个人助理

增加chatGLM int4配置支持 小显存也可以选择chatGLM

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

@@ -1,5 +1,5 @@
 # https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image for ChatGLM support
+name: build-with-chatglm
 
 on:
   push:

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

@@ -1,5 +1,5 @@
 # https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image for ChatGLM support
+name: build-with-jittorllms
 
 on:
   push:

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

@@ -1,5 +1,5 @@
 # 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
+name: build-with-latex
 
 on:
   push:

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

@@ -1,5 +1,5 @@
 # https://docs.github.com/en/actions/publishing-packages/publishing-docker-images#publishing-images-to-github-packages
-name: Create and publish a Docker image
+name: build-without-local-llms
 
 on:
   push:

.gitignore

@@ -2,14 +2,15 @@
 __pycache__/
 *.py[cod]
 *$py.class
+
 # C extensions
 *.so
+
 # Distribution / packaging
 .Python
 build/
 develop-eggs/
 dist/
-plugins/
 downloads/
 eggs/
 .eggs/
@@ -25,6 +26,7 @@ share/python-wheels/
 .installed.cfg
 *.egg
 MANIFEST
+
 # PyInstaller
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.
@@ -33,6 +35,7 @@ MANIFEST
 # Installer logs
 pip-log.txt
 pip-delete-this-directory.txt
+
 # Unit test / coverage reports
 htmlcov/
 .tox/
@@ -46,64 +49,91 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+
 # Translations
 *.mo
 *.pot
+github
+.github
+TEMP
+TRASH
+
 # Django stuff:
+*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
+
 # Flask stuff:
 instance/
 .webassets-cache
+
 # Scrapy stuff:
 .scrapy
+
 # Sphinx documentation
 docs/_build/
-site/
+
 # PyBuilder
 target/
+
 # Jupyter Notebook
 .ipynb_checkpoints
+
 # IPython
 profile_default/
 ipython_config.py
+
 # pyenv
 .python-version
+
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 #   install all needed dependencies.
 #Pipfile.lock
+
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow
 __pypackages__/
+
 # Celery stuff
 celerybeat-schedule
 celerybeat.pid
+
 # SageMath parsed files
 *.sage.py
+
 # Environments
-.direnv/
+.env
 .venv
 env/
-venv*/
+venv/
 ENV/
 env.bak/
+venv.bak/
+
 # Spyder project settings
 .spyderproject
 .spyproject
+
 # Rope project settings
 .ropeproject
+
 # mkdocs documentation
 /site
+
 # mypy
 .mypy_cache/
 .dmypy.json
 dmypy.json
+
 # Pyre type checker
 .pyre/
+
+.vscode
 .idea
+
 history
 ssr_conf
 config_private.py
@@ -115,12 +145,9 @@ cradle*
 debug*
 private*
 crazy_functions/test_project/pdf_and_word
-crazy_fun
-ctions/test_samples
 crazy_functions/test_samples
 request_llm/jittorllms
-users_data/*
-request_llm/moss
 multi-language
+request_llm/moss
 media
-__test.py
+flagged

Dockerfile

@@ -1,28 +1,34 @@
-# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型，请参考 docs/Dockerfile+ChatGLM
-# 如何构建: 先修改 `config.py`， 然后 docker build -t gpt-academic .
-# 如何运行: docker run --rm -it --net=host gpt-academic
+# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型或者latex运行依赖，请参考 docker-compose.yml
+# 如何构建: 先修改 `config.py`， 然后 `docker build -t gpt-academic . `
+# 如何运行(Linux下): `docker run --rm -it --net=host gpt-academic `
+# 如何运行(其他操作系统，选择任意一个固定端口50923): `docker run --rm -it -e WEB_PORT=50923 -p 50923:50923 gpt-academic `
 FROM python:3.11
 
+
+# 非必要步骤，更换pip源
 RUN echo '[global]' > /etc/pip.conf && \
     echo 'index-url = https://mirrors.aliyun.com/pypi/simple/' >> /etc/pip.conf && \
     echo 'trusted-host = mirrors.aliyun.com' >> /etc/pip.conf
 
 
+# 进入工作路径
 WORKDIR /gpt
 
 
-
-
-# 安装依赖
+# 安装大部分依赖，利用Docker缓存加速以后的构建
 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
+
+
+# 装载项目文件，安装剩余依赖
 COPY . .
 RUN pip3 install -r requirements.txt
 
-# 可选步骤，用于预热模块
+
+# 非必要步骤，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"]

README.md

@@ -1,31 +1,31 @@
 > **Note**
 >
-> 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**： 
+> 2023.7.8: Gradio, Pydantic依赖调整，已修改 `requirements.txt`。请及时**更新代码**，安装依赖时，请严格选择`requirements.txt`中**指定的版本**
 >
 > `pip install -r requirements.txt`
->
 
-# <img src="docs/logo.png" width="40" > GPT 学术优化 (GPT Academic)
 
-**如果喜欢这个项目，请给它一个Star；如果你发明了更好用的快捷键或函数插件，欢迎发pull requests**
+# <div align=center><img src="docs/logo.png" width="40"> GPT 学术优化 (GPT Academic)</div>
+
+**如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或函数插件，欢迎发pull requests！**
 
 If you like this project, please give it a Star. If you've come up with more useful academic shortcuts or functional plugins, feel free to open an issue or pull request. We also have a README in [English|](docs/README_EN.md)[日本語|](docs/README_JP.md)[한국어|](https://github.com/mldljyh/ko_gpt_academic)[Русский|](docs/README_RS.md)[Français](docs/README_FR.md) translated by this project itself.
 To translate this project to arbitary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
 
 > **Note**
 >
-> 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！
+> 1.请注意只有 **高亮(如红色)** 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/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。
+> 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM和Moss等等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。
 
 
  
 
 <div align="center">
 
-功能 | 描述
+功能（⭐= 近期新增功能） | 描述
 --- | ---
 一键润色 | 支持一键润色、一键查找论文语法错误
 一键中英互译 | 一键中英互译
@@ -41,14 +41,17 @@ Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [函数
 chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
 [PDF论文全文翻译功能](https://www.bilibili.com/video/BV1KT411x7Wn) | [函数插件] PDF论文提取题目&摘要+翻译全文（多线程）
 [Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [函数插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
+Latex论文一键校对 | [函数插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
 [谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [函数插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
-互联网信息聚合+GPT | [函数插件] 一键[让GPT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⭐
+互联网信息聚合+GPT | [函数插件] 一键[让GPT从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)回答问题，让信息永不过时
+⭐Arxiv论文精细翻译 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [函数插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
+⭐[实时语音对话输入](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [函数插件] 异步[监听音频](https://www.bilibili.com/video/BV1AV4y187Uy/)，自动断句，自动寻找回答时机
 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/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/)
+启动暗色[主题](https://github.com/binary-husky/gpt_academic/issues/173) | 在浏览器url后面添加```/?__theme=dark```可以切换dark主题
+[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)同时伺候的感觉一定会很不错吧？
+⭐ChatGLM2微调模型 | 支持加载ChatGLM2微调模型，提供ChatGLM2微调辅助插件
+更多LLM模型接入，支持[huggingface部署](https://huggingface.co/spaces/qingxu98/gpt-academic) | 加入Newbing接口(新必应)，引入清华[Jittorllms](https://github.com/Jittor/JittorLLMs)支持[LLaMA](https://github.com/facebookresearch/llama)和[盘古α](https://openi.org.cn/pangu/)
 更多新功能展示 (图像生成等) …… | 见本文档结尾处 ……
 
 </div>
@@ -85,13 +88,12 @@ chat分析报告生成 | [函数插件] 运行后自动生成总结汇报
 <img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
 </div>
 
----
 # Installation
-## 安装-方法1：直接运行 (Windows, Linux or MacOS) 
+### 安装方法I：直接运行 (Windows, Linux or MacOS) 
 
 1. 下载项目
 ```sh
-git clone https://github.com/binary-husky/gpt_academic.git
+git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
 cd gpt_academic
 ```
 
@@ -114,17 +116,17 @@ python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步
 ```
 
 
-<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>
+<details><summary>如果需要支持清华ChatGLM2/复旦MOSS作为后端，请点击展开此处</summary>
 <p>
 
-【可选步骤】如果需要支持清华ChatGLM/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
+【可选步骤】如果需要支持清华ChatGLM2/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
 ```sh
-# 【可选步骤I】支持清华ChatGLM。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
+# 【可选步骤I】支持清华ChatGLM2。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
 python -m pip install -r request_llm/requirements_chatglm.txt  
 
 # 【可选步骤II】支持复旦MOSS
 python -m pip install -r request_llm/requirements_moss.txt
-git clone https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 注意执行此行代码时，必须处于项目根路径
+git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llm/moss  # 注意执行此行代码时，必须处于项目根路径
 
 # 【可选步骤III】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
 AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "newbing", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
@@ -140,24 +142,27 @@ AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-
 python main.py
 ```
 
-## 安装-方法2：使用Docker
+### 安装方法II：使用Docker
 
 1. 仅ChatGPT（推荐大多数人选择，等价于docker-compose方案1）
+[![basic](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
+[![basiclatex](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
 
 ``` sh
-git clone https://github.com/binary-husky/gpt_academic.git  # 下载项目
+git clone --depth=1 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
 
-#（最后一步-选择1）在Linux环境下，用`--net=host`更方便快捷
+#（最后一步-Linux操作系统）用`--net=host`更方便快捷
 docker run --rm -it --net=host gpt-academic
-#（最后一步-选择2）在macOS/windows环境下，只能用-p选项将容器上的端口(例如50923)暴露给主机上的端口
+#（最后一步-MacOS/Windows操作系统）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）
+2. ChatGPT + ChatGLM2 + MOSS（需要熟悉Docker）
+[![chatglm](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)
 
 ``` sh
 # 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
@@ -165,13 +170,15 @@ docker-compose up
 ```
 
 3. ChatGPT + LLAMA + 盘古 + RWKV（需要熟悉Docker）
+[![jittorllms](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-jittorllms.yml/badge.svg?branch=master)](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-jittorllms.yml)
+
 ``` sh
 # 修改docker-compose.yml，保留方案3并删除其他方案。修改docker-compose.yml中方案3的配置，参考其中注释即可
 docker-compose up
 ```
 
 
-## 安装-方法3：其他部署姿势
+### 安装方法III：其他部署姿势
 1. 一键运行脚本。
 完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。
 脚本的贡献来源是[oobabooga](https://github.com/oobabooga/one-click-installers)。
@@ -194,11 +201,9 @@ docker-compose up
 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)
 
----
-# Advanced Usage
-## 自定义新的便捷按钮 / 自定义函数插件
 
-1. 自定义新的便捷按钮（学术快捷键）
+# Advanced Usage
+### I：自定义新的便捷按钮（学术快捷键）
 任意文本编辑器打开`core_functional.py`，添加条目如下，然后重启程序即可。（如果按钮已经添加成功并可见，那么前缀、后缀都支持热修改，无需重启程序即可生效。）
 例如
 ```
@@ -214,15 +219,15 @@ docker-compose up
 <img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
 </div>
 
-2. 自定义函数插件
+### II：自定义函数插件
 
 编写强大的函数插件来执行任何你想得到的和想不到的任务。
 本项目的插件编写、调试难度很低，只要您具备一定的python基础知识，就可以仿照我们提供的模板实现自己的插件功能。
 详情请参考[函数插件指南](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)。
 
----
+
 # Latest Update
-## 新功能动态
+### I：新功能动态
 
 1. 对话保存功能。在函数插件区调用 `保存当前的对话` 即可将当前对话保存为可读+可复原的html文件，
 另外在函数插件区（下拉菜单）调用 `载入对话历史存档` ，即可还原之前的会话。
@@ -283,8 +288,11 @@ 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
 
 
 
-## 版本:
+### II：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 3.46: 支持完全脱手操作的实时语音对话
+- version 3.45: 支持自定义ChatGLM2微调模型
+- version 3.44: 正式支持Azure，优化界面易用性
 - version 3.4: +arxiv论文翻译、latex论文批改功能
 - version 3.3: +互联网信息综合功能
 - version 3.2: 函数插件支持更多参数接口 (保存对话功能, 解读任意语言代码+同时询问任意的LLM组合)
@@ -305,13 +313,18 @@ gpt_academic开发者QQ群-2：610599535
     - 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
 
-## 参考与学习
+### III：主题
+可以通过修改`THEME`选项（config.py）变更主题
+1. `Chuanhu-Small-and-Beautiful` [网址](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
+
+
+### IV：参考与学习
 
 ```
 代码中参考了很多其他优秀项目中的设计，顺序不分先后：
 
-# 清华ChatGLM-6B:
-https://github.com/THUDM/ChatGLM-6B
+# 清华ChatGLM2-6B:
+https://github.com/THUDM/ChatGLM2-6B
 
