response = openai.ChatCompletion.create(
|
||||
engine="gpt-35-turbo", #这里填入的不是模型名，是部署名
|
||||
messages=[
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},
|
||||
{"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},
|
||||
{"role": "user", "content": "Do other Azure Cognitive Services support this too?"}
|
||||
]
|
||||
)
|
||||
|
||||
print(response)
|
||||
print(response['choices'][0]['message']['content'])
|
||||
|
||||
```
|
||||
|
||||
需要注意的是：
|
||||
|
||||
1. engine那里填入的是部署名，不是模型名
|
||||
|
||||
2. 通过openai库获得的这个 response 和通过 request 库访问 url 获得的 response 不同，不需要 decode，已经是解析好的 json 了，直接根据键值读取即可。
|
||||
|
||||
更细节的使用方法，详见官方API文档。
|
||||
|
||||
# 关于费用
|
||||
|
||||
Azure OpenAI API 还是需要一些费用的（免费订阅只有1个月有效期），费用如下：
|
||||
|
||||
|
||||
|
||||
具体可以可以看这个网址 ：[Azure OpenAI 服务 - 定价| Microsoft Azure](https://azure.microsoft.com/zh-cn/pricing/details/cognitive-services/openai-service/?cdn=disable)
|
||||
|
||||
并非网上说的什么“一年白嫖”，但注册方法以及网络问题都比直接使用openai的api要简单一些。
|
||||
@@ -16,6 +16,9 @@ from toolbox import get_conf, trimmed_format_exc
|
||||
from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
|
||||
from .bridge_chatgpt import predict as chatgpt_ui
|
||||
|
||||
from .bridge_azure_test import predict_no_ui_long_connection as azure_noui
|
||||
from .bridge_azure_test import predict as azure_ui
|
||||
|
||||
from .bridge_chatglm import predict_no_ui_long_connection as chatglm_noui
|
||||
from .bridge_chatglm import predict as chatglm_ui
|
||||
|
||||
@@ -84,6 +87,33 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"gpt-3.5-turbo-16k": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 1024*16,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"gpt-3.5-turbo-0613": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"gpt-3.5-turbo-16k-0613": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 1024 * 16,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
"gpt-4": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -93,6 +123,16 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
# azure openai
|
||||
"azure-gpt35":{
|
||||
"fn_with_ui": azure_ui,
|
||||
"fn_without_ui": azure_noui,
|
||||
"endpoint": get_conf("AZURE_ENDPOINT"),
|
||||
"max_token": 4096,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
# api_2d
|
||||
"api2d-gpt-3.5-turbo": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
|
||||
241
request_llm/bridge_azure_test.py
普通文件
241
request_llm/bridge_azure_test.py
普通文件
@@ -0,0 +1,241 @@
|
||||
"""
|
||||
该文件中主要包含三个函数
|
||||
|
||||
不具备多线程能力的函数：
|
||||
1. predict: 正常对话时使用，具备完备的交互功能，不可多线程
|
||||
|
||||
具备多线程调用能力的函数
|
||||
2. predict_no_ui：高级实验性功能模块调用，不会实时显示在界面上，参数简单，可以多线程并行，方便实现复杂的功能逻辑
|
||||
3. predict_no_ui_long_connection：在实验过程中发现调用predict_no_ui处理长文档时，和openai的连接容易断掉，这个函数用stream的方式解决这个问题，同样支持多线程
|
||||
"""
|
||||
|
||||
import logging
|
||||
import traceback
|
||||
import importlib
|
||||
import openai
|
||||
import time
|
||||
|
||||
|
||||
# 读取config.py文件中关于AZURE OPENAI API的信息
|
||||
from toolbox import get_conf, update_ui, clip_history, trimmed_format_exc
|
||||
TIMEOUT_SECONDS, MAX_RETRY, AZURE_ENGINE, AZURE_ENDPOINT, AZURE_API_VERSION, AZURE_API_KEY = \
|
||||
get_conf('TIMEOUT_SECONDS', 'MAX_RETRY',"AZURE_ENGINE","AZURE_ENDPOINT", "AZURE_API_VERSION", "AZURE_API_KEY")
|
||||
|
||||
|
||||
def get_full_error(chunk, stream_response):
|
||||
"""
|
||||
获取完整的从Openai返回的报错
|
||||
"""
|
||||
while True:
|
||||
try:
|
||||
chunk += next(stream_response)
|
||||
except:
|
||||
break
|
||||
return chunk
|
||||
|
||||
def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
|
||||
"""
|
||||
发送至azure openai api，流式获取输出。
|
||||
用于基础的对话功能。