 # 清华JittorLLMs:
 https://github.com/Jittor/JittorLLMs

__main__.py

@@ -1,486 +0,0 @@
-import os
-import gradio as gr
-from request_llm.bridge_all import predict
-from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_user_upload, \
-    get_conf, ArgsGeneralWrapper, DummyWith
-
-# 问询记录, python 版本建议3.9+（越新越好）
-import logging
-
-# 一些普通功能模块
-from core_functional import get_core_functions
-
-functional = get_core_functions()
-
-# 高级函数插件
-from crazy_functional import get_crazy_functions
-
-crazy_fns = get_crazy_functions()
-
-# 处理markdown文本格式的转变
-gr.Chatbot.postprocess = format_io
-
-# 做一些外观色彩上的调整
-from theme import adjust_theme, advanced_css, custom_css
-
-set_theme = adjust_theme()
-
-# 代理与自动更新
-from check_proxy import check_proxy, auto_update, warm_up_modules
-
-import func_box
-
-from check_proxy import get_current_version
-
-os.makedirs("gpt_log", exist_ok=True)
-try:
-    logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8")
-except:
-    logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO)
-print("所有问询记录将自动保存在本地目录./gpt_log/chat_secrets.log, 请注意自我隐私保护哦！")
-
-# 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, LAYOUT, API_KEY, AVAIL_LLM_MODELS, LOCAL_PORT= \
-    get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'LAYOUT',
-             'API_KEY', 'AVAIL_LLM_MODELS', 'LOCAL_PORT')
-
-proxy_info = check_proxy(proxies)
-# 如果WEB_PORT是-1, 则随机选取WEB端口
-PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
-if not AUTHENTICATION: AUTHENTICATION = None
-os.environ['no_proxy'] = '*'  # 避免代理网络产生意外污染
-
-
-class ChatBotFrame:
-
-    def __init__(self):
-        self.cancel_handles = []
-        self.initial_prompt = "You will play a professional to answer me according to my needs."
-        self.title_html = f"<h1 align=\"center\">Chatbot for KSO {get_current_version()}</h1>"
-        self.description = """代码开源和更新[地址🚀](https://github.com/binary-husky/chatgpt_academic)，感谢热情的[开发者们❤️](https://github.com/binary-husky/chatgpt_academic/graphs/contributors)"""
-
-
-class ChatBot(ChatBotFrame):
-
-    def __init__(self):
-        super().__init__()
-        self.__url = f'http://{func_box.ipaddr()}:{PORT}'
-        # self.__gr_url = gr.State(self.__url)
-
-    def draw_title(self):
-        # self.title = gr.HTML(self.title_html)
-        self.cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL, 'local': self.__url})
-    def draw_chatbot(self):
-        self.chatbot = gr.Chatbot(elem_id='main_chatbot', label=f"当前模型：{LLM_MODEL}")
-        self.chatbot.style()
-        self.history = gr.State([])
-        temp_draw = [gr.HTML() for i in range(7)]
-        with gr.Box(elem_id='chat_box'):
-            self.state_users = gr.HTML(value='', visible=False, elem_id='state_users')
-            with gr.Row():
-                self.sm_upload = gr.UploadButton(label='UPLOAD', file_count='multiple', elem_classes='sm_btn').style(size='sm', full_width=False)
-                self.sm_code_block = gr.Button(value='CODE', elem_classes='sm_btn').style(size='sm', full_width=False)
-                self.sm_upload_history = gr.Button("SPASE", variant="primary", elem_classes='sm_btn').style(size='sm', full_width=False)
-                self.md_dropdown = gr.Dropdown(choices=AVAIL_LLM_MODELS, value=LLM_MODEL,
-                                               show_label=False, interactive=True,
-                                               elem_classes='sm_select', elem_id='change-font-size').style(container=False)
-                gr.HTML(func_box.get_html("appearance_switcher.html").format(label=""), elem_id='user_input_tb', elem_classes="insert_block")
-
-            with gr.Row():
-                self.txt = gr.Textbox(show_label=False,  placeholder="Input question here.", elem_classes='chat_input').style(container=False)
-                self.input_copy = gr.State('')
-                self.submitBtn = gr.Button("", variant="primary", elem_classes='submit_btn').style(full_width=False)
-        with gr.Row():
-            self.status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行\n {proxy_info}", elem_id='debug_mes')
-
-    def signals_sm_btn(self):
-        self.sm_upload.upload(on_file_uploaded, [self.sm_upload, self.chatbot, self.txt], [self.chatbot, self.txt]).then(
-            fn=lambda: [gr.Tabs.update(selected='plug_tab'), gr.Column.update(visible=False)], inputs=None, outputs=[self.tabs_inputs, self.examples_column]
-        )
-        self.sm_code_block.click(fn=lambda x: x+'```\n\n```', inputs=[self.txt], outputs=[self.txt])
-        self.sm_upload_history.click(get_user_upload, [self.chatbot], outputs=[self.chatbot]).then(fn=lambda: gr.Column.update(visible=False), inputs=None, outputs=self.examples_column)
-        # self.sm_select_font.select(fn=lambda x: gr.HTML.update(value=f"{x}px"), inputs=[self.sm_select_font], outputs=[self.state_users])
-
-    def draw_examples(self):
-        with gr.Column(elem_id='examples_col') as self.examples_column:
-            gr.Markdown('# Get Started Quickly')
-            with gr.Row():
-                hide_components = gr.Textbox(visible=False)
-                gr.Button.update = func_box.update_btn
-                self.example = [['今天伦敦天气怎么样？', '对2021年以后的世界和事件了解有限', self.submitBtn.update(elem_id='highlight_update')],
-                                ['今夕何夕，明月何月？', '偶尔会产生不正确的信息', self.submitBtn.update(elem_id='highlight_update')],
-                                ['怎么才能把学校给炸了？', '经过训练，会拒绝不适当的请求', self.submitBtn.update(elem_id='highlight_update')]]
-                self.example_inputs = [self.txt, hide_components, self.submitBtn]
-                self.guidance_example = gr.Examples(examples=self.example, inputs=self.example_inputs, label='基础对话')
-                self.guidance_plugins = gr.Dataset(components=[gr.HTML(visible=False)], samples=[['...'] for i in range(4)], label='高级功能', type='index')
-                self.guidance_plugins_state = gr.State()
-                self.guidance_news = gr.Examples(examples=func_box.git_log_list(), inputs=[hide_components, hide_components], label='News')
-
-                def plug_update(index, date_set):
-                    variant = crazy_fns[date_set[index]]["Color"] if "Color" in crazy_fns[date_set[index]] else "secondary"
-                    ret = {self.switchy_bt:  self.switchy_bt.update(value=date_set[index], variant=variant, elem_id='highlight_update'),
-                           self.tabs_inputs: gr.Tabs.update(selected='plug_tab'),
-                           self.area_crazy_fn: self.area_crazy_fn.update(open=True)}
-                    fns_value = func_box.txt_converter_json(str(crazy_fns[date_set[index]].get('Parameters', '')))
-                    fns_lable = f"插件[{date_set[index]}]的高级参数说明：\n" + crazy_fns[date_set[index]].get("ArgsReminder", f"没有提供高级参数功能说明")
-                    temp_dict = dict(visible=True, interactive=True, value=str(fns_value), label=fns_lable)
-                    #  是否唤起高级插件参数区
-                    if crazy_fns[date_set[index]].get("AdvancedArgs", False):
-                        ret.update({self.plugin_advanced_arg: gr.update(**temp_dict)})
-                        ret.update({self.area_crazy_fn: self.area_crazy_fn.update(open=False)})
-                    else:
-                        ret.update({self.plugin_advanced_arg: gr.update(visible=False, label=f"插件[{date_set[index]}]不需要高级参数。")})
-                    return ret
-
-                self.guidance_plugins.select(fn=plug_update, inputs=[self.guidance_plugins, self.guidance_plugins_state],
-                                             outputs=[self.switchy_bt, self.plugin_advanced_arg, self.tabs_inputs,
-                                                      self.area_crazy_fn])
-
-    def __clear_input(self, inputs):
-        return '', inputs, self.examples_column.update(visible=False)
-
-    def draw_prompt(self):
-        with gr.Row():
-            self.pro_search_txt = gr.Textbox(show_label=False, placeholder="Enter the prompt you want.").style(
-                container=False)
-            self.pro_entry_btn = gr.Button("搜索", variant="primary").style(full_width=False, size="sm")
-        with gr.Row():
-            with gr.Accordion(label='Prompt usage frequency'):
-                self.pro_prompt_list = gr.Dataset(components=[gr.HTML(visible=False)], samples_per_page=10,
-                                                  label='Results',
-                                                  samples=[[". . ."] for i in range(20)], type='index')
-                self.pro_prompt_state = gr.State(self.pro_prompt_list)
-
-    def draw_temp_edit(self):
-        with gr.Box():
-            with gr.Row():
-                with gr.Column(scale=100):
-                    self.pro_results = gr.Chatbot(label='Prompt and result', elem_id='prompt_result').style()
-                with gr.Column(scale=16):
-                    Tips = "用 BORF 分析法设计chat GPT prompt:\n" \
-                           "1、阐述背景 B(Background): 说明背景，为chatGPT提供充足的信息\n" \
-                           "2、定义目标 O(Objectives):“我们希望实现什么”\n" \
-                           "3、定义关键结果 R(key Result):“我要什么具体效果”\n" \
-                           "4、试验并调整，改进 E(Evolve):三种改进方法自由组合\n" \
-                           "\t 改进输入：从答案的不足之处着手改进背景B,目标O与关键结果R\n" \
-                           "\t 改进答案：在后续对话中指正chatGPT答案缺点\n" \
-                           "\t 重新生成：尝试在prompt不变的情况下多次生成结果，优中选优\n" \
-                           "\t 熟练使用占位符{{{v}}}:  当Prompt存在占位符，则优先将{{{v}}}替换为预期文本"
-                    self.pro_edit_txt = gr.Textbox(show_label=False, info='Prompt编辑区', lines=14,
-                                                   placeholder=Tips).style(container=False)
-                    with gr.Row():
-                        self.pro_name_txt = gr.Textbox(show_label=False, placeholder='是否全复用prompt / prompt功能名', ).style(
-                            container=False)
-                        self.pro_new_btn = gr.Button("保存Prompt", variant="primary").style(size='sm').style()
-                    with gr.Row(elem_id='sm_btn'):
-                        self.pro_reuse_btn = gr.Button("复用Result", variant="secondary").style(size='sm').style(full_width=False)
-                        self.pro_clear_btn = gr.Button("重置Result", variant="stop").style(size='sm').style(full_width=False)
-
-
-    def signals_prompt_edit(self):
-        self.pro_clear_btn.click(fn=lambda: [], inputs=None, outputs=self.pro_results)
-        self.prompt_tab.select(fn=func_box.draw_results,
-                               inputs=[self.pro_search_txt, self.pro_prompt_state, self.pro_tf_slider,
-                                       self.pro_private_check],
-                               outputs=[self.pro_prompt_list, self.pro_prompt_state])
-        self.pro_search_txt.submit(fn=func_box.draw_results,
-                                 inputs=[self.pro_search_txt, self.pro_prompt_state, self.pro_tf_slider,
-                                         self.pro_private_check],
-                                 outputs=[self.pro_prompt_list, self.pro_prompt_state])
-        self.pro_entry_btn.click(fn=func_box.draw_results,
-                                 inputs=[self.pro_search_txt, self.pro_prompt_state, self.pro_tf_slider,
-                                         self.pro_private_check],
-                                 outputs=[self.pro_prompt_list, self.pro_prompt_state])
-        self.pro_prompt_list.click(fn=func_box.show_prompt_result,
-                                   inputs=[self.pro_prompt_list, self.pro_prompt_state, self.pro_results, self.pro_edit_txt, self.pro_name_txt],
-                                   outputs=[self.pro_results, self.pro_edit_txt, self.pro_name_txt])
-        self.pro_new_btn.click(fn=func_box.prompt_save,
-                               inputs=[self.pro_edit_txt, self.pro_name_txt, self.pro_fp_state],
-                               outputs=[self.pro_edit_txt, self.pro_name_txt, self.pro_private_check,
-                                        self.pro_func_prompt, self.pro_fp_state, self.tabs_chatbot])
-        self.pro_reuse_btn.click(
-            fn=func_box.reuse_chat,
-            inputs=[self.pro_results, self.chatbot, self.history, self.pro_name_txt, self.txt],
-            outputs=[self.chatbot, self.history, self.txt, self.tabs_chatbot, self.pro_name_txt, self.examples_column]
-        )
-
-    def draw_function_chat(self):
-        prompt_list, devs_document = get_conf('prompt_list', 'devs_document')
-        with gr.TabItem('Function', id='func_tab'):
-            with gr.Accordion("基础功能区", open=False) as self.area_basic_fn:
-                with gr.Row():
-                    for k in functional:
-                        variant = functional[k]["Color"] if "Color" in functional[k] else "secondary"
-                        functional[k]["Button"] = gr.Button(k, variant=variant)
-            with gr.Accordion("上传你的Prompt", open=False) as self.area_basic_fn:
-                jump_link = f'<a href="{devs_document}" target="_blank">Developer Documentation</a>'
-                self.pro_devs_link = gr.HTML(jump_link)
-                self.pro_upload_btn = gr.File(file_count='single', file_types=['.yaml', '.json'],
-                                              label=f'上传你的Prompt文件, 编写格式请遵循上述开发者文档', )
-            self.pro_private_check = gr.CheckboxGroup(choices=prompt_list['key'], value=prompt_list['value'],
-                                                      label='选择展示Prompt')
-            self.pro_func_prompt = gr.Dataset(components=[gr.HTML()], label="Prompt List", visible=False,
-                                              samples=[['...', ""] for i in range(20)], type='index',
-                                              samples_per_page=10)
-            self.pro_fp_state = gr.State(self.pro_func_prompt)
-
-    def signals_prompt_func(self):
-        self.pro_private_check.select(fn=func_box.prompt_reduce,
-                                      inputs=[self.pro_private_check, self.pro_fp_state],
-                                      outputs=[self.pro_func_prompt, self.pro_fp_state, self.pro_private_check])
-        self.tabs_code = gr.State(0)
-        self.pro_func_prompt.select(fn=func_box.prompt_input,
-                                    inputs=[self.txt, self.pro_edit_txt, self.pro_name_txt, self.pro_func_prompt, self.pro_fp_state, self.tabs_code],
-                                    outputs=[self.txt, self.pro_edit_txt, self.pro_name_txt])
-        self.pro_upload_btn.upload(fn=func_box.prompt_upload_refresh,
-                                   inputs=[self.pro_upload_btn, self.pro_prompt_state],
-                                   outputs=[self.pro_func_prompt, self.pro_prompt_state, self.pro_private_check])
-        self.chat_tab.select(fn=lambda: 0, inputs=None, outputs=self.tabs_code)
-        self.prompt_tab.select(fn=lambda: 1, inputs=None, outputs=self.tabs_code)
-
-    def draw_public_chat(self):
-        with gr.TabItem('Plugins', id='plug_tab'):
-            with gr.Accordion("上传本地文件可供高亮函数插件调用", open=False) as self.area_file_up:
-                self.file_upload = gr.Files(label="任何文件, 但推荐上传压缩文件(zip, tar)",
-                                            file_count="multiple")
-                self.file_upload.style()
-            with gr.Accordion("函数插件区", open=True) as self.area_crazy_fn:
-                with gr.Row():
-                    for k in crazy_fns:
-                        if not crazy_fns[k].get("AsButton", True): continue
-                        self.variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
-                        crazy_fns[k]["Button"] = gr.Button(k, variant=self.variant)
-                        crazy_fns[k]["Button"].style(size="sm")
-            with gr.Accordion("更多函数插件/高级用法", open=True, ):
-                dropdown_fn_list = []
-                for k in crazy_fns.keys():
-                    if not crazy_fns[k].get("AsButton", True):
-                        dropdown_fn_list.append(k)
-                    elif crazy_fns[k].get('AdvancedArgs', False):
-                        dropdown_fn_list.append(k)
-                self.dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", show_label=False, label="").style(
-                    container=False)
-                self.plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False,
-                                                 placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
-                self.switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary")
-
-    def draw_setting_chat(self):
-        switch_model = get_conf('switch_model')[0]
-        with gr.TabItem('Settings', id='sett_tab'):
-            self.top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01, interactive=True,
-                                   label="Top-p (nucleus sampling)", ).style(container=False)
-            self.temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True,
-                                         label="Temperature", ).style(container=False)
-            self.max_length_sl = gr.Slider(minimum=256, maximum=4096, value=4096, step=1, interactive=True,
-                                           label="MaxLength", ).style(container=False)
-            self.pro_tf_slider = gr.Slider(minimum=0.01, maximum=1.0, value=0.70, step=0.01, interactive=True,
-                                           label="Term Frequency系数").style(container=False)
-            self.models_box = gr.CheckboxGroup(choices=switch_model['key'], value=switch_model['value'], label="对话模式")
-            self.system_prompt = gr.Textbox(show_label=True, lines=2, placeholder=f"System Prompt",
-                                            label="System prompt", value=self.initial_prompt)
-            # temp = gr.Markdown(self.description)
-
-    def draw_goals_auto(self):
-        with gr.Row():
-            self.ai_name = gr.Textbox(show_label=False, placeholder="给Ai一个名字").style(container=False)
-        with gr.Row():
-            self.ai_role = gr.Textbox(lines=5, show_label=False, placeholder="请输入你的需求").style(
-                container=False)
-        with gr.Row():
-            self.ai_goal_list = gr.Dataframe(headers=['Goals'], interactive=True, row_count=4,
-                                             col_count=(1, 'fixed'), type='array')
-        with gr.Row():
-            self.ai_budget = gr.Number(show_label=False, value=0.0,
-                                       info="关于本次项目的预算，超过预算自动停止，默认无限").style(container=False)
-
-
-    def draw_next_auto(self):
-        with gr.Row():
-            self.text_continue = gr.Textbox(visible=False, show_label=False,
-                                            placeholder="请根据提示输入执行命令").style(container=False)
-        with gr.Row():
-            self.submit_start = gr.Button("Start", variant='primary')
-            self.submit_next = gr.Button("Next", visible=False, variant='primary')
-            self.submit_stop = gr.Button("Stop", variant="stop")
-            self.agent_obj = gr.State({'obj': None, "start": self.submit_start,
-                                       "next": self.submit_next, "text": self.text_continue})
-
-
-    def signals_input_setting(self):
-        # 注册input
-        self.input_combo = [self.cookies, self.max_length_sl, self.md_dropdown,
-                            self.input_copy, self.top_p, self.temperature, self.chatbot, self.history,
-                            self.system_prompt, self.models_box, self.plugin_advanced_arg]
-        self.output_combo = [self.cookies, self.chatbot, self.history, self.status]
-        self.predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=self.input_combo, outputs=self.output_combo)
-        self.clear_agrs = dict(fn=self.__clear_input, inputs=[self.txt], outputs=[self.txt, self.input_copy,
-                                                                                  self.examples_column])
-        # 提交按钮、重置按钮
-        self.cancel_handles.append(self.txt.submit(**self.clear_agrs).then(**self.predict_args))
-        self.cancel_handles.append(self.submitBtn.click(**self.clear_agrs).then(**self.predict_args))
-        # self.cpopyBtn.click(fn=func_box.copy_result, inputs=[self.history], outputs=[self.status])
-        self.resetBtn.click(lambda: ([], [], "已重置"), None, [self.chatbot, self.history, self.status])
-
-    def signals_function(self):
-        # 基础功能区的回调函数注册
-        for k in functional:
-            self.click_handle = functional[k]["Button"].click(**self.clear_agrs).then(fn=ArgsGeneralWrapper(predict),
-                                                              inputs=[*self.input_combo, gr.State(True), gr.State(k)],
-                                                              outputs=self.output_combo)
-            self.cancel_handles.append(self.click_handle)
-
-    def signals_public(self):
-        # 文件上传区，接收文件后与chatbot的互动
-        self.file_upload.upload(on_file_uploaded, [self.file_upload, self.chatbot, self.txt], [self.chatbot, self.txt])
-        # 函数插件-固定按钮区
-        for k in crazy_fns:
-            if not crazy_fns[k].get("AsButton", True): continue
-            self.click_handle = crazy_fns[k]["Button"].click(**self.clear_agrs).then(
-                ArgsGeneralWrapper(crazy_fns[k]["Function"]),
-                [*self.input_combo, gr.State(PORT), gr.State(crazy_fns[k].get('Parameters', False))],
-                self.output_combo)
-            self.click_handle.then(on_report_generated, [self.cookies, self.file_upload, self.chatbot],
-                                   [self.cookies, self.file_upload, self.chatbot])
-            # self.click_handle.then(fn=lambda x: '', inputs=[], outputs=self.txt)
-            self.cancel_handles.append(self.click_handle)
-
-        # 函数插件-下拉菜单与随变按钮的互动
-        def on_dropdown_changed(k):
-            # 按钮颜色随变
-            variant = crazy_fns[k]["Color"] if "Color" in crazy_fns[k] else "secondary"
-            ret = {self.switchy_bt: self.switchy_bt.update(value=k, variant=variant)}
-            # 参数取随变
-            fns_value = func_box.txt_converter_json(str(crazy_fns[k].get('Parameters', '')))
-            fns_lable = f"插件[{k}]的高级参数说明：\n" + crazy_fns[k].get("ArgsReminder", f"没有提供高级参数功能说明")
-            temp_dict = dict(visible=True, interactive=True, value=str(fns_value), label=fns_lable)
-            #  是否唤起高级插件参数区
-            if crazy_fns[k].get("AdvancedArgs", False):
-                ret.update({self.plugin_advanced_arg: gr.update(**temp_dict)})
-            else:
-                ret.update({self.plugin_advanced_arg: gr.update(visible=False, label=f"插件[{k}]不需要高级参数。")})
-            return ret
-
-        self.dropdown.select(on_dropdown_changed, [self.dropdown], [self.switchy_bt, self.plugin_advanced_arg])
-
-        # 随变按钮的回调函数注册
-        def route(k, ipaddr: gr.Request, *args, **kwargs):
-            if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
-            append = list(args)
-            append[-2] = func_box.txt_converter_json(append[-2])
-            append.insert(-1, ipaddr)
-            args = tuple(append)
-            yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(*args, **kwargs)
-
-        self.click_handle = self.switchy_bt.click(**self.clear_agrs).then(route, [self.switchy_bt, *self.input_combo, gr.State(PORT)], self.output_combo)
-        self.click_handle.then(on_report_generated, [self.cookies, self.file_upload, self.chatbot],
-                               [self.cookies, self.file_upload, self.chatbot])
-        self.cancel_handles.append(self.click_handle)
-        # 终止按钮的回调函数注册
-        self.stopBtn.click(fn=None, inputs=None, outputs=None, cancels=self.cancel_handles)
-
-        def on_md_dropdown_changed(k):
-            return {self.chatbot: gr.update(label="当前模型：" + k)}
-
-        self.md_dropdown.select(on_md_dropdown_changed, [self.md_dropdown], [self.chatbot])
-
-    def signals_auto_input(self):
-        self.auto_input_combo = [self.ai_name, self.ai_role, self.ai_goal_list, self.ai_budget,
-                                 self.cookies, self.chatbot, self.history,
-                                 self.agent_obj]
-        self.auto_output_combo = [self.cookies, self.chatbot, self.history, self.status,
-                                  self.agent_obj, self.submit_start, self.submit_next, self.text_continue]
-
-
-    # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
-    def auto_opentab_delay(self, is_open=False):
-        import threading, webbrowser, time
-
-        print(f"如果浏览器没有自动打开，请复制并转到以下URL：")
-        print(f"\t（亮色主题）: http://localhost:{PORT}")
-        print(f"\t（暗色主题）: {self.__url}/?__theme=dark")
-        if is_open:
-            def open():
-                time.sleep(2)  # 打开浏览器
-                webbrowser.open_new_tab(f"http://localhost:{PORT}/?__theme=dark")
-
-            threading.Thread(target=open, name="open-browser", daemon=True).start()
-            threading.Thread(target=auto_update, name="self-upgrade", daemon=True).start()
-        # threading.Thread(target=warm_up_modules, name="warm-up", daemon=True).start()
-
-
-    def main(self):
-
-        with gr.Blocks(title="Chatbot for KSO ", theme=set_theme, analytics_enabled=False, css=custom_css) as self.demo:
-            # 绘制页面title
-            self.draw_title()
-            # 绘制一个ROW，row会让底下的元素自动排成一行
-            with gr.Row().style(justify='between'):
-                # 绘制列1
-                with gr.Column(scale=44):
-                    with gr.Tabs() as self.tabs_copilot:
-                        # 绘制对话模组
-                        with gr.TabItem('Chat-Copilot'):
-                            with gr.Row():
-                                # self.cpopyBtn = gr.Button("复制回答", variant="secondary").style(size="sm")
-                                self.resetBtn = gr.Button("新建对话", variant="primary", elem_id='empty_btn').style(
-                                    size="sm")
-                                self.stopBtn = gr.Button("中止对话", variant="stop").style(size="sm")
-                            with gr.Tabs() as self.tabs_inputs:
-                                self.draw_function_chat()
-                                self.draw_public_chat()
-                                self.draw_setting_chat()
-
-                        # 绘制autogpt模组
-                        with gr.TabItem('Auto-GPT'):
-                            self.draw_next_auto()
-                            self.draw_goals_auto()
-                # 绘制列2
-                with gr.Column(scale=100):
-                    with gr.Tabs() as self.tabs_chatbot:
-                        with gr.TabItem('Chatbot', id='chatbot') as self.chat_tab:
-                            # self.draw_chatbot()
-                            pass
-                        with gr.TabItem('Prompt检索/编辑') as self.prompt_tab:
-                            self.draw_prompt()
-
-                with self.chat_tab:  # 使用 gr.State()对组件进行拷贝时，如果之前绘制了Markdown格式，会导致启动崩溃,所以将 markdown相关绘制放在最后
-                    self.draw_chatbot()
-                    self.draw_examples()
-                with self.prompt_tab:
-                    self.draw_temp_edit()
-            # 函数注册，需要在Blocks下进行
-            self.signals_sm_btn()
-            self.signals_input_setting()
-            self.signals_function()
-            self.signals_prompt_func()
-            self.signals_public()
-            self.signals_prompt_edit()
-            # self.signals_auto_input()
-            adv_plugins = gr.State([i for i in crazy_fns])
-            self.demo.load(fn=func_box.refresh_load_data, postprocess=False,
-                           inputs=[self.chatbot, self.history, self.pro_fp_state, adv_plugins],
-                           outputs=[self.pro_func_prompt, self.pro_fp_state, self.chatbot,  self.history, self.guidance_plugins, self.guidance_plugins_state])
-
-        # Start
-        self.auto_opentab_delay()
-        self.demo.queue(concurrency_count=CONCURRENT_COUNT).launch(server_name="0.0.0.0", server_port=PORT, auth=AUTHENTICATION,
-        blocked_paths=["config.py", "config_private.py", "docker-compose.yml", "Dockerfile"])
-
-
-def check_proxy_free():
-    proxy_state = func_box.Shell(f'lsof -i :{PORT}').read()[1].splitlines()
-    if proxy_state != ["", ""]:
-        print('Kill Old Server')
-        for i in proxy_state[1:]:
-            func_box.Shell(f'kill -9 {i.split()[1]}').read()
-        import time
-        time.sleep(5)
-
-if __name__ == '__main__':
-    # PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
-    PORT = LOCAL_PORT if WEB_PORT <= 0 else WEB_PORT
-    check_proxy_free()
-    ChatBot().main()
-    gr.close_all()
-    check_proxy_free()
-

check_proxy.py

@@ -11,7 +11,9 @@ def check_proxy(proxies):
             country = data['country_name']
             result = f"代理配置 {proxies_https}, 代理所在地：{country}"
         elif 'error' in data:
-            result = f"代理配置 {proxies_https}, 代理所在地：未知"
+            result = f"代理配置 {proxies_https}, 代理所在地：未知，IP查询频率受限"
+        else:
+            result = f"代理配置 {proxies_https}, 代理数据解析失败：{data}"
         print(result)
         return result
     except:
@@ -115,7 +117,7 @@ def auto_update(raise_error=False):
         with open('./version', 'r', encoding='utf8') as f:
             current_version = f.read()
             current_version = json.loads(current_version)['version']
-        if (remote_version - current_version) >= 0.01:
+        if (remote_version - current_version) >= 0.01-1e-5:
             from colorful import print亮黄
             print亮黄(
                 f'\n新版本可用。新版本:{remote_version}，当前版本:{current_version}。{new_feature}')
@@ -137,7 +139,7 @@ def auto_update(raise_error=False):
         else:
             return
     except:
-        msg = '自动更新程序：已禁用'
+        msg = '自动更新程序：已禁用。建议排查：代理网络配置。'
         if raise_error:
             from toolbox import trimmed_format_exc
             msg += trimmed_format_exc()

config.py

@@ -1,36 +1,27 @@
-# [step 1]>> 例如： API_KEY = "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" （此key无效）
-API_KEY = "sk-此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
+"""
+    以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
+    读取优先级：环境变量 > config_private.py > config.py
+    --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
+    All the following configurations also support using environment variables to override, 
+    and the environment variable configuration format can be seen in docker-compose.yml. 
+    Configuration reading priority: environment variable > config_private.py > config.py
+"""
 
+# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
+API_KEY = "此处填API密钥"    # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
 
 
-prompt_list = {'key': ['所有人', '个人'], 'value': []}
-
-switch_model = {'key': ['input加密', '隐私模式'], 'value': ['input加密']}
-
-private_key = 'uhA51pHtjisfjij'
-
-import func_box
-import os
-devs_document = "/file="+os.path.join(func_box.base_path, 'README.md')
-
-#增加关于AZURE的配置信息， 可以在AZURE网页中找到
-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"
-
 # [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
-
-LOCAL_PORT = 7891
 if USE_PROXY:
-    # 填写格式是 [协议]://  [地址] :[端口]，填写之前不要忘记把USE_PROXY改成True，如果直接在海外服务器部署，此处不修改
-    # 例如    "socks5h://localhost:11284"
-    # [协议] 常见协议无非socks5h/http; 例如 v2**y 和 ss* 的默认本地协议是socks5h; 而cl**h 的默认本地协议是http
-    # [地址] 懂的都懂，不懂就填localhost或者127.0.0.1肯定错不了（localhost意思是代理软件安装在本机上）
-    # [端口] 在代理软件的设置里找。虽然不同的代理软件界面不一样，但端口号都应该在最显眼的位置上
-
-    # 代理网络的地址，打开你的*学*网软件查看代理的协议(socks5/http)、地址(localhost)和端口(11284)
+    """
+    填写格式是 [协议]://  [地址] :[端口]，填写之前不要忘记把USE_PROXY改成True，如果直接在海外服务器部署，此处不修改
+            <配置教程&视频教程> https://github.com/binary-husky/gpt_academic/issues/1>
+    [协议] 常见协议无非socks5h/http; 例如 v2**y 和 ss* 的默认本地协议是socks5h; 而cl**h 的默认本地协议是http
+    [地址] 懂的都懂，不懂就填localhost或者127.0.0.1肯定错不了（localhost意思是代理软件安装在本机上）
+    [端口] 在代理软件的设置里找。虽然不同的代理软件界面不一样，但端口号都应该在最显眼的位置上
+    """
+    # 代理网络的地址，打开你的*学*网软件查看代理的协议(socks5h / http)、地址(localhost)和端口(11284)
     proxies = {
         #          [协议]://  [地址]  :[端口]
         "http":  "socks5h://localhost:11284",  # 再例如  "http":  "http://127.0.0.1:7890",
@@ -39,78 +30,87 @@ if USE_PROXY:
 else:
     proxies = None
 
-# [step 3]>> 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
-# 一言以蔽之：免费用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
+# ------------------------------------ 以下配置可以优化体验, 但大部分场合下并不需要修改 ------------------------------------
+
+# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
+# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"} 
+# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions"}
+API_URL_REDIRECT = {}
+
+
+# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
+# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
 DEFAULT_WORKER_NUM = 3
 
 
-# [step 3]>> 以下配置可以优化体验，但大部分场合下并不需要修改  # 废弃了，移步到theme.py 的 #main_chatbot中修改
 # 对话窗的高度
 CHATBOT_HEIGHT = 1115
 
-# 主题
-THEME = "Default"
 
 # 代码高亮
 CODE_HIGHLIGHT = True
 
+
 # 窗口布局
 LAYOUT = "LEFT-RIGHT"   # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
-DARK_MODE = True  # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
+DARK_MODE = True        # 暗色模式 / 亮色模式
+
 
 # 发送请求到OpenAI后，等待多久判定为超时
 TIMEOUT_SECONDS = 30
 
+
 # 网页的端口, -1代表随机端口
 WEB_PORT = -1
 
+
 # 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
 MAX_RETRY = 2
 
-# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 同时它必须被包含在AVAIL_LLM_MODELS切换列表中 )
-LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
 
-AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt35", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "newbing-free", "stack-claude"]
-# P.S. 其他可用的模型还包括 ["newbing-free", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+# 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
+LLM_MODEL = "gpt-3.5-turbo" # 可选 ↓↓↓
+AVAIL_LLM_MODELS = ["gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss", "newbing", "stack-claude"]
+# P.S. 其他可用的模型还包括 ["gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "claude-1-100k", "claude-2", "internlm", "jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
+
+
+# ChatGLM(2) Finetune Model Path （如果使用ChatGLM2微调模型，需要把"chatglmft"加入AVAIL_LLM_MODELS中）
+ChatGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
+
 
 # 本地LLM模型如ChatGLM的执行方式 CPU/GPU
 LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
+LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
 
-# OpenAI的API_URL
-API_URL = "https://api.openai.com/v1/chat/completions"
-PROXY_API_URL = '' # 你的网关应用
 
 # 设置gradio的并行线程数（不需要修改）
 CONCURRENT_COUNT = 100
 
+
 # 是否在提交时自动清空输入框
 AUTO_CLEAR_TXT = False
 
+
+# 色彩主体，可选 ["Default", "Chuanhu-Small-and-Beautiful"]
+THEME = "Default"
+
+
 # 加一个live2d装饰
 ADD_WAIFU = False
 
-# 川虎JS
-ADD_CHUANHU = True
 
 # 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
 # [("username", "password"), ("username2", "password2"), ...]
 AUTHENTICATION = []
 
-# 重新URL重新定向，实现更换API_URL的作用（常规情况下，不要修改!!）
-# （高危设置！通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
-# 格式 {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"} 
-# 例如 API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://ai.open.com/api/conversation"}
-API_URL_REDIRECT = {}
 
 # 如果需要在二级路径下运行（常规情况下，不要修改!!）（需要配合修改main.py才能生效!）
 CUSTOM_PATH = "/"
 
-# 如果需要使用newbing，把newbing的长长的cookie放到这里
-NEWBING_STYLE = "creative"  # ["creative", "balanced", "precise"]
-# 从现在起，如果您调用"newbing-free"模型，则无需填写NEWBING_COOKIES
-NEWBING_COOKIES = """
-your bing cookies here
-"""
+
+# 极少数情况下，openai的官方KEY需要伴随组织编码（格式如org-xxxxxxxxxxxxxxxxxxxxxxxx）使用
+API_ORG = ""
+
 
 # 如果需要使用Slack Claude，使用教程详情见 request_llm/README.md
 SLACK_CLAUDE_BOT_ID = ''   
@@ -118,7 +118,27 @@ 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"
+AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/"
+AZURE_API_KEY = "填入azure openai api的密钥"    # 建议直接在API_KEY处填写，该选项即将被弃用
+AZURE_ENGINE = "填入你亲手写的部署名"            # 读 docs\use_azure.md
+
+
+# 使用Newbing
+NEWBING_STYLE = "creative"  # ["creative", "balanced", "precise"]
+NEWBING_COOKIES = """
+put your new bing cookies here
+"""
+
+
+# 阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
+ENABLE_AUDIO = False
+ALIYUN_TOKEN=""    # 例如 f37f30e0f9934c34a992f6f64f7eba4f
+ALIYUN_APPKEY=""   # 例如 RoPlZrM88DnAFkZK
+
+
+# Claude API KEY
+ANTHROPIC_API_KEY = ""
+
+
+# 自定义API KEY格式
+CUSTOM_API_KEY_PATTERN = ""

core_functional.py

@@ -61,7 +61,7 @@ def get_core_functions():
         },
         "找图片": {
             "Prefix":   r"我需要你找一张网络图片。使用Unsplash API(https://source.unsplash.com/960x640/?<英语关键词>)获取图片URL，" +
-                        r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n",
+                        r"然后请使用Markdown格式封装，并且不要有反斜线，不要用代码块。现在，请按以下描述给我发送图片：" + "\n\n",
             "Suffix":   r"",
             "Visible": False,
         },
@@ -76,11 +76,3 @@ def get_core_functions():
             "Suffix":   r"",
         }
     }
-
-
-def get_guidance():
-    pass
-
-
-def get_guidance():
-    pass

crazy_functional.py

@@ -20,28 +20,19 @@ def get_crazy_functions():
     from crazy_functions.解析项目源代码 import 解析一个Lua项目
     from crazy_functions.解析项目源代码 import 解析一个CSharp项目
     from crazy_functions.总结word文档 import 总结word文档
-    from crazy_functions.辅助回答 import 猜你想问
     from crazy_functions.解析JupyterNotebook import 解析ipynb文件
     from crazy_functions.对话历史存档 import 对话历史存档
     from crazy_functions.对话历史存档 import 载入对话历史存档
     from crazy_functions.对话历史存档 import 删除所有本地对话历史记录
+    
     from crazy_functions.批量Markdown翻译 import Markdown英译中
     function_plugins = {
-        "猜你想问": {
-            "Function": HotReload(猜你想问)
-        },
         "解析整个Python项目": {
-            "Color": "primary",    # 按钮颜色
-            "AsButton": False,
+            "Color": "stop",    # 按钮颜色
             "Function": HotReload(解析一个Python项目)
         },
-
-        "保存当前的对话": {
-            "AsButton": True,
-            "Function": HotReload(对话历史存档)
-        },
         "载入对话历史存档（先上传存档或输入路径）": {
-            "Color": "primary",
+            "Color": "stop",
             "AsButton":False,
             "Function": HotReload(载入对话历史存档)
         },
@@ -49,78 +40,77 @@ def get_crazy_functions():
             "AsButton":False,
             "Function": HotReload(删除所有本地对话历史记录)
         },
-
         "[测试功能] 解析Jupyter Notebook文件": {
-            "Color": "primary",
+            "Color": "stop",
             "AsButton":False,
             "Function": HotReload(解析ipynb文件),
             "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
             "ArgsReminder": "若输入0，则不解析notebook中的Markdown块", # 高级参数输入区的显示提示
         },
         "批量总结Word文档": {
-            "AsButton": False,
-            "Color": "primary",
+            "Color": "stop",
             "Function": HotReload(总结word文档)
         },
         "解析整个C++项目头文件": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个C项目的头文件)
         },
         "解析整个C++项目（.cpp/.hpp/.c/.h）": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个C项目)
         },
         "解析整个Go项目": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个Golang项目)
         },
         "解析整个Rust项目": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个Rust项目)
         },
         "解析整个Java项目": {
-            "Color": "primary",  # 按钮颜色
+            "Color": "stop",  # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个Java项目)
         },
         "解析整个前端项目（js,ts,css等）": {
-            "Color": "primary",  # 按钮颜色
+            "Color": "stop",  # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个前端项目)
         },
         "解析整个Lua项目": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个Lua项目)
         },
         "解析整个CSharp项目": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(解析一个CSharp项目)
         },
         "读Tex论文写摘要": {
-            "Color": "primary",    # 按钮颜色
-            "AsButton": False,  # 加入下拉菜单中
+            "Color": "stop",    # 按钮颜色
             "Function": HotReload(读文章写摘要)
         },
         "Markdown/Readme英译中": {
             # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "primary",
-            "AsButton": False,
+            "Color": "stop",
             "Function": HotReload(Markdown英译中)
         },
         "批量生成函数注释": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(批量生成函数注释)
         },
+        "保存当前的对话": {
+            "Function": HotReload(对话历史存档)
+        },
         "[多线程Demo] 解析此项目本身（源码自译解）": {
-            "Function": HotReload(解析项目本身),
             "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
@@ -129,8 +119,7 @@ def get_crazy_functions():
         # },
         "[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),
-            "AsButton": False,
+            "Function": HotReload(高阶功能模板函数)
         },
 
     }
@@ -149,69 +138,69 @@ def get_crazy_functions():
 
     function_plugins.update({
         "批量翻译PDF文档（多线程）": {
-            "Color": "primary",
-            "AsButton": False,  # 加入下拉菜单中
+            "Color": "stop",
+            "AsButton": True,  # 加入下拉菜单中
             "Function": HotReload(批量翻译PDF文档)
         },
         "询问多个GPT模型": {
-            "Color": "primary",    # 按钮颜色
+            "Color": "stop",    # 按钮颜色
             "Function": HotReload(同时问询)
         },
         "[测试功能] 批量总结PDF文档": {
-            "Color": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
             "Function": HotReload(批量总结PDF文档)
         },
         # "[测试功能] 批量总结PDF文档pdfminer": {
-        #     "Color": "primary",
+        #     "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": "primary",
+            "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": "primary",
-            "AsButton": True,  # 加入下拉菜单中
+            "Color": "stop",
+            "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(理解PDF文档内容标准文件输入)
         },
         "英文Latex项目全文润色（输入路径或上传压缩包）": {
             # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(Latex英文润色)
         },
         "英文Latex项目全文纠错（输入路径或上传压缩包）": {
             # 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": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(Latex英文纠错)
         },
         "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": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(Latex中文润色)
         },
         "Latex项目全文中译英（输入路径或上传压缩包）": {
             # 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": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(Latex中译英)
         },
         "Latex项目全文英译中（输入路径或上传压缩包）": {
             # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(Latex英译中)
         },
         "批量Markdown中译英（输入路径或上传压缩包）": {
             # HotReload 的意思是热更新，修改函数插件代码后，不需要重启程序，代码直接生效
-            "Color": "primary",
+            "Color": "stop",
             "AsButton": False,  # 加入下拉菜单中
             "Function": HotReload(Markdown中译英)
         },
@@ -221,11 +210,12 @@ 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
+
     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）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,  # 加入下拉菜单中
                 "Function": HotReload(下载arxiv论文并翻译摘要)
             }
@@ -237,7 +227,7 @@ def get_crazy_functions():
         from crazy_functions.联网的ChatGPT import 连接网络回答问题
         function_plugins.update({
             "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,  # 加入下拉菜单中
                 "Function": HotReload(连接网络回答问题)
             }
@@ -245,7 +235,7 @@ def get_crazy_functions():
         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": "primary",
+                "Color": "stop",
                 "AsButton": False,  # 加入下拉菜单中
                 "Function": HotReload(连接bing搜索回答问题)
             }
@@ -257,7 +247,7 @@ def get_crazy_functions():
         from crazy_functions.解析项目源代码 import 解析任意code项目
         function_plugins.update({
             "解析项目源代码（手动指定和筛选源代码文件类型）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
                 "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
@@ -271,7 +261,7 @@ def get_crazy_functions():
         from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
         function_plugins.update({
             "询问多个GPT模型（手动指定询问哪些模型）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
                 "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
@@ -285,7 +275,7 @@ def get_crazy_functions():
         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）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
                 "ArgsReminder": "在这里输入分辨率, 如256x256（默认）", # 高级参数输入区的显示提示
@@ -299,7 +289,7 @@ def get_crazy_functions():
         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）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
                 "ArgsReminder": "调用openai api 使用whisper-1模型, 目前支持的格式:mp4, m4a, wav, mpga, mpeg, mp3。此处可以输入解析提示，例如：解析为简体中文（默认）。",
@@ -309,51 +299,11 @@ def get_crazy_functions():
     except:
         print('Load function plugin failed')
 
-    from crazy_functions.解析项目源代码 import 解析任意code项目
-    function_plugins.update({
-        "解析项目源代码（手动指定和筛选源代码文件类型）": {
-            "Color": "primary",
-            "AsButton": False,
-            "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-            "ArgsReminder": "输入时用逗号隔开, *代表通配符, 加了^代表不匹配; 不输入代表全部匹配。例如: \"*.c, ^*.cpp, config.toml, ^*.toml\"", # 高级参数输入区的显示提示
-            "Function": HotReload(解析任意code项目)
-        },
-    })
-    from crazy_functions.询问多个大语言模型 import 同时问询_指定模型
-    function_plugins.update({
-        "询问多个GPT模型（手动指定询问哪些模型）": {
-            "Color": "primary",
-            "AsButton": False,
-            "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-            "ArgsReminder": "支持任意数量的llm接口，用&符号分隔。例如chatglm&gpt-3.5-turbo&api2d-gpt-4", # 高级参数输入区的显示提示
-            "Function": HotReload(同时问询_指定模型)
-        },
-    })
-    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）": {
-            "Color": "primary",
-            "AsButton": True,
-            "AdvancedArgs": True, # 调用时，唤起高级参数输入区（默认False）
-            "ArgsReminder": "在这里输入分辨率, 如'256x256'（默认）, '512x512', '1024x1024'", # 高级参数输入区的显示提示
-            "Function": HotReload(图片生成)
-        },
-    })
-    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）": {
-            "Color": "primary",
-            "AsButton": False,
-            "AdvancedArgs": True,
-            "ArgsReminder": "调用openai api 使用whisper-1模型, 目前支持的格式:mp4, m4a, wav, mpga, mpeg, mp3。此处可以输入解析提示，例如：解析为简体中文（默认）。",
-            "Function": HotReload(总结音视频)
-        }
-    })
     try:
         from crazy_functions.数学动画生成manim import 动画生成
         function_plugins.update({
             "数学动画生成（Manim）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "Function": HotReload(动画生成)
             }
@@ -365,7 +315,7 @@ def get_crazy_functions():
         from crazy_functions.批量Markdown翻译 import Markdown翻译指定语言
         function_plugins.update({
             "Markdown翻译（手动指定语言）": {
-                "Color": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
                 "ArgsReminder": "请输入要翻译成哪种语言，默认为Chinese。",
@@ -379,7 +329,7 @@ def get_crazy_functions():
         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": "primary",
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
                 "ArgsReminder": "待注入的知识库名称id, 默认为default",
@@ -393,7 +343,7 @@ def get_crazy_functions():
         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": "primary",
+                "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",
@@ -403,11 +353,37 @@ def get_crazy_functions():
     except:
         print('Load function plugin failed')
         
+    try:
+        from crazy_functions.交互功能函数模板 import 交互功能模板函数
+        function_plugins.update({
+            "交互功能模板函数": {
+                "Color": "stop",
+                "AsButton": False,
+                "Function": HotReload(交互功能模板函数)
+            }
+        })
+    except:
+        print('Load function plugin failed')
+
+    # try:
+    #     from crazy_functions.chatglm微调工具 import 微调数据集生成
+    #     function_plugins.update({
+    #         "黑盒模型学习: 微调数据集生成 (先上传数据集)": {
+    #             "Color": "stop",
+    #             "AsButton": False,
+    #             "AdvancedArgs": True,
+    #             "ArgsReminder": "针对数据集输入（如 绿帽子*深蓝色衬衫*黑色运动裤）给出指令，例如您可以将以下命令复制到下方: --llm_to_learn=azure-gpt-3.5 --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、过去经历进行描写。要求：100字以内，用第二人称。' --system_prompt=''",
+    #             "Function": HotReload(微调数据集生成)
+    #         }
+    #     })
+    # except:
+    #     print('Load function plugin failed')
+
     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": "primary",
+                "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）。",
@@ -416,8 +392,8 @@ def get_crazy_functions():
         })
         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": "primary",
+            "Arixv论文精细翻译（输入arxivID）[需Latex]": {
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
                 "ArgsReminder": 
@@ -427,8 +403,8 @@ def get_crazy_functions():
             }
         })
         function_plugins.update({
-            "本地论文翻译（上传Latex压缩包）[需Latex]": {
-                "Color": "primary",
+            "本地Latex论文精细翻译（上传Latex项目）[需Latex]": {
+                "Color": "stop",
                 "AsButton": False,
                 "AdvancedArgs": True,
                 "ArgsReminder": 
@@ -440,11 +416,27 @@ def get_crazy_functions():
     except:
         print('Load function plugin failed')
 
+
+    try:
+        from toolbox import get_conf
+        ENABLE_AUDIO, = get_conf('ENABLE_AUDIO')
+        if ENABLE_AUDIO:
+            from crazy_functions.语音助手 import 语音助手
+            function_plugins.update({
+                "实时音频采集": {
+                    "Color": "stop",
+                    "AsButton": True,
+                    "Function": HotReload(语音助手)
+                }
+            })
+    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": "primary",
+    #             "Color": "stop",
     #             "AsButton": False,
     #             # "AdvancedArgs": True,
     #             # "ArgsReminder": "",
@@ -454,5 +446,4 @@ def get_crazy_functions():
     # except:
     #     print('Load function plugin failed')
 
-    ###################### 第n组插件 ###########################
     return function_plugins

crazy_functions/Langchain知识库.py

@@ -30,7 +30,7 @@ def 知识库问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
         )
         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'])
+        try_install_deps(['zh_langchain==0.2.1', 'pypinyin'])
     