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
print(llm_kwargs["llm_model"])
|
||||
|
||||
if additional_fn is not None:
|
||||
import core_functional
|
||||
importlib.reload(core_functional) # 热更新prompt
|
||||
core_functional = core_functional.get_core_functions()
|
||||
if "PreProcess" in core_functional[additional_fn]: inputs = core_functional[additional_fn]["PreProcess"](inputs) # 获取预处理函数（如果有的话）
|
||||
inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
|
||||
|
||||
raw_input = inputs
|
||||
logging.info(f'[raw_input] {raw_input}')
|
||||
chatbot.append((inputs, ""))
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
|
||||
|
||||
|
||||
payload = generate_azure_payload(inputs, llm_kwargs, history, system_prompt, stream)
|
||||
|
||||
history.append(inputs); history.append("")
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
|
||||
openai.api_type = "azure"
|
||||
openai.api_version = AZURE_API_VERSION
|
||||
openai.api_base = AZURE_ENDPOINT
|
||||
openai.api_key = AZURE_API_KEY
|
||||
response = openai.ChatCompletion.create(timeout=TIMEOUT_SECONDS, **payload);break
|
||||
|
||||
except:
|
||||
retry += 1
|
||||
chatbot[-1] = ((chatbot[-1][0], "获取response失败，重试中。。。"))
|
||||
retry_msg = f"，正在重试 ({retry}/{MAX_RETRY}) ……" if MAX_RETRY > 0 else ""
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
is_head_of_the_stream = True
|
||||
if stream:
|
||||
|
||||
stream_response = response
|
||||
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
|
||||
except StopIteration:
|
||||
from toolbox import regular_txt_to_markdown; tb_str = '```\n' + trimmed_format_exc() + '```'
|
||||
chatbot[-1] = (chatbot[-1][0], f"[Local Message] 远程返回错误: \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk)}")
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="远程返回错误:" + chunk) # 刷新界面
|
||||
return
|
||||
|
||||
if is_head_of_the_stream and (r'"object":"error"' not in chunk):
|
||||
# 数据流的第一帧不携带content
|
||||
is_head_of_the_stream = False; continue
|
||||
|
||||
if chunk:
|
||||
#print(chunk)
|
||||
try:
|
||||
if "delta" in chunk["choices"][0]:
|
||||
if chunk["choices"][0]["finish_reason"] == "stop":
|
||||
logging.info(f'[response] {gpt_replying_buffer}')
|
||||
break
|
||||
status_text = f"finish_reason: {chunk['choices'][0]['finish_reason']}"
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunk["choices"][0]["delta"]["content"]
|
||||
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
|
||||
|
||||
except Exception as e:
|
||||
traceback.print_exc()
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
|
||||
error_msg = chunk
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
|
||||
return
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
发送至AZURE OPENAI API，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
是本次问询的输入
|
||||
sys_prompt:
|
||||
系统静默prompt
|
||||
llm_kwargs：
|
||||
chatGPT的内部调优参数
|
||||
history：
|
||||
是之前的对话列表
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
|
||||
payload = generate_azure_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
|
||||
retry = 0
|
||||
while True:
|
||||
|
||||
try:
|
||||
openai.api_type = "azure"
|
||||
openai.api_version = AZURE_API_VERSION
|
||||
openai.api_base = AZURE_ENDPOINT
|
||||
openai.api_key = AZURE_API_KEY
|
||||
response = openai.ChatCompletion.create(timeout=TIMEOUT_SECONDS, **payload);break
|
||||
|
||||
except:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时，正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
|
||||
|
||||
stream_response = response
|
||||
result = ''
|
||||
while True:
|
||||
try: chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
break
|