     # < --------------------读取参数--------------- >
     if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")

crazy_functions/Latex输出PDF结果.py

@@ -157,7 +157,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
     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
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
     except Exception as e:
         chatbot.append([ f"解析项目: {txt}",
             f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])
@@ -234,7 +234,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
     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
+        from .latex_fns.latex_actions import Latex精细分解与转化, 编译Latex
     except Exception as e:
         chatbot.append([ f"解析项目: {txt}",
             f"尝试执行Latex指令失败。Latex没有安装, 或者不在环境变量PATH中。安装方法https://tug.org/texlive/。报错信息\n\n```\n\n{trimmed_format_exc()}\n\n```\n\n"])

crazy_functions/chatglm微调工具.py

@@ -0,0 +1,141 @@
+from toolbox import CatchException, update_ui, promote_file_to_downloadzone
+from .crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+import datetime, json
+
+def fetch_items(list_of_items, batch_size):
+    for i in range(0, len(list_of_items), batch_size):
+        yield list_of_items[i:i + batch_size]
+
+def string_to_options(arguments):
+    import argparse
+    import shlex
+
+    # Create an argparse.ArgumentParser instance
+    parser = argparse.ArgumentParser()
+
+    # Add command-line arguments
+    parser.add_argument("--llm_to_learn", type=str, help="LLM model to learn", default="gpt-3.5-turbo")
+    parser.add_argument("--prompt_prefix", type=str, help="Prompt prefix", default='')
+    parser.add_argument("--system_prompt", type=str, help="System prompt", default='')
+    parser.add_argument("--batch", type=int, help="System prompt", default=50)
+    parser.add_argument("--pre_seq_len", type=int, help="pre_seq_len", default=50)
+    parser.add_argument("--learning_rate", type=float, help="learning_rate", default=2e-2)
+    parser.add_argument("--num_gpus", type=int, help="num_gpus", default=1)
+    parser.add_argument("--json_dataset", type=str, help="json_dataset", default="")
+    parser.add_argument("--ptuning_directory", type=str, help="ptuning_directory", default="")
+
+
+
+    # Parse the arguments
+    args = parser.parse_args(shlex.split(arguments))
+
+    return args
+
+@CatchException
+def 微调数据集生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, 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
+    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] 微调数据集生成"))
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    args = plugin_kwargs.get("advanced_arg", None)
+    if args is None: 
+        chatbot.append(("没给定指令", "退出"))
+        yield from update_ui(chatbot=chatbot, history=history); return
+    else:
+        arguments = string_to_options(arguments=args)
+
+    dat = []
+    with open(txt, 'r', encoding='utf8') as f:
+        for line in f.readlines():
+            json_dat = json.loads(line)
+            dat.append(json_dat["content"])
+
+    llm_kwargs['llm_model'] = arguments.llm_to_learn
+    for batch in fetch_items(dat, arguments.batch):
+        res = yield from request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
+            inputs_array=[f"{arguments.prompt_prefix}\n\n{b}" for b in (batch)],
+            inputs_show_user_array=[f"Show Nothing" for _ in (batch)],
+            llm_kwargs=llm_kwargs,
+            chatbot=chatbot,
+            history_array=[[] for _ in (batch)],
+            sys_prompt_array=[arguments.system_prompt for _ in (batch)],
+            max_workers=10  # OpenAI所允许的最大并行过载
+        )
+    
+        with open(txt+'.generated.json', 'a+', encoding='utf8') as f:
+            for b, r in zip(batch, res[1::2]):
+                f.write(json.dumps({"content":b, "summary":r}, ensure_ascii=False)+'\n')
+
+    promote_file_to_downloadzone(txt+'.generated.json', rename_file='generated.json', chatbot=chatbot)
+    return
+
+
+
+@CatchException
+def 启动微调(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, 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
+    chatbot         聊天显示框的句柄，用于显示给用户
+    history         聊天历史，前情提要
+    system_prompt   给gpt的静默提醒
+    web_port        当前软件运行的端口号
+    """
+    import subprocess
+    history = []    # 清空历史，以免输入溢出
+    chatbot.append(("这是什么功能？", "[Local Message] 微调数据集生成"))
+    if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
+    args = plugin_kwargs.get("advanced_arg", None)
+    if args is None: 
+        chatbot.append(("没给定指令", "退出"))
+        yield from update_ui(chatbot=chatbot, history=history); return
+    else:
+        arguments = string_to_options(arguments=args)
+      
+
+
+    pre_seq_len = arguments.pre_seq_len             # 128
+    learning_rate = arguments.learning_rate                               # 2e-2
+    num_gpus = arguments.num_gpus                   # 1
+    json_dataset = arguments.json_dataset                 # 't_code.json'
+    ptuning_directory = arguments.ptuning_directory       # '/home/hmp/ChatGLM2-6B/ptuning'
+
+    command = f"torchrun --standalone --nnodes=1 --nproc-per-node={num_gpus} main.py \
+        --do_train \
+        --train_file AdvertiseGen/{json_dataset} \
+        --validation_file AdvertiseGen/{json_dataset} \
+        --preprocessing_num_workers 20 \
+        --prompt_column content \
+        --response_column summary \
+        --overwrite_cache \
+        --model_name_or_path THUDM/chatglm2-6b \
+        --output_dir output/clothgen-chatglm2-6b-pt-{pre_seq_len}-{learning_rate} \
+        --overwrite_output_dir \
+        --max_source_length 256 \
+        --max_target_length 256 \
+        --per_device_train_batch_size 1 \
+        --per_device_eval_batch_size 1 \
+        --gradient_accumulation_steps 16 \
+        --predict_with_generate \
+        --max_steps 100 \
+        --logging_steps 10 \
+        --save_steps 20 \
+        --learning_rate {learning_rate} \
+        --pre_seq_len {pre_seq_len} \
+        --quantization_bit 4"
+
+    process = subprocess.Popen(command, shell=True, cwd=ptuning_directory)
+    try:
+        process.communicate(timeout=3600*24)
+    except subprocess.TimeoutExpired:
+        process.kill()
+    return

crazy_functions/crazy_functions_test.py

@@ -195,9 +195,12 @@ def test_Latex():
     # 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"
-    txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
-    
-
+    # txt = r"2306.17157" # 这个paper有个input命令文件名大小写错误！
+    # txt = "https://arxiv.org/abs/2205.14135"
+    # txt = r"C:\Users\fuqingxu\arxiv_cache\2205.14135\workfolder"
+    # txt = r"C:\Users\fuqingxu\arxiv_cache\2205.14135\workfolder"
+    txt = r"2210.03629"
+    txt = r"2307.04964"
     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)
 
@@ -211,8 +214,22 @@ def test_Latex():
     # # 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)
 
+def test_chatglm_finetune():
+    from crazy_functions.chatglm微调工具 import 微调数据集生成, 启动微调
+    txt = 'build/dev.json'
+    plugin_kwargs = {"advanced_arg":"--llm_to_learn=gpt-3.5-turbo --prompt_prefix='根据下面的服装类型提示，想象一个穿着者，对这个人外貌、身处的环境、内心世界、人设进行描写。要求：100字以内，用第二人称。' --system_prompt=''" }
+
+    # for cookies, cb, hist, msg in (微调数据集生成)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    #     cli_printer.print(cb)
+
+    plugin_kwargs = {"advanced_arg":
+    "      --pre_seq_len=128 --learning_rate=2e-2 --num_gpus=1 --json_dataset='t_code.json' --ptuning_directory='/home/hmp/ChatGLM2-6B/ptuning'     " }
+
+    for cookies, cb, hist, msg in (启动微调)(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+        cli_printer.print(cb)
 
 
+if __name__ == "__main__":
     # test_解析一个Python项目()
     # test_Latex英文润色()
     # test_Markdown中译英()
@@ -226,7 +243,7 @@ def test_Latex():
     # test_数学动画生成manim()
     # test_Langchain知识库()
     # test_Langchain知识库读取()
-if __name__ == "__main__":
     test_Latex()
+    # test_chatglm_finetune()
     input("程序完成，回车退出。")
     print("退出。")

crazy_functions/crazy_utils.py

@@ -130,6 +130,11 @@ def request_gpt_model_in_new_thread_with_ui_alive(
     yield from update_ui(chatbot=chatbot, history=[]) # 如果最后成功了，则删除报错信息
     return final_result
 
+def can_multi_process(llm):
+    if llm.startswith('gpt-'): return True
+    if llm.startswith('api2d-'): return True
+    if llm.startswith('azure-'): return True
+    return False
 
 def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         inputs_array, inputs_show_user_array, llm_kwargs, 
@@ -175,16 +180,16 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
         except: max_workers = 8
         if max_workers <= 0: max_workers = 3
     # 屏蔽掉 chatglm的多线程，可能会导致严重卡顿
-    if not (llm_kwargs['llm_model'].startswith('gpt-') or llm_kwargs['llm_model'].startswith('api2d-') or llm_kwargs['llm_model'].startswith('proxy-gpt')):
+    if not can_multi_process(llm_kwargs['llm_model']):
         max_workers = 1
         
     executor = ThreadPoolExecutor(max_workers=max_workers)
     n_frag = len(inputs_array)
     # 用户反馈
-    chatbot.append([None, ""])
+    chatbot.append(["请开始多线程操作。", ""])
     yield from update_ui(chatbot=chatbot, history=[]) # 刷新界面
     # 跨线程传递
-    mutable = [[f"", time.time(), "等待中"] for _ in range(n_frag)]
+    mutable = [["", time.time(), "等待中"] for _ in range(n_frag)]
 
     # 子线程任务
     def _req_gpt(index, inputs, history, sys_prompt):
@@ -272,8 +277,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
                     ' ', '.').replace('<br/>', '.....').replace('$', '.')+"`... ]"
             observe_win.append(print_something_really_funny)
         # 在前端打印些好玩的东西
-        stat_str = ''.join([f'`{inputs_show_user_array[thread_index][0:5]}...{inputs_show_user_array[thread_index][-5:]}`\t'
-                            f'`{mutable[thread_index][2]}`: {obs}\n\n'
+        stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n' 
                             if not done else f'`{mutable[thread_index][2]}`\n\n' 
                             for thread_index, done, obs in zip(range(len(worker_done)), worker_done, observe_win)])
         # 在前端打印些好玩的东西

crazy_functions/latex_fns/latex_actions.py

@@ -1,312 +1,16 @@
 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
+from .latex_toolbox import PRESERVE, TRANSFORM
+from .latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
+from .latex_toolbox import reverse_forbidden_text_careful_brace, reverse_forbidden_text, convert_to_linklist, post_process
+from .latex_toolbox import fix_content, find_main_tex_file, merge_tex_files, compile_latex_with_timeout
+
 import os, shutil
 import re
 import numpy as np
+
 pj = os.path.join
 
-"""
-========================================================================
-Part One
-Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
-========================================================================
-"""
-PRESERVE = 0
-TRANSFORM = 1
-
-def set_forbidden_text(text, mask, pattern, flags=0):
-    """
-    Add a preserve text area in this paper
-    e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
-    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
-    everything between "\begin{equation}" and "\end{equation}"
-    """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        mask[res.span()[0]:res.span()[1]] = PRESERVE
-    return text, mask
-
-def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
-    """
-    Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
-    e.g.
-    \begin{abstract} blablablablablabla. \end{abstract} 
-    """
-    if isinstance(pattern, list): pattern = '|'.join(pattern)
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        if not forbid_wrapper:
-            mask[res.span()[0]:res.span()[1]] = TRANSFORM
-        else:
-            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
-            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
-            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
-    return text, mask
-
-def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
-    """
-    Add a preserve text area in this paper (text become untouchable for GPT).
-    count the number of the braces so as to catch compelete text area. 
-    e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
-    """
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        brace_level = -1
-        p = begin = end = res.regs[0][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
-            p += 1
-        end = p+1
-        mask[begin:end] = PRESERVE
-    return text, mask
-
-def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
-    """
-    Move area out of preserve area (make text editable for GPT)
-    count the number of the braces so as to catch compelete text area. 
-    e.g.
-    \caption{blablablablabla\texbf{blablabla}blablabla.} 
-    """
-    pattern_compile = re.compile(pattern, flags)
-    for res in pattern_compile.finditer(text):
-        brace_level = 0
-        p = begin = end = res.regs[1][0]
-        for _ in range(1024*16):
-            if text[p] == '}' and brace_level == 0: break
-            elif text[p] == '}':  brace_level -= 1
-            elif text[p] == '{':  brace_level += 1
-            p += 1
-        end = p
-        mask[begin:end] = TRANSFORM
-        if forbid_wrapper:
-            mask[res.regs[0][0]:begin] = PRESERVE
-            mask[end:res.regs[0][1]] = PRESERVE
-    return text, mask
-
-def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
-    """
-    Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
-    Add it to preserve area
-    """
-    pattern_compile = re.compile(pattern, flags)
-    def search_with_line_limit(text, mask):
-        for res in pattern_compile.finditer(text):
-            cmd = res.group(1)  # begin{what}
-            this = res.group(2) # content between begin and end
-            this_mask = mask[res.regs[2][0]:res.regs[2][1]]
-            white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof', 
-                          'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
-            if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
-                this, this_mask = search_with_line_limit(this, this_mask)
-                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
-            else:
-                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
-        return text, mask
-    return search_with_line_limit(text, mask) 
-
-class LinkedListNode():
-    """
-    Linked List Node
-    """
-    def __init__(self, string, preserve=True) -> None:
-        self.string = string
-        self.preserve = preserve
-        self.next = None
-        # self.begin_line = 0
-        # self.begin_char = 0
-
-def convert_to_linklist(text, mask):
-    root = LinkedListNode("", preserve=True)
-    current_node = root
-    for c, m, i in zip(text, mask, range(len(text))):
-        if (m==PRESERVE and current_node.preserve) \
-            or (m==TRANSFORM and not current_node.preserve):
-            # add
-            current_node.string += c
-        else:
-            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
-            current_node = current_node.next
-    return root
-"""
-========================================================================
-Latex Merge File
-========================================================================
-"""
-
-def 寻找Latex主文件(file_manifest, mode):
-    """
-    在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
-    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
-    """
-    canidates = []
-    for texf in file_manifest:
-        if os.path.basename(texf).startswith('merge'):
-            continue
-        with open(texf, 'r', encoding='utf8') as f:
-            file_content = f.read()
-        if r'\documentclass' in file_content:
-            canidates.append(texf)
-        else:
-            continue
-
-    if len(canidates) == 0:
-        raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
-    elif len(canidates) == 1:
-        return canidates[0]
-    else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
-        canidates_score = []
-        # 给出一些判定模板文档的词作为扣分项
-        unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
-        expected_words = ['\input', '\ref', '\cite']
-        for texf in canidates:
-            canidates_score.append(0)
-            with open(texf, 'r', encoding='utf8') as f:
-                file_content = f.read()
-            for uw in unexpected_words:
-                if uw in file_content:
-                    canidates_score[-1] -= 1
-            for uw in expected_words:
-                if uw in file_content:
-                    canidates_score[-1] += 1
-        select = np.argmax(canidates_score) # 取评分最高者返回
-        return canidates[select]
-    
-def rm_comments(main_file):
-    new_file_remove_comment_lines = []
-    for l in main_file.splitlines():
-        # 删除整行的空注释
-        if l.lstrip().startswith("%"):
-            pass
-        else:
-            new_file_remove_comment_lines.append(l)
-    main_file = '\n'.join(new_file_remove_comment_lines)
-    # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
-    main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
-    return main_file
-
-def merge_tex_files_(project_foler, main_file, mode):
-    """
-    Merge Tex project recrusively
-    """
-    main_file = rm_comments(main_file)
-    for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
-        f = s.group(1)
-        fp = os.path.join(project_foler, f)
-        if os.path.exists(fp):  
-            # e.g., \input{srcs/07_appendix.tex}
-            with open(fp, 'r', encoding='utf-8', errors='replace') as fx:
-                c = fx.read()
-        else:  
-            # e.g., \input{srcs/07_appendix}
-            assert os.path.exists(fp+'.tex'), f'即找不到{fp}，也找不到{fp}.tex，Tex源文件缺失！'
-            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):
     """
@@ -318,13 +22,14 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
 
     # 吸收title与作者以上的部分
-    text, mask = set_forbidden_text(text, mask, r"(.*?)\\maketitle", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"^(.*?)\\maketitle", re.DOTALL)
+    text, mask = set_forbidden_text(text, mask, r"^(.*?)\\begin{document}", re.DOTALL)
     # 吸收iffalse注释
     text, mask = set_forbidden_text(text, mask, r"\\iffalse(.*?)\\fi", re.DOTALL)
     # 吸收在42行以内的begin-end组合
     text, mask = set_forbidden_text_begin_end(text, mask, r"\\begin\{([a-z\*]*)\}(.*?)\\end\{\1\}", re.DOTALL, limit_n_lines=42)
     # 吸收匿名公式
-    text, mask = set_forbidden_text(text, mask, [ r"\$\$(.*?)\$\$",  r"\\\[.*?\\\]" ], re.DOTALL)
+    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\{(.*?)\}" ])
@@ -348,77 +53,9 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     text, mask = reverse_forbidden_text(text, mask, r"\\begin\{abstract\}(.*?)\\end\{abstract\}", re.DOTALL, forbid_wrapper=True)
     root = convert_to_linklist(text, mask)
 
-    # 修复括号
-    node = root
-    while True:
-        string = node.string
-        if node.preserve: 
-            node = node.next
-            if node is None: break
-            continue
-        def break_check(string):
-            str_stack = [""] # (lv, index)
-            for i, c in enumerate(string):
-                if c == '{':
-                    str_stack.append('{')
-                elif c == '}':
-                    if len(str_stack) == 1:
-                        print('stack fix')
-                        return i
-                    str_stack.pop(-1)
-                else:
-                    str_stack[-1] += c
-            return -1
-        bp = break_check(string)
+    # 最后一步处理，增强稳健性
+    root = post_process(root)
 
-        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 = []
@@ -429,7 +66,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
             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>')
+                f.write(f'<p style="color:black;">#{node.range}{show_html}#</p>')
             else:
                 f.write(f'<p style="color:red;">{show_html}</p>')
             node = node.next
@@ -440,8 +77,6 @@ def split_subprocess(txt, project_folder, return_dict, opts):
     return_dict['segment_parts_for_gpt'] = segment_parts_for_gpt
     return return_dict
 
-
-
 class LatexPaperSplit():
     """
     break down latex file to a linked list,
@@ -456,18 +91,32 @@ class LatexPaperSplit():
         # 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):
+
+    def merge_result(self, arr, mode, msg, buggy_lines=[], buggy_line_surgery_n_lines=10):
         """
         Merge the result after the GPT process completed
         """
         result_string = ""
-        p = 0
+        node_cnt = 0
+        line_cnt = 0
+        
         for node in self.nodes:
             if node.preserve:
+                line_cnt += node.string.count('\n')
                 result_string += node.string
             else:
-                result_string += fix_content(arr[p], node.string)
-                p += 1
+                translated_txt = fix_content(arr[node_cnt], node.string)
+                begin_line = line_cnt
+                end_line = line_cnt + translated_txt.count('\n')
+
+                # reverse translation if any error
+                if any([begin_line-buggy_line_surgery_n_lines <= b_line <= end_line+buggy_line_surgery_n_lines for b_line in buggy_lines]):
+                    translated_txt = node.string
+
+                result_string += translated_txt
+                node_cnt += 1
+                line_cnt += translated_txt.count('\n')
+
         if mode == 'translate_zh':
             pattern = re.compile(r'\\begin\{abstract\}.*\n')
             match = pattern.search(result_string)
@@ -482,6 +131,7 @@ class LatexPaperSplit():
             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,
@@ -503,7 +153,6 @@ class LatexPaperSplit():
         return self.sp
 
 
-
 class LatexPaperFileGroup():
     """
     use tokenizer to break down text according to max_token_limit
@@ -531,7 +180,7 @@ class LatexPaperFileGroup():
                 self.sp_file_index.append(index)
                 self.sp_file_tag.append(self.file_paths[index])
             else:
-                from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+                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)
@@ -552,41 +201,14 @@ class LatexPaperFileGroup():
                 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
+    from ..crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
+    from .latex_actions import LatexPaperFileGroup, LatexPaperSplit
 
     #  <-------- 寻找主tex文件 ----------> 
-    maintex = 寻找Latex主文件(file_manifest, mode)
+    maintex = find_main_tex_file(file_manifest, mode)
     chatbot.append((f"定位主Latex文件", f'[Local Message] 分析结果：该项目的Latex主文件是{maintex}, 如果分析错误, 请立即终止程序, 删除或修改歧义文件, 然后重试。主程序即将开始, 请稍候。'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
     time.sleep(3)
@@ -657,58 +279,54 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
 
     write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
 
-
     #  <-------- 写出文件 ----------> 
     msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
     final_tex = lps.merge_result(pfg.file_result, mode, msg)
+    objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
+
     with open(project_folder + f'/merge_{mode}.tex', 'w', encoding='utf-8', errors='replace') as f:
         if mode != 'translate_zh' or "binary" in final_tex: f.write(final_tex)
         
 
     #  <-------- 整理结果, 退出 ----------> 
-    chatbot.append((f"完成了吗？", 'GPT结果已输出, 正在编译PDF'))
+    chatbot.append((f"完成了吗？", 'GPT结果已输出, 即将编译PDF'))
     yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
 
     #  <-------- 返回 ----------> 
     return project_folder + f'/merge_{mode}.tex'
 
 
-
-def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified):
+def remove_buggy_lines(file_path, log_path, tex_name, tex_name_pure, n_fix, work_folder_modified, fixed_line=[]):
     try:
         with open(log_path, 'r', encoding='utf-8', errors='replace') as f:
             log = f.read()
-        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)
+        buggy_line = buggy_lines[0]-1
+        print("reversing tex line that has errors", buggy_line)
+
+        # 重组，逆转出错的段落
+        if buggy_line not in fixed_line:
+            fixed_line.append(buggy_line)
+
+        lps, file_result, mode, msg = objload(file=pj(work_folder_modified,'merge_result.pkl'))
+        final_tex = lps.merge_result(file_result, mode, msg, buggy_lines=fixed_line, buggy_line_surgery_n_lines=5*n_fix)
+
         with open(pj(work_folder_modified, f"{tex_name_pure}_fix_{n_fix}.tex"), 'w', encoding='utf-8', errors='replace') as f:
-            f.writelines(file_lines)
+            f.write(final_tex)
+
         return True, f"{tex_name_pure}_fix_{n_fix}", buggy_lines
     except:
         print("Fatal error occurred, but we cannot identify error, please download zip, read latex log, and compile manually.")
         return False, -1, [-1]
 
-def compile_latex_with_timeout(command, cwd, timeout=60):
-    import subprocess
-    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
-    try:
-        stdout, stderr = process.communicate(timeout=timeout)
-    except subprocess.TimeoutExpired:
-        process.kill()
-        stdout, stderr = process.communicate()
-        print("Process timed out!")
-        return False
-    return True
 
 def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_folder_original, work_folder_modified, work_folder, mode='default'):
     import os, time
-    current_dir = os.getcwd()
     n_fix = 1
+    fixed_line = []
     max_try = 32
     chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
     chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
@@ -716,6 +334,10 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
 
     while True:
         import os
+        may_exist_bbl = pj(work_folder_modified, f'merge.bbl')
+        target_bbl = pj(work_folder_modified, f'{main_file_modified}.bbl')
+        if os.path.exists(may_exist_bbl) and not os.path.exists(target_bbl):
+            shutil.copyfile(may_exist_bbl, target_bbl)
 
         # https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
         yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history)   # 刷新Gradio前端界面
@@ -744,13 +366,11 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                 ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex  {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
 
                 yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history)   # 刷新Gradio前端界面
-
                 ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
                 ok = compile_latex_with_timeout(f'bibtex    merge_diff.aux', work_folder)
                 ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
                 ok = compile_latex_with_timeout(f'pdflatex  -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
 
-
         # <---------- 检查结果 ----------->
         results_ = ""
         original_pdf_success = os.path.exists(pj(work_folder_original, f'{main_file_original}.pdf'))
@@ -767,10 +387,19 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
         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
+            origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
             if os.path.exists(pj(work_folder, '..', 'translation')):
                 shutil.copyfile(result_pdf, pj(work_folder, '..', 'translation', 'translate_zh.pdf'))
-
             promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
+            # 将两个PDF拼接
+            if original_pdf_success: 
+                try:
+                    from .latex_toolbox import merge_pdfs
+                    concat_pdf = pj(work_folder_modified, f'comparison.pdf')
+                    merge_pdfs(origin_pdf, result_pdf, concat_pdf)
+                    promote_file_to_downloadzone(concat_pdf, rename_file=None, chatbot=chatbot)  # promote file to web UI
+                except Exception as e:
+                    pass
             return True # 成功啦
         else:
             if n_fix>=max_try: break
@@ -782,6 +411,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
                 tex_name_pure=f'{main_file_modified}',
                 n_fix=n_fix,
                 work_folder_modified=work_folder_modified,
+                fixed_line=fixed_line
             )
             yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history)   # 刷新Gradio前端界面
             if not can_retry: break
@@ -789,4 +419,29 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
     return False # 失败啦
 
 
-
+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())

crazy_functions/latex_fns/latex_toolbox.py

@@ -0,0 +1,456 @@
+import os, shutil
+import re
+import numpy as np
+PRESERVE = 0
+TRANSFORM = 1
+
+pj = os.path.join
+
+class LinkedListNode():
+    """
+    Linked List Node
+    """
+    def __init__(self, string, preserve=True) -> None:
+        self.string = string
+        self.preserve = preserve
+        self.next = None
+        self.range = None
+        # self.begin_line = 0
+        # self.begin_char = 0
+
+def convert_to_linklist(text, mask):
+    root = LinkedListNode("", preserve=True)
+    current_node = root
+    for c, m, i in zip(text, mask, range(len(text))):
+        if (m==PRESERVE and current_node.preserve) \
+            or (m==TRANSFORM and not current_node.preserve):
+            # add
+            current_node.string += c
+        else:
+            current_node.next = LinkedListNode(c, preserve=(m==PRESERVE))
+            current_node = current_node.next
+    return root
+
+def post_process(root):
+    # 修复括号
+    node = root
+    while True:
+        string = node.string
+        if node.preserve: 
+            node = node.next
+            if node is None: break
+            continue
+        def break_check(string):
+            str_stack = [""] # (lv, index)
+            for i, c in enumerate(string):
+                if c == '{':
+                    str_stack.append('{')
+                elif c == '}':
+                    if len(str_stack) == 1:
+                        print('stack fix')
+                        return i
+                    str_stack.pop(-1)
+                else:
+                    str_stack[-1] += c
+            return -1
+        bp = break_check(string)
+
+        if bp == -1:
+            pass
+        elif bp == 0:
+            node.string = string[:1]
+            q = LinkedListNode(string[1:], False)
+            q.next = node.next
+            node.next = q
+        else:
+            node.string = string[:bp]
+            q = LinkedListNode(string[bp:], False)
+            q.next = node.next
+            node.next = q
+
+        node = node.next
+        if node is None: break
+
+    # 屏蔽空行和太短的句子
+    node = root
+    while True:
+        if len(node.string.strip('\n').strip(''))==0: node.preserve = True
+        if len(node.string.strip('\n').strip(''))<42: node.preserve = True
+        node = node.next
+        if node is None: break
+    node = root
+    while True:
+        if node.next and node.preserve and node.next.preserve:
+            node.string += node.next.string
+            node.next = node.next.next
+        node = node.next
+        if node is None: break
+
+    # 将前后断行符脱离
+    node = root
+    prev_node = None
+    while True:
+        if not node.preserve:
+            lstriped_ = node.string.lstrip().lstrip('\n')
+            if (prev_node is not None) and (prev_node.preserve) and (len(lstriped_)!=len(node.string)):
+                prev_node.string += node.string[:-len(lstriped_)]
+                node.string = lstriped_
+            rstriped_ = node.string.rstrip().rstrip('\n')
+            if (node.next is not None) and (node.next.preserve) and (len(rstriped_)!=len(node.string)):
+                node.next.string = node.string[len(rstriped_):] + node.next.string
+                node.string = rstriped_
+        # =====
+        prev_node = node
+        node = node.next
+        if node is None: break
+
+    # 标注节点的行数范围
+    node = root
+    n_line = 0
+    expansion = 2
+    while True:
+        n_l = node.string.count('\n')
+        node.range = [n_line-expansion, n_line+n_l+expansion]   # 失败时，扭转的范围
+        n_line = n_line+n_l
+        node = node.next
+        if node is None: break
+    return root
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+Latex segmentation with a binary mask (PRESERVE=0, TRANSFORM=1)
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+"""
+
+
+def set_forbidden_text(text, mask, pattern, flags=0):
+    """
+    Add a preserve text area in this paper
+    e.g. with pattern = r"\\begin\{algorithm\}(.*?)\\end\{algorithm\}"
+    you can mask out (mask = PRESERVE so that text become untouchable for GPT) 
+    everything between "\begin{equation}" and "\end{equation}"
+    """
+    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        mask[res.span()[0]:res.span()[1]] = PRESERVE
+    return text, mask
+
+def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \begin{abstract} blablablablablabla. \end{abstract} 
+    """
+    if isinstance(pattern, list): pattern = '|'.join(pattern)
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        if not forbid_wrapper:
+            mask[res.span()[0]:res.span()[1]] = TRANSFORM
+        else:
+            mask[res.regs[0][0]: res.regs[1][0]] = PRESERVE   # '\\begin{abstract}'
+            mask[res.regs[1][0]: res.regs[1][1]] = TRANSFORM   # abstract
+            mask[res.regs[1][1]: res.regs[0][1]] = PRESERVE   # abstract
+    return text, mask
+
+def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
+    """
+    Add a preserve text area in this paper (text become untouchable for GPT).
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    """
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        brace_level = -1
+        p = begin = end = res.regs[0][0]
+        for _ in range(1024*16):
+            if text[p] == '}' and brace_level == 0: break
+            elif text[p] == '}':  brace_level -= 1
+            elif text[p] == '{':  brace_level += 1
+            p += 1
+        end = p+1
+        mask[begin:end] = PRESERVE
+    return text, mask
+
+def reverse_forbidden_text_careful_brace(text, mask, pattern, flags=0, forbid_wrapper=True):
+    """
+    Move area out of preserve area (make text editable for GPT)
+    count the number of the braces so as to catch compelete text area. 
+    e.g.
+    \caption{blablablablabla\texbf{blablabla}blablabla.} 
+    """
+    pattern_compile = re.compile(pattern, flags)
+    for res in pattern_compile.finditer(text):
+        brace_level = 0
+        p = begin = end = res.regs[1][0]
+        for _ in range(1024*16):
+            if text[p] == '}' and brace_level == 0: break
+            elif text[p] == '}':  brace_level -= 1
+            elif text[p] == '{':  brace_level += 1
+            p += 1
+        end = p
+        mask[begin:end] = TRANSFORM
+        if forbid_wrapper:
+            mask[res.regs[0][0]:begin] = PRESERVE
+            mask[end:res.regs[0][1]] = PRESERVE
+    return text, mask
+
+def set_forbidden_text_begin_end(text, mask, pattern, flags=0, limit_n_lines=42):
+    """
+    Find all \begin{} ... \end{} text block that with less than limit_n_lines lines.
+    Add it to preserve area
+    """
+    pattern_compile = re.compile(pattern, flags)
+    def search_with_line_limit(text, mask):
+        for res in pattern_compile.finditer(text):
+            cmd = res.group(1)  # begin{what}
+            this = res.group(2) # content between begin and end
+            this_mask = mask[res.regs[2][0]:res.regs[2][1]]
+            white_list = ['document', 'abstract', 'lemma', 'definition', 'sproof', 
+                          'em', 'emph', 'textit', 'textbf', 'itemize', 'enumerate']
+            if (cmd in white_list) or this.count('\n') >= limit_n_lines: # use a magical number 42
+                this, this_mask = search_with_line_limit(this, this_mask)
+                mask[res.regs[2][0]:res.regs[2][1]] = this_mask
+            else:
+                mask[res.regs[0][0]:res.regs[0][1]] = PRESERVE
+        return text, mask
+    return search_with_line_limit(text, mask) 
+
+
+
+"""
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+Latex Merge File
+=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
+"""
+
+def find_main_tex_file(file_manifest, mode):
+    """
+    在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
+    P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
+    """
+    canidates = []
+    for texf in file_manifest:
+        if os.path.basename(texf).startswith('merge'):
+            continue
+        with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+            file_content = f.read()
+        if r'\documentclass' in file_content:
+            canidates.append(texf)
+        else:
+            continue
+
+    if len(canidates) == 0:
+        raise RuntimeError('无法找到一个主Tex文件（包含documentclass关键字）')
+    elif len(canidates) == 1:
+        return canidates[0]
+    else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
+        canidates_score = []
+        # 给出一些判定模板文档的词作为扣分项
+        unexpected_words = ['\LaTeX', 'manuscript', 'Guidelines', 'font', 'citations', 'rejected', 'blind review', 'reviewers']
+        expected_words = ['\input', '\ref', '\cite']
+        for texf in canidates:
+            canidates_score.append(0)
+            with open(texf, 'r', encoding='utf8', errors='ignore') as f:
+                file_content = f.read()
+            for uw in unexpected_words:
+                if uw in file_content:
+                    canidates_score[-1] -= 1
+            for uw in expected_words:
+                if uw in file_content:
+                    canidates_score[-1] += 1
+        select = np.argmax(canidates_score) # 取评分最高者返回
+        return canidates[select]
+    
+def rm_comments(main_file):
+    new_file_remove_comment_lines = []
+    for l in main_file.splitlines():
+        # 删除整行的空注释
+        if l.lstrip().startswith("%"):
+            pass
+        else:
+            new_file_remove_comment_lines.append(l)
+    main_file = '\n'.join(new_file_remove_comment_lines)
+    # main_file = re.sub(r"\\include{(.*?)}", r"\\input{\1}", main_file)  # 将 \include 命令转换为 \input 命令
+    main_file = re.sub(r'(?<!\\)%.*', '', main_file)  # 使用正则表达式查找半行注释, 并替换为空字符串
+    return main_file
+
+def find_tex_file_ignore_case(fp):
+    dir_name = os.path.dirname(fp)
+    base_name = os.path.basename(fp)
+    if not base_name.endswith('.tex'): base_name+='.tex'
+    if os.path.exists(pj(dir_name, base_name)): return pj(dir_name, base_name)
+    # go case in-sensitive
+    import glob
+    for f in glob.glob(dir_name+'/*.tex'):
+        base_name_s = os.path.basename(fp)
+        if base_name_s.lower() == base_name.lower(): return f
+    return None
+
+def merge_tex_files_(project_foler, main_file, mode):
+    """
+    Merge Tex project recrusively
+    """
+    main_file = rm_comments(main_file)
+    for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
+        f = s.group(1)
+        fp = os.path.join(project_foler, f)
+        fp = find_tex_file_ignore_case(fp)
+        if fp:
+            with open(fp, 'r', encoding='utf-8', errors='replace') as fx: c = fx.read()
+        else:
+            raise RuntimeError(f'找不到{fp}，Tex源文件缺失！')
+        c = merge_tex_files_(project_foler, c, mode)
+        main_file = main_file[:s.span()[0]] + c + main_file[s.span()[1]:]
+    return main_file
+
+def 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 compile_latex_with_timeout(command, cwd, timeout=60):
+    import subprocess
+    process = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, cwd=cwd)
+    try:
+        stdout, stderr = process.communicate(timeout=timeout)
+    except subprocess.TimeoutExpired:
+        process.kill()
+        stdout, stderr = process.communicate()
+        print("Process timed out!")
+        return False
+    return True
+
+
+
+def merge_pdfs(pdf1_path, pdf2_path, output_path):
+    import PyPDF2
+    Percent = 0.8
+    # Open the first PDF file
+    with open(pdf1_path, 'rb') as pdf1_file:
+        pdf1_reader = PyPDF2.PdfFileReader(pdf1_file)
+        # Open the second PDF file
+        with open(pdf2_path, 'rb') as pdf2_file:
+            pdf2_reader = PyPDF2.PdfFileReader(pdf2_file)
+            # Create a new PDF file to store the merged pages
+            output_writer = PyPDF2.PdfFileWriter()
+            # Determine the number of pages in each PDF file
+            num_pages = max(pdf1_reader.numPages, pdf2_reader.numPages)
+            # Merge the pages from the two PDF files
+            for page_num in range(num_pages):
+                # Add the page from the first PDF file
+                if page_num < pdf1_reader.numPages:
+                    page1 = pdf1_reader.getPage(page_num)
+                else:
+                    page1 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
+                # Add the page from the second PDF file
+                if page_num < pdf2_reader.numPages:
+                    page2 = pdf2_reader.getPage(page_num)
+                else:
+                    page2 = PyPDF2.PageObject.createBlankPage(pdf1_reader)
+                # Create a new empty page with double width
+                new_page = PyPDF2.PageObject.createBlankPage(
+                    width = int(int(page1.mediaBox.getWidth()) + int(page2.mediaBox.getWidth()) * Percent),
+                    height = max(page1.mediaBox.getHeight(), page2.mediaBox.getHeight())
+                )
+                new_page.mergeTranslatedPage(page1, 0, 0)
+                new_page.mergeTranslatedPage(page2, int(int(page1.mediaBox.getWidth())-int(page2.mediaBox.getWidth())* (1-Percent)), 0)
+                output_writer.addPage(new_page)
+            # Save the merged PDF file
+            with open(output_path, 'wb') as output_file:
+                output_writer.write(output_file)

crazy_functions/live_audio/aliyunASR.py

@@ -0,0 +1,130 @@
+import time, threading, json
+
+
+class AliyunASR():
+
+    def test_on_sentence_begin(self, message, *args):
+        # print("test_on_sentence_begin:{}".format(message))
+        pass
+
+    def test_on_sentence_end(self, message, *args):
+        # print("test_on_sentence_end:{}".format(message))
+        message = json.loads(message)
+        self.parsed_sentence = message['payload']['result']
+        self.event_on_entence_end.set()
+        print(self.parsed_sentence)
+
+    def test_on_start(self, message, *args):
+        # print("test_on_start:{}".format(message))
+        pass
+
+    def test_on_error(self, message, *args):
+        print("on_error args=>{}".format(args))
+        pass
+
+    def test_on_close(self, *args):
+        self.aliyun_service_ok = False
+        pass
+
+    def test_on_result_chg(self, message, *args):
+        # print("test_on_chg:{}".format(message))
+        message = json.loads(message)
+        self.parsed_text = message['payload']['result']
+        self.event_on_result_chg.set()
+
+    def test_on_completed(self, message, *args):
+        # print("on_completed:args=>{} message=>{}".format(args, message))
+        pass
+
+
+    def audio_convertion_thread(self, uuid):
+        # 在一个异步线程中采集音频
+        import nls  # pip install git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+        import tempfile
+        from scipy import io
+        from toolbox import get_conf
+        from .audio_io import change_sample_rate
+        from .audio_io import RealtimeAudioDistribution
+        NEW_SAMPLERATE = 16000
+        rad = RealtimeAudioDistribution()
+        rad.clean_up()
+        temp_folder = tempfile.gettempdir()
+        TOKEN, APPKEY = get_conf('ALIYUN_TOKEN', 'ALIYUN_APPKEY')
+        if len(TOKEN) == 0:
+            TOKEN = self.get_token()
+        self.aliyun_service_ok = True
+        URL="wss://nls-gateway.aliyuncs.com/ws/v1"
+        sr = nls.NlsSpeechTranscriber(
+                    url=URL,
+                    token=TOKEN,
+                    appkey=APPKEY,
+                    on_sentence_begin=self.test_on_sentence_begin,
+                    on_sentence_end=self.test_on_sentence_end,
+                    on_start=self.test_on_start,
+                    on_result_changed=self.test_on_result_chg,
+                    on_completed=self.test_on_completed,
+                    on_error=self.test_on_error,
+                    on_close=self.test_on_close,
+                    callback_args=[uuid.hex]
+                )
+
+        r = sr.start(aformat="pcm",
+                enable_intermediate_result=True,
+                enable_punctuation_prediction=True,
+                enable_inverse_text_normalization=True)
+
+        while not self.stop:
+            # time.sleep(self.capture_interval)
+            audio = rad.read(uuid.hex) 
+            if audio is not None:
+                # convert to pcm file
+                temp_file = f'{temp_folder}/{uuid.hex}.pcm' # 
+                dsdata = change_sample_rate(audio, rad.rate, NEW_SAMPLERATE) # 48000 --> 16000
+                io.wavfile.write(temp_file, NEW_SAMPLERATE, dsdata)
+                # read pcm binary
+                with open(temp_file, "rb") as f: data = f.read()
+                # print('audio len:', len(audio), '\t ds len:', len(dsdata), '\t need n send:', len(data)//640)
+                slices = zip(*(iter(data),) * 640)    # 640个字节为一组
+                for i in slices: sr.send_audio(bytes(i))
+            else:
+                time.sleep(0.1)
+
+            if not self.aliyun_service_ok:
+                self.stop = True
+                self.stop_msg = 'Aliyun音频服务异常，请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期。'
+        r = sr.stop()
+
+    def get_token(self):
+        from toolbox import get_conf
+        import json
+        from aliyunsdkcore.request import CommonRequest
+        from aliyunsdkcore.client import AcsClient
+        AccessKey_ID, AccessKey_secret = get_conf('ALIYUN_ACCESSKEY', 'ALIYUN_SECRET')
+
+        # 创建AcsClient实例
+        client = AcsClient(
+            AccessKey_ID,
+            AccessKey_secret,
+            "cn-shanghai"
+        )
+
+        # 创建request，并设置参数。
+        request = CommonRequest()
+        request.set_method('POST')
+        request.set_domain('nls-meta.cn-shanghai.aliyuncs.com')
+        request.set_version('2019-02-28')
+        request.set_action_name('CreateToken')
+
+        try:
+            response = client.do_action_with_exception(request)
+            print(response)
+            jss = json.loads(response)
+            if 'Token' in jss and 'Id' in jss['Token']:
+                token = jss['Token']['Id']
+                expireTime = jss['Token']['ExpireTime']
+                print("token = " + token)
+                print("expireTime = " + str(expireTime))
+        except Exception as e:
+            print(e)
+
+        return token

crazy_functions/live_audio/audio_io.py

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

crazy_functions/下载arxiv论文翻译摘要.py

@@ -144,11 +144,11 @@ def 下载arxiv论文并翻译摘要(txt, llm_kwargs, plugin_kwargs, chatbot, hi
 