||||
except:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
|
||||
if len(chunk)==0: continue
|
||||
if not chunk.startswith('data:'):
|
||||
error_msg = get_full_error(chunk, stream_response)
|
||||
if "reduce the length" in error_msg:
|
||||
raise ConnectionAbortedError("AZURE OPENAI API拒绝了请求:" + error_msg)
|
||||
else:
|
||||
raise RuntimeError("AZURE OPENAI API拒绝了请求：" + error_msg)
|
||||
if ('data: [DONE]' in chunk): break
|
||||
|
||||
delta = chunk["delta"]
|
||||
if len(delta) == 0: break
|
||||
if "role" in delta: continue
|
||||
if "content" in delta:
|
||||
result += delta["content"]
|
||||
if not console_slience: print(delta["content"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1: observe_window[0] += delta["content"]
|
||||
# 看门狗，如果超过期限没有喂狗，则终止
|
||||
if len(observe_window) >= 2:
|
||||
if (time.time()-observe_window[1]) > watch_dog_patience:
|
||||
raise RuntimeError("用户取消了程序。")
|
||||
else: raise RuntimeError("意外Json结构："+delta)
|
||||
if chunk['finish_reason'] == 'length':
|
||||
raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
|
||||
return result
|
||||
|
||||
|
||||
def generate_azure_payload(inputs, llm_kwargs, history, system_prompt, stream):
|
||||
"""
|
||||
整合所有信息，选择LLM模型，生成 azure openai api请求，为发送请求做准备
|
||||
"""
|
||||
|
||||
conversation_cnt = len(history) // 2
|
||||
|
||||
messages = [{"role": "system", "content": system_prompt}]
|
||||
if conversation_cnt:
|
||||
for index in range(0, 2*conversation_cnt, 2):
|
||||
what_i_have_asked = {}
|
||||
what_i_have_asked["role"] = "user"
|
||||
what_i_have_asked["content"] = history[index]
|
||||
what_gpt_answer = {}
|
||||
what_gpt_answer["role"] = "assistant"
|
||||
what_gpt_answer["content"] = history[index+1]
|
||||
if what_i_have_asked["content"] != "":
|
||||
if what_gpt_answer["content"] == "": continue
|
||||
messages.append(what_i_have_asked)
|
||||
messages.append(what_gpt_answer)
|
||||
else:
|
||||
messages[-1]['content'] = what_gpt_answer['content']
|
||||
|
||||
what_i_ask_now = {}
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = inputs
|
||||
messages.append(what_i_ask_now)
|
||||
|
||||
payload = {
|
||||
"model": llm_kwargs['llm_model'],
|
||||
"messages": messages,
|
||||
"temperature": llm_kwargs['temperature'], # 1.0,
|
||||
"top_p": llm_kwargs['top_p'], # 1.0,
|
||||
"n": 1,
|
||||
"stream": stream,
|
||||
"presence_penalty": 0,
|
||||
"frequency_penalty": 0,
|
||||
"engine": AZURE_ENGINE
|
||||
}
|
||||
try:
|
||||
print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
|
||||
except:
|
||||
print('输入中可能存在乱码。')
|
||||
return payload
|
||||
|
||||
|
||||
87
toolbox.py
87
toolbox.py
@@ -1,11 +1,12 @@
|
||||
import markdown
|
||||
import importlib
|
||||
import traceback
|
||||
import time
|
||||
import inspect
|
||||
import re
|
||||
import os
|
||||
from latex2mathml.converter import convert as tex2mathml
|
||||
from functools import wraps, lru_cache
|
||||
pj = os.path.join
|
||||
|
||||
"""
|
||||
========================================================================
|
||||
@@ -70,6 +71,17 @@ def update_ui(chatbot, history, msg='正常', **kwargs): # 刷新界面
|
||||
assert isinstance(chatbot, ChatBotWithCookies), "在传递chatbot的过程中不要将其丢弃。必要时，可用clear将其清空，然后用for+append循环重新赋值。"
|
||||
yield chatbot.get_cookies(), chatbot, history, msg
|
||||
|
||||
def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1): # 刷新界面
|
||||
"""
|
||||
刷新用户界面
|
||||
"""
|
||||
if len(chatbot) == 0: chatbot.append(["update_ui_last_msg", lastmsg])
|
||||
chatbot[-1] = list(chatbot[-1])
|
||||
chatbot[-1][-1] = lastmsg
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
time.sleep(delay)
|
||||
|
||||
|
||||
def trimmed_format_exc():
|
||||
import os, traceback
|
||||
str = traceback.format_exc()
|
||||
@@ -83,7 +95,7 @@ def CatchException(f):
|
||||
"""
|
||||
|
||||
@wraps(f)
|
||||
def decorated(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT):
|
||||
def decorated(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT=-1):
|
||||
try:
|
||||
yield from f(txt, top_p, temperature, chatbot, history, systemPromptTxt, WEB_PORT)
|
||||
except Exception as e:
|
||||
@@ -210,16 +222,21 @@ def text_divide_paragraph(text):
|
||||
"""
|
||||
将文本按照段落分隔符分割开，生成带有段落标签的HTML代码。
|
||||
"""
|
||||
pre = '<div class="markdown-body">'
|
||||
suf = '</div>'
|
||||
if text.startswith(pre) and text.endswith(suf):
|
||||
return text
|
||||
|
||||
if '```' in text:
|
||||
# careful input
|
||||
return text
|
||||
return pre + text + suf
|
||||
else:
|
||||
# wtf input
|
||||
lines = text.split("\n")
|
||||
for i, line in enumerate(lines):
|
||||
lines[i] = lines[i].replace(" ", " ")
|
||||
text = "</br>".join(lines)
|
||||
return text
|
||||
return pre + text + suf
|
||||
|
||||
@lru_cache(maxsize=128) # 使用 lru缓存 加快转换速度
|
||||
def markdown_convertion(txt):
|
||||
@@ -331,8 +348,11 @@ def format_io(self, y):
|
||||
if y is None or y == []:
|
||||
return []
|
||||
i_ask, gpt_reply = y[-1]
|
||||
i_ask = text_divide_paragraph(i_ask) # 输入部分太自由，预处理一波
|
||||
gpt_reply = close_up_code_segment_during_stream(gpt_reply) # 当代码输出半截的时候，试着补上后个```
|
||||
# 输入部分太自由，预处理一波
|
||||
if i_ask is not None: i_ask = text_divide_paragraph(i_ask)
|
||||
# 当代码输出半截的时候，试着补上后个```
|
||||
if gpt_reply is not None: gpt_reply = close_up_code_segment_during_stream(gpt_reply)
|
||||
# process
|
||||
y[-1] = (
|
||||
None if i_ask is None else markdown.markdown(i_ask, extensions=['fenced_code', 'tables']),
|
||||
None if gpt_reply is None else markdown_convertion(gpt_reply)
|
||||
@@ -380,7 +400,7 @@ def extract_archive(file_path, dest_dir):
|
||||
print("Successfully extracted rar archive to {}".format(dest_dir))
|
||||
except:
|
||||
print("Rar format requires additional dependencies to install")
|
||||
return '\n\n需要安装pip install rarfile来解压rar文件'
|
||||
return '\n\n解压失败! 需要安装pip install rarfile来解压rar文件'
|
||||
|
||||
# 第三方库，需要预先pip install py7zr
|
||||
elif file_extension == '.7z':
|
||||
@@ -391,7 +411,7 @@ def extract_archive(file_path, dest_dir):
|
||||
print("Successfully extracted 7z archive to {}".format(dest_dir))
|
||||
except:
|
||||
print("7z format requires additional dependencies to install")
|
||||
return '\n\n需要安装pip install py7zr来解压7z文件'
|
||||
return '\n\n解压失败! 需要安装pip install py7zr来解压7z文件'
|
||||
else:
|
||||
return ''
|
||||
return ''
|
||||
@@ -420,6 +440,17 @@ def find_recent_files(directory):
|
||||
|
||||
return recent_files
|
||||
|
||||
def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
|
||||
# 将文件复制一份到下载区
|
||||
import shutil
|
||||
if rename_file is None: rename_file = f'{gen_time_str()}-{os.path.basename(file)}'
|
||||
new_path = os.path.join(f'./gpt_log/', rename_file)
|
||||
if os.path.exists(new_path) and not os.path.samefile(new_path, file): os.remove(new_path)
|
||||
if not os.path.exists(new_path): shutil.copyfile(file, new_path)
|
||||
if chatbot:
|
||||
if 'file_to_promote' in chatbot._cookies: current = chatbot._cookies['file_to_promote']
|
||||
else: current = []
|
||||
chatbot._cookies.update({'file_to_promote': [new_path] + current})
|
||||
|
||||
def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
|
||||
"""
|
||||
@@ -459,14 +490,20 @@ def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
|
||||
return chatbot, txt, txt2
|
||||
|
||||