     # 尝试导入依赖，如果缺少依赖，则给出安装建议
     try:
-        import pdfminer, bs4
+        import bs4
     except:
         report_execption(chatbot, history, 
             a = f"解析项目: {txt}", 
-            b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pdfminer beautifulsoup4```。")
+            b = f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade beautifulsoup4```。")
         yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
         return
 

crazy_functions/交互功能函数模板.py

@@ -0,0 +1,63 @@
+from toolbox import CatchException, update_ui
+from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+
+
+@CatchException
+def 交互功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, 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, 如温度和top_p等, 一般原样传递下去就行
+    chatbot         聊天显示框的句柄，用于显示给用户
+    history         聊天历史，前情提要
+    system_prompt   给gpt的静默提醒
+    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？", "交互功能函数模板。在执行完成之后, 可以将自身的状态存储到cookie中, 等待用户的再次调用。"))
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    state = chatbot._cookies.get('plugin_state_0001', None) # 初始化插件状态
+
+    if state is None:
+        chatbot._cookies['lock_plugin'] = 'crazy_functions.交互功能函数模板->交互功能模板函数'      # 赋予插件锁定 锁定插件回调路径，当下一次用户提交时，会直接转到该函数
+        chatbot._cookies['plugin_state_0001'] = 'wait_user_keyword'                              # 赋予插件状态
+
+        chatbot.append(("第一次调用：", "请输入关键词, 我将为您查找相关壁纸, 建议使用英文单词, 插件锁定中，请直接提交即可。"))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    if state == 'wait_user_keyword':
+        chatbot._cookies['lock_plugin'] = None          # 解除插件锁定，避免遗忘导致死锁
+        chatbot._cookies['plugin_state_0001'] = None    # 解除插件状态，避免遗忘导致死锁
+
+        # 解除插件锁定
+        chatbot.append((f"获取关键词：{txt}", ""))
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        page_return = get_image_page_by_keyword(txt)
+        inputs=inputs_show_user=f"Extract all image urls in this html page, pick the first 5 images and show them with markdown format: \n\n {page_return}"
+        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
+            inputs=inputs, inputs_show_user=inputs_show_user,
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
+            sys_prompt="When you want to show an image, use markdown format. e.g. ![image_description](image_url). If there are no image url provided, answer 'no image url provided'"
+        )
+        chatbot[-1] = [chatbot[-1][0], gpt_say]
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+
+
+# ---------------------------------------------------------------------------------
+
+def get_image_page_by_keyword(keyword):
+    import requests
+    from bs4 import BeautifulSoup
+    response = requests.get(f'https://wallhaven.cc/search?q={keyword}', timeout=2)
+    res = "image urls: \n"
+    for image_element in BeautifulSoup(response.content, 'html.parser').findAll("img"):
+        try:
+            res += image_element["data-src"]
+            res += "\n"
+        except:
+            pass
+    return res

crazy_functions/图片生成.py

@@ -27,22 +27,20 @@ def gen_image(llm_kwargs, prompt, resolution="256x256"):
     }
     response = requests.post(url, headers=headers, json=data, proxies=proxies)
     print(response.content)
-
     try:
         image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
     except:
         raise RuntimeError(response.content.decode())
-
     # 文件保存到本地
     r = requests.get(image_url, proxies=proxies)
     file_path = 'gpt_log/image_gen/'
     os.makedirs(file_path, exist_ok=True)
     file_name = 'Image' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.png'
-    with open(file_path + file_name, 'wb+') as f:
-        f.write(r.content)
-    return image_url, file_path + file_name
+    with open(file_path+file_name, 'wb+') as f: f.write(r.content)
 
 
+    return image_url, file_path+file_name
+
 
 
 @CatchException

crazy_functions/对话历史存档.py

@@ -12,7 +12,7 @@ def write_chat_to_file(chatbot, history=None, file_name=None):
         file_name = 'chatGPT对话历史' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.html'
     os.makedirs('./gpt_log/', exist_ok=True)
     with open(f'./gpt_log/{file_name}', 'w', encoding='utf8') as f:
-        from theme import advanced_css
+        from themes.theme import advanced_css
         f.write(f'<!DOCTYPE html><head><meta charset="utf-8"><title>对话历史</title><style>{advanced_css}</style></head>')
         for i, contents in enumerate(chatbot):
             for j, content in enumerate(contents):

crazy_functions/总结word文档.py

@@ -14,17 +14,19 @@ def 解析docx(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot
             doc = Document(fp)
             file_content = "\n".join([para.text for para in doc.paragraphs])
         else:
+            try:
                 import win32com.client
                 word = win32com.client.Dispatch("Word.Application")
                 word.visible = False
                 # 打开文件
-            print('fp', os.getcwd())
                 doc = word.Documents.Open(os.getcwd() + '/' + fp)
                 # file_content = doc.Content.Text
                 doc = word.ActiveDocument
                 file_content = doc.Range().Text
                 doc.Close()
                 word.Quit()
+            except:
+                raise RuntimeError('请先将.doc文档转换为.docx文档。')
 
         print(file_content)
         # private_upload里面的文件名在解压zip后容易出现乱码（rar和7z格式正常），故可以只分析文章内容，不输入文件名

crazy_functions/批量总结PDF文档.py

@@ -1,121 +1,107 @@
-from toolbox import update_ui
+from toolbox import update_ui, promote_file_to_downloadzone, gen_time_str
 from toolbox import CatchException, report_execption, write_results_to_file
-import re
-import unicodedata
-fast_debug = False
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
+from .crazy_utils import read_and_clean_pdf_text
+from .crazy_utils import input_clipping
 
-def is_paragraph_break(match):
-    """
-    根据给定的匹配结果来判断换行符是否表示段落分隔。
-    如果换行符前为句子结束标志（句号，感叹号，问号），且下一个字符为大写字母，则换行符更有可能表示段落分隔。
-    也可以根据之前的内容长度来判断段落是否已经足够长。
-    """
-    prev_char, next_char = match.groups()
 
-    # 句子结束标志
-    sentence_endings = ".!?"
-
-    # 设定一个最小段落长度阈值
-    min_paragraph_length = 140
-
-    if prev_char in sentence_endings and next_char.isupper() and len(match.string[:match.start(1)]) > min_paragraph_length:
-        return "\n\n" 
-    else:
-        return " "
-
-def normalize_text(text):
-    """
-    通过把连字（ligatures）等文本特殊符号转换为其基本形式来对文本进行归一化处理。
-    例如，将连字 "fi" 转换为 "f" 和 "i"。
-    """
-    # 对文本进行归一化处理，分解连字
-    normalized_text = unicodedata.normalize("NFKD", text)
-
-    # 替换其他特殊字符
-    cleaned_text = re.sub(r'[^\x00-\x7F]+', '', normalized_text)
-
-    return cleaned_text
-
-def clean_text(raw_text):
-    """
-    对从 PDF 提取出的原始文本进行清洗和格式化处理。
-    1. 对原始文本进行归一化处理。
-    2. 替换跨行的连词
-    3. 根据 heuristic 规则判断换行符是否是段落分隔，并相应地进行替换
-    """
-    # 对文本进行归一化处理
-    normalized_text = normalize_text(raw_text)
-
-    # 替换跨行的连词
-    text = re.sub(r'(\w+-\n\w+)', lambda m: m.group(1).replace('-\n', ''), normalized_text)
-
-    # 根据前后相邻字符的特点，找到原文本中的换行符
-    newlines = re.compile(r'(\S)\n(\S)')
-
-    # 根据 heuristic 规则，用空格或段落分隔符替换原换行符
-    final_text = re.sub(newlines, lambda m: m.group(1) + is_paragraph_break(m) + m.group(2), text)
-
-    return final_text.strip()
 
 def 解析PDF(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
-    import time, glob, os, fitz
-    print('begin analysis on:', file_manifest)
-    for index, fp in enumerate(file_manifest):
-        with fitz.open(fp) as doc:
-            file_content = ""
-            for page in doc:
-                file_content += page.get_text()
-            file_content = clean_text(file_content)
-            print(file_content)
+    file_write_buffer = []
+    for file_name in file_manifest:
+        print('begin analysis on:', file_name)
+        ############################## <第 0 步，切割PDF> ##################################
+        # 递归地切割PDF文件，每一块（尽量是完整的一个section，比如introduction，experiment等，必要时再进行切割）
+        # 的长度必须小于 2500 个 Token
+        file_content, page_one = read_and_clean_pdf_text(file_name) # （尝试）按照章节切割PDF
+        file_content = file_content.encode('utf-8', 'ignore').decode()   # avoid reading non-utf8 chars
+        page_one = str(page_one).encode('utf-8', 'ignore').decode()  # avoid reading non-utf8 chars
         
-        prefix = "接下来请你逐文件分析下面的论文文件，概括其内容" if index==0 else ""
-        i_say = prefix + f'请对下面的文章片段用中文做一个概述，文件名是{os.path.relpath(fp, project_folder)}，文章内容是 ```{file_content}```'
-        i_say_show_user = prefix + f'[{index}/{len(file_manifest)}] 请对下面的文章片段做一个概述: {os.path.abspath(fp)}'
-        chatbot.append((i_say_show_user, "[Local Message] waiting gpt response."))
-        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        TOKEN_LIMIT_PER_FRAGMENT = 2500
 
-        if not fast_debug: 
-            msg = '正常'
-            # ** gpt request **
+        from .crazy_utils import breakdown_txt_to_satisfy_token_limit_for_pdf
+        from request_llm.bridge_all import model_info
+        enc = model_info["gpt-3.5-turbo"]['tokenizer']
+        def get_token_num(txt): return len(enc.encode(txt, disallowed_special=()))
+        paper_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
+            txt=file_content,  get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT)
+        page_one_fragments = breakdown_txt_to_satisfy_token_limit_for_pdf(
+            txt=str(page_one), get_token_fn=get_token_num, limit=TOKEN_LIMIT_PER_FRAGMENT//4)
+        # 为了更好的效果，我们剥离Introduction之后的部分（如果有）
+        paper_meta = page_one_fragments[0].split('introduction')[0].split('Introduction')[0].split('INTRODUCTION')[0]
+        
+        ############################## <第 1 步，从摘要中提取高价值信息，放到history中> ##################################
+        final_results = []
+        final_results.append(paper_meta)
+
+        ############################## <第 2 步，迭代地历遍整个文章，提取精炼信息> ##################################
+        i_say_show_user = f'首先你在中文语境下通读整篇论文。'; gpt_say = "[Local Message] 收到。"           # 用户提示
+        chatbot.append([i_say_show_user, gpt_say]); yield from update_ui(chatbot=chatbot, history=[])    # 更新UI
+
+        iteration_results = []
+        last_iteration_result = paper_meta  # 初始值是摘要
+        MAX_WORD_TOTAL = 4096 * 0.7
+        n_fragment = len(paper_fragments)
+        if n_fragment >= 20: print('文章极长，不能达到预期效果')
+        for i in range(n_fragment):
+            NUM_OF_WORD = MAX_WORD_TOTAL // n_fragment
+            i_say = f"Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i]}"
+            i_say_show_user = f"[{i+1}/{n_fragment}] Read this section, recapitulate the content of this section with less than {NUM_OF_WORD} Chinese characters: {paper_fragments[i][:200]}"
+            gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(i_say, i_say_show_user,  # i_say=真正给chatgpt的提问， i_say_show_user=给用户看的提问
+                                                                                llm_kwargs, chatbot, 
+                                                                                history=["The main idea of the previous section is?", last_iteration_result], # 迭代上一次的结果
+                                                                                sys_prompt="Extract the main idea of this section with Chinese."  # 提示
+                                                                                ) 
+            iteration_results.append(gpt_say)
+            last_iteration_result = gpt_say
+
+        ############################## <第 3 步，整理history，提取总结> ##################################
+        final_results.extend(iteration_results)
+        final_results.append(f'Please conclude this paper discussed above。')
+        # This prompt is from https://github.com/kaixindelele/ChatPaper/blob/main/chat_paper.py
+        NUM_OF_WORD = 1000
+        i_say = """
+1. Mark the title of the paper (with Chinese translation)
+2. list all the authors' names (use English)
+3. mark the first author's affiliation (output Chinese translation only)
+4. mark the keywords of this article (use English)
+5. link to the paper, Github code link (if available, fill in Github:None if not)
+6. summarize according to the following four points.Be sure to use Chinese answers (proper nouns need to be marked in English)
+    - (1):What is the research background of this article?
+    - (2):What are the past methods? What are the problems with them? Is the approach well motivated?
+    - (3):What is the research methodology proposed in this paper?
+    - (4):On what task and what performance is achieved by the methods in this paper? Can the performance support their goals?
+Follow the format of the output that follows:                  
+1. Title: xxx\n\n
+2. Authors: xxx\n\n
+3. Affiliation: xxx\n\n
+4. Keywords: xxx\n\n
+5. Urls: xxx or xxx , xxx \n\n
+6. Summary: \n\n
+    - (1):xxx;\n 
+    - (2):xxx;\n 
+    - (3):xxx;\n
+    - (4):xxx.\n\n
+Be sure to use Chinese answers (proper nouns need to be marked in English), statements as concise and academic as possible,
+do not have too much repetitive information, numerical values using the original numbers.
+        """
+        # This prompt is from https://github.com/kaixindelele/ChatPaper/blob/main/chat_paper.py
+        file_write_buffer.extend(final_results)
+        i_say, final_results = input_clipping(i_say, final_results, max_token_limit=2000)
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-                inputs=i_say, 
-                inputs_show_user=i_say_show_user, 
-                llm_kwargs=llm_kwargs,
-                chatbot=chatbot, 
-                history=[],
-                sys_prompt="总结文章。"
-            )  # 带超时倒计时
+            inputs=i_say, inputs_show_user='开始最终总结', 
+            llm_kwargs=llm_kwargs, chatbot=chatbot, history=final_results, 
+            sys_prompt= f"Extract the main idea of this paper with less than {NUM_OF_WORD} Chinese characters"
+        )
+        final_results.append(gpt_say)
+        file_write_buffer.extend([i_say, gpt_say])
+        ############################## <第 4 步，设置一个token上限> ##################################
+        _, final_results = input_clipping("", final_results, max_token_limit=3200)
+        yield from update_ui(chatbot=chatbot, history=final_results) # 注意这里的历史记录被替代了
 
-
-            chatbot[-1] = (i_say_show_user, gpt_say)
-            history.append(i_say_show_user); history.append(gpt_say)
-            yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-            if not fast_debug: time.sleep(2)
-
-    all_file = ', '.join([os.path.relpath(fp, project_folder) for index, fp in enumerate(file_manifest)])
-    i_say = f'根据以上你自己的分析，对全文进行概括，用学术性语言写一段中文摘要，然后再写一段英文摘要（包括{all_file}）。'
-    chatbot.append((i_say, "[Local Message] waiting gpt response."))
-    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
-
-    if not fast_debug: 
-        msg = '正常'
-        # ** gpt request **
-        gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
-            inputs=i_say, 
-            inputs_show_user=i_say, 
-            llm_kwargs=llm_kwargs,
-            chatbot=chatbot, 
-            history=history,
-            sys_prompt="总结文章。"
-        )  # 带超时倒计时
-
-        chatbot[-1] = (i_say, gpt_say)
-        history.append(i_say); history.append(gpt_say)
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
-        res = write_results_to_file(history)
-        chatbot.append(("完成了吗？", res))
-        yield from update_ui(chatbot=chatbot, history=history, msg=msg) # 刷新界面
+    res = write_results_to_file(file_write_buffer, file_name=gen_time_str())
+    promote_file_to_downloadzone(res.split('\t')[-1], chatbot=chatbot)
+    yield from update_ui(chatbot=chatbot, history=final_results) # 刷新界面
 
 
 @CatchException
@@ -151,10 +137,7 @@ def 批量总结PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
         return
 
     # 搜索需要处理的文件清单
-    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)] # + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)] + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.cpp', recursive=True)] + \
-                    # [f for f in glob.glob(f'{project_folder}/**/*.c', recursive=True)]
+    file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.pdf', recursive=True)]
     
     # 如果没找到任何文件
     if len(file_manifest) == 0:

crazy_functions/理解PDF文档内容.py

@@ -53,10 +53,9 @@ def 解析PDF(file_name, llm_kwargs, plugin_kwargs, chatbot, history, system_pro
                                                                         ) 
         iteration_results.append(gpt_say)
         last_iteration_result = gpt_say
+
     ############################## <第 3 步，整理history> ##################################
     final_results.extend(iteration_results)
-    # 将摘要添加到历史中，方便"猜你想问"使用
-    history.extend([last_iteration_result])
     final_results.append(f'接下来，你是一名专业的学术教授，利用以上信息，使用中文回答我的问题。')
     # 接下来两句话只显示在界面上，不起实际作用
     i_say_show_user = f'接下来，你是一名专业的学术教授，利用以上信息，使用中文回答我的问题。'; gpt_say = "[Local Message] 收到。"
@@ -113,4 +112,3 @@ def 理解PDF文档内容标准文件输入(txt, llm_kwargs, plugin_kwargs, chat
     txt = file_manifest[0]
     # 开始正式执行任务
     yield from 解析PDF(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
-

crazy_functions/解析JupyterNotebook.py

@@ -144,13 +144,3 @@ def 解析ipynb文件(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_p
         yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
         return
     yield from ipynb解释(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, )
-
-
-if __name__ == '__main__':
-    import json
-    filename = ''
-    code = parseNotebook(filename)
-    print(code)
-    with open(filename, 'r', encoding='utf-8', errors='replace') as f:
-        notebook = f.read()
-        print(notebook)

crazy_functions/询问多个大语言模型.py

@@ -6,7 +6,7 @@ def 同时问询(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数，如温度和top_p等，一般原样传递下去就行
+    plugin_kwargs   插件模型的参数，用于灵活调整复杂功能的各种参数
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
@@ -35,7 +35,7 @@ def 同时问询_指定模型(txt, llm_kwargs, plugin_kwargs, chatbot, history,
     """
     txt             输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径
     llm_kwargs      gpt模型参数，如温度和top_p等，一般原样传递下去就行
-    plugin_kwargs   插件模型的参数，如温度和top_p等，一般原样传递下去就行
+    plugin_kwargs   插件模型的参数，用于灵活调整复杂功能的各种参数
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒

crazy_functions/语音助手.py

@@ -0,0 +1,195 @@
+from toolbox import update_ui
+from toolbox import CatchException, get_conf, markdown_convertion
+from crazy_functions.crazy_utils import input_clipping
+from request_llm.bridge_all import predict_no_ui_long_connection
+import threading, time
+import numpy as np
+from .live_audio.aliyunASR import AliyunASR
+import json
+
+class WatchDog():
+    def __init__(self, timeout, bark_fn, interval=3, msg="") -> None:
+        self.last_feed = None
+        self.timeout = timeout
+        self.bark_fn = bark_fn
+        self.interval = interval
+        self.msg = msg
+        self.kill_dog = False
+    
+    def watch(self):
+        while True:
+            if self.kill_dog: break
+            if time.time() - self.last_feed > self.timeout:
+                if len(self.msg) > 0: print(self.msg)
+                self.bark_fn()
+                break
+            time.sleep(self.interval)
+
+    def begin_watch(self):
+        self.last_feed = time.time()
+        th = threading.Thread(target=self.watch)
+        th.daemon = True
+        th.start()
+
+    def feed(self):
+        self.last_feed = time.time()
+
+def chatbot2history(chatbot):
+    history = []
+    for c in chatbot:
+        for q in c:
+            if q not in ["[请讲话]", "[等待GPT响应]", "[正在等您说完问题]"]:
+                history.append(q.strip('<div class="markdown-body">').strip('</div>').strip('<p>').strip('</p>'))
+    return history
+
+class AsyncGptTask():
+    def __init__(self) -> None:
+        self.observe_future = []
+        self.observe_future_chatbot_index = []
+
+    def gpt_thread_worker(self, i_say, llm_kwargs, history, sys_prompt, observe_window, index):
+        try:
+            MAX_TOKEN_ALLO = 2560
+            i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
+            gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt, 
+                                                            observe_window=observe_window[index], console_slience=True)
+        except ConnectionAbortedError as token_exceed_err:
+            print('至少一个线程任务Token溢出而失败', e)
+        except Exception as e:
+            print('至少一个线程任务意外失败', e)
+
+    def add_async_gpt_task(self, i_say, chatbot_index, llm_kwargs, history, system_prompt):
+        self.observe_future.append([""])
+        self.observe_future_chatbot_index.append(chatbot_index)
+        cur_index = len(self.observe_future)-1
+        th_new = threading.Thread(target=self.gpt_thread_worker, args=(i_say, llm_kwargs, history, system_prompt, self.observe_future, cur_index))
+        th_new.daemon = True
+        th_new.start()
+
+    def update_chatbot(self, chatbot):
+        for of, ofci in zip(self.observe_future, self.observe_future_chatbot_index):
+            try:
+                chatbot[ofci] = list(chatbot[ofci])
+                chatbot[ofci][1] = markdown_convertion(of[0])
+            except:
+                self.observe_future = []
+                self.observe_future_chatbot_index = []
+        return chatbot
+
+class InterviewAssistant(AliyunASR):
+    def __init__(self):
+        self.capture_interval = 0.5 # second
+        self.stop = False
+        self.parsed_text = ""
+        self.parsed_sentence = ""
+        self.buffered_sentence = ""
+        self.event_on_result_chg = threading.Event()
+        self.event_on_entence_end = threading.Event()
+        self.event_on_commit_question = threading.Event()
+
+    def __del__(self):
+        self.stop = True
+        self.stop_msg = ""
+        self.commit_wd.kill_dog = True
+        self.plugin_wd.kill_dog = True
+
+    def init(self, chatbot):
+        # 初始化音频采集线程
+        self.captured_audio = np.array([])
+        self.keep_latest_n_second = 10
+        self.commit_after_pause_n_second = 1.5
+        self.ready_audio_flagment = None
+        self.stop = False
+        self.plugin_wd = WatchDog(timeout=5, bark_fn=self.__del__, msg="程序终止")
+        self.aut = threading.Thread(target=self.audio_convertion_thread, args=(chatbot._cookies['uuid'],))
+        self.aut.daemon = True
+        self.aut.start()
+        # th2 = threading.Thread(target=self.audio2txt_thread, args=(chatbot._cookies['uuid'],))
+        # th2.daemon = True
+        # th2.start()
+
+    def no_audio_for_a_while(self):
+        if len(self.buffered_sentence) < 7: # 如果一句话小于7个字，暂不提交
+            self.commit_wd.begin_watch()
+        else:
+            self.event_on_commit_question.set()
+
+    def begin(self, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt):
+        # main plugin function
+        self.init(chatbot)
+        chatbot.append(["[请讲话]", "[正在等您说完问题]"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        self.plugin_wd.begin_watch()
+        self.agt = AsyncGptTask()
+        self.commit_wd = WatchDog(timeout=self.commit_after_pause_n_second, bark_fn=self.no_audio_for_a_while, interval=0.2)
+        self.commit_wd.begin_watch()
+
+        while not self.stop:
+            self.event_on_result_chg.wait(timeout=0.25)  # run once every 0.25 second
+            chatbot = self.agt.update_chatbot(chatbot)   # 将子线程的gpt结果写入chatbot
+            history = chatbot2history(chatbot)
+            yield from update_ui(chatbot=chatbot, history=history)      # 刷新界面
+            self.plugin_wd.feed()
+
+            if self.event_on_result_chg.is_set(): 
+                # update audio decode result
+                self.event_on_result_chg.clear()
+                chatbot[-1] = list(chatbot[-1])
+                chatbot[-1][0] = self.buffered_sentence + self.parsed_text
+                history = chatbot2history(chatbot)
+                yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
+                self.commit_wd.feed()
+
+            if self.event_on_entence_end.is_set():
+                # called when a sentence has ended
+                self.event_on_entence_end.clear()
+                self.parsed_text = self.parsed_sentence
+                self.buffered_sentence += self.parsed_sentence
+
+            if self.event_on_commit_question.is_set():
+                # called when a question should be commited
+                self.event_on_commit_question.clear()
+                if len(self.buffered_sentence) == 0: raise RuntimeError
+
+                self.commit_wd.begin_watch()
+                chatbot[-1] = list(chatbot[-1])
+                chatbot[-1] = [self.buffered_sentence, "[等待GPT响应]"]
+                yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+                # add gpt task 创建子线程请求gpt，避免线程阻塞
+                history = chatbot2history(chatbot)
+                self.agt.add_async_gpt_task(self.buffered_sentence, len(chatbot)-1, llm_kwargs, history, system_prompt)
+                
+                self.buffered_sentence = ""
+                chatbot.append(["[请讲话]", "[正在等您说完问题]"])
+                yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+        if len(self.stop_msg) != 0:
+            raise RuntimeError(self.stop_msg)
+
+
+
+@CatchException
+def 语音助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
+    # pip install -U openai-whisper
+    chatbot.append(["对话助手函数插件：使用时，双手离开鼠标键盘吧", "音频助手, 正在听您讲话（点击“停止”键可终止程序）..."])
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+
+    # 尝试导入依赖，如果缺少依赖，则给出安装建议
+    try:
+        import nls
+        from scipy import io
+    except:
+        chatbot.append(["导入依赖失败", "使用该模块需要额外依赖, 安装方法:```pip install --upgrade aliyun-python-sdk-core==2.13.3 pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git```"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    APPKEY = get_conf('ALIYUN_APPKEY')
+    if APPKEY == "":
+        chatbot.append(["导入依赖失败", "没有阿里云语音识别APPKEY和TOKEN, 详情见https://help.aliyun.com/document_detail/450255.html"])
+        yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+        return
+
+    yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
+    ia = InterviewAssistant()
+    yield from ia.begin(llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
+

crazy_functions/辅助回答.py

@@ -13,13 +13,8 @@ def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
         show_say = txt
         prompt = txt+'\n回答完问题后，再列出用户可能提出的三个问题。'
     else:
-
+        prompt = history[-1]+"\n分析上述回答，再列出用户可能提出的三个问题。"
         show_say = '分析上述回答，再列出用户可能提出的三个问题。'
-        try:
-            prompt = history[-1]+f"\n{show_say}"
-        except IndexError:
-            prompt = system_prompt+"\n再列出用户可能提出的三个问题。"
-
     gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
         inputs=prompt,
         inputs_show_user=show_say,
@@ -28,8 +23,6 @@ def 猜你想问(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
         history=history,
         sys_prompt=system_prompt
     )
-
     chatbot[-1] = (show_say, gpt_say)
     history.extend([show_say, gpt_say])
     yield from update_ui(chatbot=chatbot, history=history)  # 刷新界面
-

crazy_functions/高级功能函数模板.py

@@ -1,13 +1,12 @@
 from toolbox import CatchException, update_ui
 from .crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
-import datetime, re
-
+import datetime
 @CatchException
 def 高阶功能模板函数(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
+    plugin_kwargs   插件模型的参数，用于灵活调整复杂功能的各种参数
     chatbot         聊天显示框的句柄，用于显示给用户
     history         聊天历史，前情提要
     system_prompt   给gpt的静默提醒
@@ -19,34 +18,12 @@ def 高阶功能模板函数(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
     for i in range(5):
         currentMonth = (datetime.date.today() + datetime.timedelta(days=i)).month
         currentDay = (datetime.date.today() + datetime.timedelta(days=i)).day
-        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？用中文列举两条，然后分别给出描述事件的两个英文单词。' + '当你给出关键词时，使用以下json格式：{"KeyWords":[EnglishKeyWord1,EnglishKeyWord2]}。'
+        i_say = f'历史中哪些事件发生在{currentMonth}月{currentDay}日？列举两条并发送相关图片。发送图片时，请使用Markdown，将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词。'
         gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
             inputs=i_say, inputs_show_user=i_say, 
             llm_kwargs=llm_kwargs, chatbot=chatbot, history=[], 
-            sys_prompt='输出格式示例：1908年，美国消防救援事业发展的“美国消防协会”成立。关键词：{"KeyWords":["Fire","American"]}。'
+            sys_prompt="当你想发送一张照片时，请使用Markdown, 并且不要有反斜线, 不要用代码块。使用 Unsplash API (https://source.unsplash.com/1280x720/? < PUT_YOUR_QUERY_HERE >)。"
         )
-        gpt_say = get_images(gpt_say)
         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
-
-
-def get_images(gpt_say):
-    def get_image_by_keyword(keyword):
-        import requests
-        from bs4 import BeautifulSoup
-        response = requests.get(f'https://wallhaven.cc/search?q={keyword}', timeout=2)
-        for image_element in BeautifulSoup(response.content, 'html.parser').findAll("img"):
-            if "data-src" in image_element: break
-        return image_element["data-src"]
-
-    for keywords in re.findall('{"KeyWords":\[(.*?)\]}', gpt_say):
-        keywords = [n.strip('"') for n in keywords.split(',')]
-        try:
-            description = keywords[0]
-            url = get_image_by_keyword(keywords[0])
-            img_tag = f"\n\n![{description}]({url})"
-            gpt_say += img_tag
-        except:
-            continue
-    return gpt_say

docker-compose.yml

@@ -6,7 +6,7 @@
 version: '3'
 services:
   gpt_academic_nolocalllms:
-    image: ghcr.io/binary-husky/gpt_academic_nolocal:master
+    image: ghcr.io/binary-husky/gpt_academic_nolocal:master # (Auto Built by Dockerfile: docs/GithubAction+NoLocal)
     environment:
       # 请查阅 `config.py` 以查看所有的配置信息
       API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                                            '
@@ -33,7 +33,7 @@ services:
 version: '3'
 services:
   gpt_academic_with_chatglm:
-    image: ghcr.io/binary-husky/gpt_academic_chatglm_moss:master
+    image: ghcr.io/binary-husky/gpt_academic_chatglm_moss:master  # (Auto Built by Dockerfile: docs/Dockerfile+ChatGLM)
     environment:
       # 请查阅 `config.py` 以查看所有的配置信息
       API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx  '
@@ -63,7 +63,7 @@ services:
 version: '3'
 services:
   gpt_academic_with_rwkv:
-    image: fuqingxu/gpt_academic:jittorllms    # [option 2] 如果需要运行ChatGLM本地模型
+    image: ghcr.io/binary-husky/gpt_academic_jittorllms:master
     environment:
       # 请查阅 `config.py` 以查看所有的配置信息
       API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx  '
@@ -85,33 +85,18 @@ services:
     # 与宿主的网络融合
     network_mode: "host"
 
-    # 使用代理网络拉取最新代码
-    # command: >
-    #   bash -c "       truncate -s -1 /etc/proxychains.conf &&
-    #                   echo \"socks5 127.0.0.1 10880\" >> /etc/proxychains.conf &&
-    #                   echo '[gpt-academic] 正在从github拉取最新代码...' &&
-    #                   proxychains git pull &&
-    #                   echo '[jittorllms] 正在从github拉取最新代码...' &&
-    #                   proxychains git --git-dir=request_llm/jittorllms/.git --work-tree=request_llm/jittorllms pull --force &&
-    #                   python3 -u main.py"
-
     # 不使用代理网络拉取最新代码
     command: >
-      bash -c "       echo '[gpt-academic] 正在从github拉取最新代码...' &&
-                      git pull &&
-                      pip install -r requirements.txt &&
-                      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"
+      python3 -u main.py
 
 
 ## ===================================================
-## 【方案四】 chatgpt + Latex
+## 【方案四】 ChatGPT + Latex
 ## ===================================================
 version: '3'
 services:
   gpt_academic_with_latex:
-    image: ghcr.io/binary-husky/gpt_academic_with_latex:master
+    image: ghcr.io/binary-husky/gpt_academic_with_latex:master  # (Auto Built by Dockerfile: docs/GithubAction+NoLocal+Latex)
     environment:
       # 请查阅 `config.py` 以查看所有的配置信息
       API_KEY:                  '    sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                              '

docs/Dockerfile+JittorLLM

@@ -26,7 +26,7 @@ RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
 RUN $useProxyNetwork python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
 # 下载分支
 WORKDIR /gpt
-RUN $useProxyNetwork git clone https://github.com/binary-husky/chatgpt_academic.git -b jittor
+RUN $useProxyNetwork git clone https://github.com/binary-husky/chatgpt_academic.git
 WORKDIR /gpt/chatgpt_academic
 RUN $useProxyNetwork python3 -m pip install -r requirements.txt
 RUN $useProxyNetwork python3 -m pip install -r request_llm/requirements_chatglm.txt

docs/GithubAction+JittorLLMs

@@ -13,7 +13,7 @@ RUN python3 -m pip install torch --extra-index-url https://download.pytorch.org/
 
 # 下载分支
 WORKDIR /gpt
-RUN git clone https://github.com/binary-husky/chatgpt_academic.git -b jittor
+RUN git clone https://github.com/binary-husky/chatgpt_academic.git
 WORKDIR /gpt/chatgpt_academic
 RUN python3 -m pip install -r requirements.txt
 RUN python3 -m pip install -r request_llm/requirements_chatglm.txt

docs/assets/custom.js

@@ -1,465 +0,0 @@
-
-// custom javascript here
-
-const MAX_HISTORY_LENGTH = 32;
-
-var key_down_history = [];
-var currentIndex = -1;
-var user_input_ta;
-
-var gradioContainer = null;
-var user_input_ta = null;
-var chat_txt = null;
-var userInfoDiv = null;
-var appTitleDiv = null;
-var chatbot = null;
-var chatbotWrap = null;
-var apSwitch = null;
-var messageBotDivs = null;
-var loginUserForm = null;
-var logginUser = null;
-
-var userLogged = false;
-var usernameGotten = false;
-var historyLoaded = false;
-
-var ga = document.getElementsByTagName("gradio-app");
-var targetNode = ga[0];
-var isInIframe = (window.self !== window.top);
-var language = navigator.language.slice(0,2);
-
-var forView_i18n = {
-    'zh': "仅供查看",
-    'en': "For viewing only",
-    'ja': "閲覧専用",
-    'fr': "Pour consultation seulement",
-    'es': "Solo para visualización",
-};
-
-var deleteConfirm_i18n_pref = {
-    'zh': "你真的要删除 ",
-    'en': "Are you sure you want to delete ",
-    'ja': "本当に ",
-};
-var deleteConfirm_i18n_suff = {
-    'zh': " 吗？",
-    'en': " ?",
-    'ja': " を削除してもよろしいですか？",
-};
-var deleteConfirm_msg_pref = "Are you sure you want to delete ";
-var deleteConfirm_msg_suff = " ?";
-
-// gradio 页面加载好了么??? 我能动你的元素了么??
-function gradioLoaded(mutations) {
-    for (var i = 0; i < mutations.length; i++) {
-        if (mutations[i].addedNodes.length) {
-            loginUserForm = document.querySelector(".gradio-container > .main > .wrap > .panel > .form")
-            gradioContainer = document.querySelector(".gradio-container");
-            chat_txt = document.getElementById('chat_txt');
-            userInfoDiv = document.getElementById("user_info");
-            appTitleDiv = document.getElementById("app_title");
-            chatbot = document.querySelector('#废弃');
-            chatbotWrap = document.querySelector('#废弃 > .wrap');
-            apSwitch = document.querySelector('.apSwitch input[type="checkbox"]');
-
-            if (loginUserForm) {
-                localStorage.setItem("userLogged", true);
-                userLogged = true;
-            }
-
-            if (gradioContainer && apSwitch) {  // gradioCainter 加载出来了没?
-                adjustDarkMode();
-            }
-            if (chat_txt) {  // chat_txt 加载出来了没?
-                selectHistory();
-            }
-            if (userInfoDiv && appTitleDiv) {  // userInfoDiv 和 appTitleDiv 加载出来了没?
-                if (!usernameGotten) {
-                    getUserInfo();
-                }
-                setTimeout(showOrHideUserInfo(), 2000);
-            }
-            if (chatbot) {  // chatbot 加载出来了没?
-                setChatbotHeight();
-            }
-            if (chatbotWrap) {
-                if (!historyLoaded) {
-                    loadHistoryHtml();
-                }
-                setChatbotScroll();
-            }
-        }
-    }
-}
-
-function webLocale() {
-    // console.log("webLocale", language);
-    if (forView_i18n.hasOwnProperty(language)) {
-        var forView = forView_i18n[language];
-        var forViewStyle = document.createElement('style');
-        forViewStyle.innerHTML = '.wrap>.history-message>:last-child::after { content: "' + forView + '"!important; }';
-        document.head.appendChild(forViewStyle);
-    }
-    if (deleteConfirm_i18n_pref.hasOwnProperty(language)) {
-        deleteConfirm_msg_pref = deleteConfirm_i18n_pref[language];
-        deleteConfirm_msg_suff = deleteConfirm_i18n_suff[language];
-    }
-}
-
-function showConfirmationDialog(a, file, c) {
-    if (file != "") {
-        var result = confirm(deleteConfirm_msg_pref + file + deleteConfirm_msg_suff);
-        if (result) {
-            return [a, file, c];
-        }
-    }
-    return [a, "CANCELED", c];
-}
-
-function selectHistory() {
-    user_input_ta = chat_txt.querySelector("textarea");
-    if (user_input_ta) {
-        observer.disconnect(); // 停止监听
-        // 在 textarea 上监听 keydown 事件
-        user_input_ta.addEventListener("keydown", function (event) {
-            var value = user_input_ta.value.trim();
-            // 判断按下的是否为方向键
-            if (event.code === 'ArrowUp' || event.code === 'ArrowDown') {
-                // 如果按下的是方向键，且输入框中有内容，且历史记录中没有该内容，则不执行操作
-                if (value && key_down_history.indexOf(value) === -1)
-                    return;
-                // 对于需要响应的动作，阻止默认行为。
-                event.preventDefault();
-                var length = key_down_history.length;
-                if (length === 0) {
-                    currentIndex = -1; // 如果历史记录为空，直接将当前选中的记录重置
-                    return;
-                }
-                if (currentIndex === -1) {
-                    currentIndex = length;
-                }
-                if (event.code === 'ArrowUp' && currentIndex > 0) {
-                    currentIndex--;
-                    user_input_ta.value = key_down_history[currentIndex];
-                } else if (event.code === 'ArrowDown' && currentIndex < length - 1) {
-                    currentIndex++;
-                    user_input_ta.value = key_down_history[currentIndex];
-                }
-                user_input_ta.selectionStart = user_input_ta.value.length;
-                user_input_ta.selectionEnd = user_input_ta.value.length;
-                const input_event = new InputEvent("input", { bubbles: true, cancelable: true });
-                user_input_ta.dispatchEvent(input_event);
-            } else if (event.code === "Enter") {
-                if (value) {
-                    currentIndex = -1;
-                    if (key_down_history.indexOf(value) === -1) {
-                        key_down_history.push(value);
-                        if (key_down_history.length > MAX_HISTORY_LENGTH) {
-                            key_down_history.shift();
-                        }
-                    }
-                }
-            }
-        });
-    }
-}
-
-var username = null;
-function getUserInfo() {
-    if (usernameGotten) {
-        return;
-    }
-    userLogged = localStorage.getItem('userLogged');
-    if (userLogged) {
-        username = userInfoDiv.innerText;
-        if (username) {
-            if (username.includes("getting user info…")) {
-                setTimeout(getUserInfo, 500);
-                return;
-            } else if (username === " ") {
-                localStorage.removeItem("username");
-                localStorage.removeItem("userLogged")
-                userLogged = false;
-                usernameGotten = true;
-                return;
-            } else {
-                username = username.match(/User:\s*(.*)/)[1] || username;
-                localStorage.setItem("username", username);
-                usernameGotten = true;
-                clearHistoryHtml();
-            }
-        }
-    }
-}
-
-function toggleUserInfoVisibility(shouldHide) {
-    if (userInfoDiv) {
-        if (shouldHide) {
-            userInfoDiv.classList.add("hideK");
-        } else {
-            userInfoDiv.classList.remove("hideK");
-        }
-    }
-}
-function showOrHideUserInfo() {
-    var sendBtn = document.getElementById("submit_btn");
-
-    // Bind mouse/touch events to show/hide user info
-    appTitleDiv.addEventListener("mouseenter", function () {
-        toggleUserInfoVisibility(false);
-    });
-    userInfoDiv.addEventListener("mouseenter", function () {
-        toggleUserInfoVisibility(false);
-    });
-    sendBtn.addEventListener("mouseenter", function () {
-        toggleUserInfoVisibility(false);
-    });
-
-    appTitleDiv.addEventListener("mouseleave", function () {
-        toggleUserInfoVisibility(true);
-    });
-    userInfoDiv.addEventListener("mouseleave", function () {
-        toggleUserInfoVisibility(true);
-    });
-    sendBtn.addEventListener("mouseleave", function () {
-        toggleUserInfoVisibility(true);
-    });
-
-    appTitleDiv.ontouchstart = function () {
-        toggleUserInfoVisibility(false);
-    };
-    userInfoDiv.ontouchstart = function () {
-        toggleUserInfoVisibility(false);
-    };
-    sendBtn.ontouchstart = function () {
-        toggleUserInfoVisibility(false);
-    };
-
-    appTitleDiv.ontouchend = function () {
-        setTimeout(function () {
-            toggleUserInfoVisibility(true);
-        }, 3000);
-    };
-    userInfoDiv.ontouchend = function () {
-        setTimeout(function () {
-            toggleUserInfoVisibility(true);
-        }, 3000);
-    };
-    sendBtn.ontouchend = function () {
-        setTimeout(function () {
-            toggleUserInfoVisibility(true);
-        }, 3000); // Delay 1 second to hide user info
-    };
-
-    // Hide user info after 2 second
-    setTimeout(function () {
-        toggleUserInfoVisibility(true);
-    }, 2000);
-}
-
-function toggleDarkMode(isEnabled) {
-    if (isEnabled) {
-        document.body.classList.add("dark");
-        document.body.style.setProperty("background-color", "var(--neutral-950)", "important");
-    } else {
-        document.body.classList.remove("dark");
-        document.body.style.backgroundColor = "";
-    }
-}
-function adjustDarkMode() {
-    const darkModeQuery = window.matchMedia("(prefers-color-scheme: dark)");
-
-    // 根据当前颜色模式设置初始状态
-    apSwitch.checked = darkModeQuery.matches;
-    toggleDarkMode(darkModeQuery.matches);
-    // 监听颜色模式变化
-    darkModeQuery.addEventListener("change", (e) => {
-        apSwitch.checked = e.matches;
-        toggleDarkMode(e.matches);
-    });
-    // apSwitch = document.querySelector('.apSwitch input[type="checkbox"]');
-    apSwitch.addEventListener("change", (e) => {
-        toggleDarkMode(e.target.checked);
-    });
-}
-
-function setChatbotHeight() {
-    const screenWidth = window.innerWidth;
-    const statusDisplay = document.querySelector('#status_display');
-    const statusDisplayHeight = statusDisplay ? statusDisplay.offsetHeight : 0;
-    const wrap = chatbot.querySelector('.wrap');
-    const vh = window.innerHeight * 0.01;
-    document.documentElement.style.setProperty('--vh', `${vh}px`);
-    if (isInIframe) {
-        chatbot.style.height = `700px`;
-        wrap.style.maxHeight = `calc(700px - var(--line-sm) * 1rem - 2 * var(--block-label-margin))`
-    } else {
-        if (screenWidth <= 320) {
-            chatbot.style.height = `calc(var(--vh, 1vh) * 100 - ${statusDisplayHeight + 150}px)`;
-            wrap.style.maxHeight = `calc(var(--vh, 1vh) * 100 - ${statusDisplayHeight + 150}px - var(--line-sm) * 1rem - 2 * var(--block-label-margin))`;
-        } else if (screenWidth <= 499) {
-            chatbot.style.height = `calc(var(--vh, 1vh) * 100 - ${statusDisplayHeight + 100}px)`;
-            wrap.style.maxHeight = `calc(var(--vh, 1vh) * 100 - ${statusDisplayHeight + 100}px - var(--line-sm) * 1rem - 2 * var(--block-label-margin))`;
-        } else {
-            chatbot.style.height = `calc(var(--vh, 1vh) * 100 - ${statusDisplayHeight + 160}px)`;
-            wrap.style.maxHeight = `calc(var(--vh, 1vh) * 100 - ${statusDisplayHeight + 160}px - var(--line-sm) * 1rem - 2 * var(--block-label-margin))`;
-        }
-    }
-}
-function setChatbotScroll() {
-    var scrollHeight = chatbotWrap.scrollHeight;
-    chatbotWrap.scrollTo(0,scrollHeight)
-}
-var rangeInputs = null;
-var numberInputs = null;
-function setSlider() {
-    rangeInputs = document.querySelectorAll('input[type="range"]');
-    numberInputs = document.querySelectorAll('input[type="number"]')
-    setSliderRange();
-    rangeInputs.forEach(rangeInput => {
-        rangeInput.addEventListener('input', setSliderRange);
-    });
-    numberInputs.forEach(numberInput => {
-        numberInput.addEventListener('input', setSliderRange);
-    })
-}
-function setSliderRange() {
-    var range = document.querySelectorAll('input[type="range"]');
-    range.forEach(range => {
-        range.style.backgroundSize = (range.value - range.min) / (range.max - range.min) * 100 + '% 100%';
-    });
-}
-
-function addChuanhuButton(botElement) {
-    var rawMessage = null;
-    var mdMessage = null;
-    rawMessage = botElement.querySelector('.raw-message');
-    mdMessage = botElement.querySelector('.md-message');
-    if (!rawMessage) {
-        var buttons = botElement.querySelectorAll('button.chuanhu-btn');
-        for (var i = 0; i < buttons.length; i++) {
-            buttons[i].parentNode.removeChild(buttons[i]);
-        }
-        return;
-    }
-    var copyButton = null;
-    var toggleButton = null;
-    copyButton = botElement.querySelector('button.copy-bot-btn');
-    toggleButton = botElement.querySelector('button.toggle-md-btn');
-    if (copyButton) copyButton.remove();
-    if (toggleButton) toggleButton.remove();
-
-    // Copy bot button
-    var copyButton = document.createElement('button');
-    copyButton.classList.add('chuanhu-btn');
-    copyButton.classList.add('copy-bot-btn');
-    copyButton.setAttribute('aria-label', 'Copy');
-    copyButton.innerHTML = copyIcon;
-    copyButton.addEventListener('click', () => {
-        const textToCopy = rawMessage.innerText;
-        navigator.clipboard
-            .writeText(textToCopy)
-            .then(() => {
-                copyButton.innerHTML = copiedIcon;
-                setTimeout(() => {
-                    copyButton.innerHTML = copyIcon;
-                }, 1500);
-            })
-            .catch(() => {
-                console.error("copy failed");
-            });
-    });
-    botElement.appendChild(copyButton);
-
-    // Toggle button
-    var toggleButton = document.createElement('button');
-    toggleButton.classList.add('chuanhu-btn');
-    toggleButton.classList.add('toggle-md-btn');
-    toggleButton.setAttribute('aria-label', 'Toggle');
-    var renderMarkdown = mdMessage.classList.contains('hideM');
-    toggleButton.innerHTML = renderMarkdown ? mdIcon : rawIcon;
-    toggleButton.addEventListener('click', () => {
-        renderMarkdown = mdMessage.classList.contains('hideM');
-        if (renderMarkdown){
-            renderMarkdownText(botElement);
-            toggleButton.innerHTML=rawIcon;
-        } else {
-            removeMarkdownText(botElement);
-            toggleButton.innerHTML=mdIcon;
-        }
-    });
-    botElement.insertBefore(toggleButton, copyButton);
-}
-
-function renderMarkdownText(message) {
-    var mdDiv = message.querySelector('.md-message');
-    if (mdDiv) mdDiv.classList.remove('hideM');
-    var rawDiv = message.querySelector('.raw-message');
-    if (rawDiv) rawDiv.classList.add('hideM');
-}
-function removeMarkdownText(message) {
-    var rawDiv = message.querySelector('.raw-message');
-    if (rawDiv) rawDiv.classList.remove('hideM');
-    var mdDiv = message.querySelector('.md-message');
-    if (mdDiv) mdDiv.classList.add('hideM');
-}
-
-let timeoutId;
-let isThrottled = false;
-var mmutation
-// 监听所有元素中 bot message 的变化，为 bot 消息添加复制按钮。
-var mObserver = new MutationObserver(function (mutationsList) {
-    for (mmutation of mutationsList) {
-        if (mmutation.type === 'childList') {
-            for (var node of mmutation.addedNodes) {
-                if (node.nodeType === 1 && node.classList.contains('message') && node.getAttribute('data-testid') === 'bot') {
-                    saveHistoryHtml();
-                    document.querySelectorAll('#废弃>.wrap>.message-wrap .message.bot').forEach(addChuanhuButton);
-                }
-                if (node.tagName === 'INPUT' && node.getAttribute('type') === 'range') {
-                    setSlider();
-                }
-            }
-            for (var node of mmutation.removedNodes) {
-                if (node.nodeType === 1 && node.classList.contains('message') && node.getAttribute('data-testid') === 'bot') {
-                    saveHistoryHtml();
-                    document.querySelectorAll('#废弃>.wrap>.message-wrap .message.bot').forEach(addChuanhuButton);
-                }
-            }
-        } else if (mmutation.type === 'attributes') {
-            if (mmutation.target.nodeType === 1 && mmutation.target.classList.contains('message') && mmutation.target.getAttribute('data-testid') === 'bot') {
-                if (isThrottled) break; // 为了防止重复不断疯狂渲染，加上等待_(:з」∠)_
-                isThrottled = true;
-                clearTimeout(timeoutId);
-                timeoutId = setTimeout(() => {
-                    isThrottled = false;
-                    document.querySelectorAll('#废弃>.wrap>.message-wrap .message.bot').forEach(addChuanhuButton);
-                    saveHistoryHtml();
-                }, 500);
-            }
-        }
-    }
-});
-mObserver.observe(document.documentElement, { attributes: true, childList: true, subtree: true });
-
-
-// 监视页面内部 DOM 变动
-var observer = new MutationObserver(function (mutations) {
-    gradioLoaded(mutations);
-});
-observer.observe(targetNode, { childList: true, subtree: true });
-
-// 监视页面变化
-window.addEventListener("DOMContentLoaded", function () {
-    isInIframe = (window.self !== window.top);
-    historyLoaded = false;
-});
-window.addEventListener('resize', setChatbotHeight);
-window.addEventListener('scroll', setChatbotHeight);
-window.matchMedia("(prefers-color-scheme: dark)").addEventListener("change", adjustDarkMode);
-
-// button svg code
-const copyIcon   = '<span><svg stroke="currentColor" fill="none" stroke-width="2" viewBox="0 0 24 24" stroke-linecap="round" stroke-linejoin="round" height=".8em" width=".8em" xmlns="http://www.w3.org/2000/svg"><rect x="9" y="9" width="13" height="13" rx="2" ry="2"></rect><path d="M5 15H4a2 2 0 0 1-2-2V4a2 2 0 0 1 2-2h9a2 2 0 0 1 2 2v1"></path></svg></span>';
-const copiedIcon = '<span><svg stroke="currentColor" fill="none" stroke-width="2" viewBox="0 0 24 24" stroke-linecap="round" stroke-linejoin="round" height=".8em" width=".8em" xmlns="http://www.w3.org/2000/svg"><polyline points="20 6 9 17 4 12"></polyline></svg></span>';
-const mdIcon     = '<span><svg stroke="currentColor" fill="none" stroke-width="1" viewBox="0 0 14 18" stroke-linecap="round" stroke-linejoin="round" height=".8em" width=".8em" xmlns="http://www.w3.org/2000/svg"><g transform-origin="center" transform="scale(0.85)"><path d="M1.5,0 L12.5,0 C13.3284271,-1.52179594e-16 14,0.671572875 14,1.5 L14,16.5 C14,17.3284271 13.3284271,18 12.5,18 L1.5,18 C0.671572875,18 1.01453063e-16,17.3284271 0,16.5 L0,1.5 C-1.01453063e-16,0.671572875 0.671572875,1.52179594e-16 1.5,0 Z" stroke-width="1.8"></path><line x1="3.5" y1="3.5" x2="10.5" y2="3.5"></line><line x1="3.5" y1="6.5" x2="8" y2="6.5"></line></g><path d="M4,9 L10,9 C10.5522847,9 11,9.44771525 11,10 L11,13.5 C11,14.0522847 10.5522847,14.5 10,14.5 L4,14.5 C3.44771525,14.5 3,14.0522847 3,13.5 L3,10 C3,9.44771525 3.44771525,9 4,9 Z" stroke="none" fill="currentColor"></path></svg></span>';
-const rawIcon    = '<span><svg stroke="currentColor" fill="none" stroke-width="1.8" viewBox="0 0 18 14" stroke-linecap="round" stroke-linejoin="round" height=".8em" width=".8em" xmlns="http://www.w3.org/2000/svg"><g transform-origin="center" transform="scale(0.85)"><polyline points="4 3 0 7 4 11"></polyline><polyline points="14 3 18 7 14 11"></polyline><line x1="12" y1="0" x2="6" y2="14"></line></g></svg></span>';