|
||||
def on_report_generated(files, chatbot):
|
||||
def on_report_generated(cookies, files, chatbot):
|
||||
from toolbox import find_recent_files
|
||||
if 'file_to_promote' in cookies:
|
||||
report_files = cookies['file_to_promote']
|
||||
cookies.pop('file_to_promote')
|
||||
else:
|
||||
report_files = find_recent_files('gpt_log')
|
||||
if len(report_files) == 0:
|
||||
return None, chatbot
|
||||
# files.extend(report_files)
|
||||
chatbot.append(['报告如何远程获取？', '报告已经添加到右侧“文件上传区”（可能处于折叠状态），请查收。'])
|
||||
return report_files, chatbot
|
||||
file_links = ''
|
||||
for f in report_files: file_links += f'<br/><a href="file={os.path.abspath(f)}" target="_blank">{f}</a>'
|
||||
chatbot.append(['报告如何远程获取？', f'报告已经添加到右侧“文件上传区”（可能处于折叠状态），请查收。{file_links}'])
|
||||
return cookies, report_files, chatbot
|
||||
|
||||
def is_openai_api_key(key):
|
||||
API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
|
||||
@@ -728,6 +765,8 @@ def clip_history(inputs, history, tokenizer, max_token_limit):
|
||||
其他小工具:
|
||||
- zip_folder: 把某个路径下所有文件压缩，然后转移到指定的另一个路径中（gpt写的）
|
||||
- gen_time_str: 生成时间戳
|
||||
- ProxyNetworkActivate: 临时地启动代理网络（如果有）
|
||||
- objdump/objload: 快捷的调试函数
|
||||
========================================================================
|
||||
"""
|
||||
|
||||
@@ -762,11 +801,16 @@ def zip_folder(source_folder, dest_folder, zip_name):
|
||||
|
||||
print(f"Zip file created at {zip_file}")
|
||||
|
||||
def zip_result(folder):
|
||||
import time
|
||||
t = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
|
||||
zip_folder(folder, './gpt_log/', f'{t}-result.zip')
|
||||
return pj('./gpt_log/', f'{t}-result.zip')
|
||||
|
||||
def gen_time_str():
|
||||
import time
|
||||
return time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
|
||||
|
||||
|
||||
class ProxyNetworkActivate():
|
||||
"""
|
||||
这段代码定义了一个名为TempProxy的空上下文管理器, 用于给一小段代码上代理
|
||||
@@ -775,8 +819,9 @@ class ProxyNetworkActivate():
|
||||
from toolbox import get_conf
|
||||
proxies, = get_conf('proxies')
|
||||
if 'no_proxy' in os.environ: os.environ.pop('no_proxy')
|
||||
os.environ['HTTP_PROXY'] = proxies['http']
|
||||
os.environ['HTTPS_PROXY'] = proxies['https']
|
||||
if proxies is not None:
|
||||
if 'http' in proxies: os.environ['HTTP_PROXY'] = proxies['http']
|
||||
if 'https' in proxies: os.environ['HTTPS_PROXY'] = proxies['https']
|
||||
return self
|
||||
|
||||
def __exit__(self, exc_type, exc_value, traceback):
|
||||
@@ -784,3 +829,17 @@ class ProxyNetworkActivate():
|
||||
if 'HTTP_PROXY' in os.environ: os.environ.pop('HTTP_PROXY')
|
||||
if 'HTTPS_PROXY' in os.environ: os.environ.pop('HTTPS_PROXY')
|
||||
return
|
||||
|
||||
def objdump(obj, file='objdump.tmp'):
|
||||
import pickle
|
||||
with open(file, 'wb+') as f:
|
||||
pickle.dump(obj, f)
|
||||
return
|
||||
|
||||
def objload(file='objdump.tmp'):
|
||||
import pickle, os
|
||||
if not os.path.exists(file):
|
||||
return
|
||||
with open(file, 'rb') as f:
|
||||
return pickle.load(f)
|
||||
|
||||
|
||||
4
version
4
version
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"version": 3.37,
|
||||
"version": 3.42,
|
||||
"show_feature": true,
|
||||
"new_feature": "修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件 <-> 添加了OpenAI音频转文本总结插件 <-> 通过Slack添加对Claude的支持 <-> 提供复旦MOSS模型适配（启用需额外依赖） <-> 提供docker-compose方案兼容LLAMA盘古RWKV等模型的后端 <-> 新增Live2D装饰 <-> 完善对话历史的保存/载入/删除 <-> 保存对话功能"
|
||||
"new_feature": "完善本地Latex矫错和翻译功能 <-> 增加gpt-3.5-16k的支持 <-> 新增最强Arxiv论文翻译插件 <-> 修复gradio复制按钮BUG <-> 修复PDF翻译的BUG, 新增HTML中英双栏对照 <-> 添加了OpenAI图片生成插件 <-> 添加了OpenAI音频转文本总结插件 <-> 通过Slack添加对Claude的支持"
|
||||
}
|
||||
|
||||
在新工单中引用
屏蔽一个用户