docs/assets/external-scripts.js

@@ -1,2 +0,0 @@
-
-// external javascript here

docs/assets/html/appearance_switcher.html

@@ -1,8 +0,0 @@
-<div style="display: flex; justify-content: space-between;">
-    <span>
-        <label class="apSwitch" for="checkbox">
-            <input type="checkbox" id="checkbox">
-            <div class="apSlider"></div>
-        </label>
-    </span>
-</div>

docs/assets/html/billing_info.html

@@ -1,9 +0,0 @@
-<b>{label}</b>
-<div class="progress-bar">
-    <div class="progress" style="width: {usage_percent}%;">
-        <span class="progress-text">{usage_percent}%</span>
-    </div>
-</div>
-<div style="display: flex; justify-content: space-between;">
-    <span>${rounded_usage}</span><span>${usage_limit}</span>
-</div>

docs/assets/html/footer.html

@@ -1 +0,0 @@
-<div class="versions">{versions}</div>

docs/test_markdown_format.py

@@ -49,7 +49,7 @@ def markdown_convertion(txt):
     """
     将Markdown格式的文本转换为HTML格式。如果包含数学公式，则先将公式转换为HTML格式。
     """
-    pre = '<div class="md-message">'
+    pre = '<div class="markdown-body">'
     suf = '</div>'
     if txt.startswith(pre) and txt.endswith(suf):
         # print('警告，输入了已经经过转化的字符串，二次转化可能出问题')

docs/translate_english.json

@@ -265,7 +265,7 @@
     "例如chatglm&gpt-3.5-turbo&api2d-gpt-4": "e.g. chatglm&gpt-3.5-turbo&api2d-gpt-4",
     "先切换模型到openai或api2d": "Switch the model to openai or api2d first",
     "在这里输入分辨率": "Enter the resolution here",
-    "如'256x256', '512x512', '1024x1024'": "e.g. '256x256', '512x512', '1024x1024'",
+    "如256x256": "e.g. 256x256",
     "默认": "Default",
     "建议您复制一个config_private.py放自己的秘密": "We suggest you to copy a config_private.py file to keep your secrets, such as API and proxy URLs, from being accidentally uploaded to Github and seen by others.",
     "如API和代理网址": "Such as API and proxy URLs",
@@ -1667,5 +1667,423 @@
     "段音频的主要内容": "The main content of the segment audio is",
     "z$ 分别是空间直角坐标系中的三个坐标": "z$, respectively, are the three coordinates in the spatial rectangular coordinate system",
     "这个是怎么识别的呢我也不清楚": "I'm not sure how this is recognized",
-    "从现在起": "From now on"
+    "从现在起": "From now on",
+    "连接bing搜索回答问题": "ConnectBingSearchAnswerQuestion",
+    "联网的ChatGPT_bing版": "OnlineChatGPT_BingEdition",
+    "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
+    "Langchain知识库": "LangchainKnowledgeBase",
+    "Latex英文纠错加PDF对比": "CorrectEnglishInLatexWithPDFComparison",
+    "Latex输出PDF结果": "OutputPDFFromLatex",
+    "Latex翻译中文并重新编译PDF": "TranslateChineseToEnglishInLatexAndRecompilePDF",
+    "sprint亮靛": "SprintIndigo",
+    "寻找Latex主文件": "FindLatexMainFile",
+    "专业词汇声明": "ProfessionalTerminologyDeclaration",
+    "Latex精细分解与转化": "DecomposeAndConvertLatex",
+    "编译Latex": "CompileLatex",
+    "如果您是论文原作者": "If you are the original author of the paper",
+    "正在编译对比PDF": "Compiling the comparison PDF",
+    "将 \\include 命令转换为 \\input 命令": "Converting the \\include command to the \\input command",
+    "取评分最高者返回": "Returning the highest-rated one",
+    "不要修改!! 高危设置！通过修改此设置": "Do not modify!! High-risk setting! By modifying this setting",
+    "Tex源文件缺失！": "Tex source file is missing!",
+    "6.25 加入判定latex模板的代码": "Added code to determine the latex template on June 25",
+    "正在精细切分latex文件": "Finely splitting the latex file",
+    "获取response失败": "Failed to get response",
+    "手动指定语言": "Manually specify the language",
+    "输入arxivID": "Enter arxivID",
+    "对输入的word文档进行摘要生成": "Generate a summary of the input word document",
+    "将指定目录下的PDF文件从英文翻译成中文": "Translate PDF files from English to Chinese in the specified directory",
+    "如果分析错误": "If the analysis is incorrect",
+    "尝试第": "Try the",
+    "用户填3": "User fills in 3",
+    "请在此处追加更细致的矫错指令": "Please append more detailed correction instructions here",
+    "为了防止大语言模型的意外谬误产生扩散影响": "To prevent the accidental spread of errors in large language models",
+    "前面是中文冒号": "The colon before is in Chinese",
+    "内含已经翻译的Tex文档": "Contains a Tex document that has been translated",
+    "成功啦": "Success!",
+    "刷新页面即可以退出UpdateKnowledgeArchive模式": "Refresh the page to exit UpdateKnowledgeArchive mode",
+    "或者不在环境变量PATH中": "Or not in the environment variable PATH",
+    "--读取文件": "--Read the file",
+    "才能继续下面的步骤": "To continue with the next steps",
+    "代理数据解析失败": "Proxy data parsing failed",
+    "详见项目主README.md": "See the main README.md of the project for details",
+    "临时存储用于调试": "Temporarily stored for debugging",
+    "屏蔽空行和太短的句子": "Filter out empty lines and sentences that are too short",
+    "gpt 多线程请求": "GPT multi-threaded request",
+    "编译已经开始": "Compilation has started",
+    "无法找到一个主Tex文件": "Cannot find a main Tex file",
+    "修复括号": "Fix parentheses",
+    "请您不要删除或修改这行警告": "Please do not delete or modify this warning",
+    "请登录OpenAI查看详情 https": "Please log in to OpenAI to view details at https",
+    "调用函数": "Call a function",
+    "请查看终端的输出或耐心等待": "Please check the output in the terminal or wait patiently",
+    "LatexEnglishCorrection+高亮修正位置": "Latex English correction + highlight correction position",
+    "行": "line",
+    "Newbing 请求失败": "Newbing request failed",
+    "转化PDF编译是否成功": "Check if the conversion to PDF and compilation were successful",
+    "建议更换代理协议": "Recommend changing the proxy protocol",
+    "========================================= 插件主程序1 =====================================================": "========================================= Plugin Main Program 1 =====================================================",
+    "终端": "terminal",
+    "请先上传文件素材": "Please upload file materials first",
+    "前面是中文逗号": "There is a Chinese comma in front",
+    "请尝试把以下指令复制到高级参数区": "Please try copying the following instructions to the advanced parameters section",
+    "翻译-": "Translation -",
+    "请耐心等待": "Please be patient",
+    "将前后断行符脱离": "Remove line breaks before and after",
+    "json等": "JSON, etc.",
+    "生成中文PDF": "Generate Chinese PDF",
+    "用红色标注处保留区": "Use red color to highlight the reserved area",
+    "对比PDF编译是否成功": "Compare if the PDF compilation was successful",
+    "回答完问题后": "After answering the question",
+    "其他操作系统表现未知": "Unknown performance on other operating systems",
+    "-构建知识库": "Build knowledge base",
+    "还原原文": "Restore original text",
+    "或者重启之后再度尝试": "Or try again after restarting",
+    "免费": "Free",
+    "仅在Windows系统进行了测试": "Tested only on Windows system",
+    "欢迎加REAME中的QQ联系开发者": "Feel free to contact the developer via QQ in REAME",
+    "当前知识库内的有效文件": "Valid files in the current knowledge base",
+    "您可以到Github Issue区": "You can go to the Github Issue area",
+    "刷新Gradio前端界面": "Refresh the Gradio frontend interface",
+    "吸收title与作者以上的部分": "Include the title and the above part of the author",
+    "给出一些判定模板文档的词作为扣分项": "Provide some words in the template document as deduction items",
+    "--读取参数": "-- Read parameters",
+    "然后进行问答": "And then perform question-answering",
+    "根据自然语言执行插件命令": "Execute plugin commands based on natural language",
+    "*{\\scriptsize\\textbf{警告": "*{\\scriptsize\\textbf{Warning",
+    "但请查收结果": "But please check the results",
+    "翻译内容可靠性无保障": "No guarantee of translation accuracy",
+    "寻找主文件": "Find the main file",
+    "消耗时间的函数": "Time-consuming function",
+    "当前语言模型温度设定": "Current language model temperature setting",
+    "这需要一段时间计算": "This requires some time to calculate",
+    "为啥chatgpt会把cite里面的逗号换成中文逗号呀": "Why does ChatGPT change commas inside 'cite' to Chinese commas?",
+    "发现已经存在翻译好的PDF文档": "Found an already translated PDF document",
+    "待提取的知识库名称id": "Knowledge base name ID to be extracted",
+    "文本碎片重组为完整的tex片段": "Reassemble text fragments into complete tex fragments",
+    "注意事项": "Notes",
+    "参数说明": "Parameter description",
+    "或代理节点": "Or proxy node",
+    "构建知识库": "Building knowledge base",
+    "报错信息如下. 如果是与网络相关的问题": "Error message as follows. If it is related to network issues",
+    "功能描述": "Function description",
+    "禁止移除或修改此警告": "Removal or modification of this warning is prohibited",
+    "Arixv翻译": "Arixv translation",
+    "读取优先级": "Read priority",
+    "包含documentclass关键字": "Contains the documentclass keyword",
+    "根据文本使用GPT模型生成相应的图像": "Generate corresponding images using GPT model based on the text",
+    "图像生成所用到的提示文本": "Prompt text used for image generation",
+    "Your account is not active. OpenAI以账户失效为由": "Your account is not active. OpenAI states that it is due to account expiration",
+    "快捷的调试函数": "Convenient debugging function",
+    "在多Tex文档中": "In multiple Tex documents",
+    "因此选择GenerateImage函数": "Therefore, choose the GenerateImage function",
+    "当前工作路径为": "The current working directory is",
+    "实际得到格式": "Obtained format in reality",
+    "这段代码定义了一个名为TempProxy的空上下文管理器": "This code defines an empty context manager named TempProxy",
+    "吸收其他杂项": "Absorb other miscellaneous items",
+    "请输入要翻译成哪种语言": "Please enter which language to translate into",
+    "的单词": "of the word",
+    "正在尝试自动安装": "Attempting automatic installation",
+    "如果有必要": "If necessary",
+    "开始下载": "Start downloading",
+    "项目Github地址 \\url{https": "Project GitHub address \\url{https",
+    "将根据报错信息修正tex源文件并重试": "The Tex source file will be corrected and retried based on the error message",
+    "发送至azure openai api": "Send to Azure OpenAI API",
+    "吸收匿名公式": "Absorb anonymous formulas",
+    "用该压缩包+ConversationHistoryArchive进行反馈": "Provide feedback using the compressed package + ConversationHistoryArchive",
+    "需要特殊依赖": "Requires special dependencies",
+    "还原部分原文": "Restore part of the original text",
+    "构建完成": "Build completed",
+    "解析arxiv网址失败": "Failed to parse arXiv URL",
+    "输入问题后点击该插件": "Click the plugin after entering the question",
+    "请求子进程": "Requesting subprocess",
+    "请务必用 pip install -r requirements.txt 指令安装依赖": "Please make sure to install the dependencies using the 'pip install -r requirements.txt' command",
+    "如果程序停顿5分钟以上": "If the program pauses for more than 5 minutes",
+    "转化PDF编译已经成功": "Conversion to PDF compilation was successful",
+    "虽然PDF生成失败了": "Although PDF generation failed",
+    "分析上述回答": "Analyze the above answer",
+    "吸收在42行以内的begin-end组合": "Absorb the begin-end combination within 42 lines",
+    "推荐http": "Recommend http",
+    "Latex没有安装": "Latex is not installed",
+    "用latex编译为PDF对修正处做高亮": "Compile to PDF using LaTeX and highlight the corrections",
+    "reverse 操作必须放在最后": "'reverse' operation must be placed at the end",
+    "AZURE OPENAI API拒绝了请求": "AZURE OPENAI API rejected the request",
+    "该项目的Latex主文件是": "The main LaTeX file of this project is",
+    "You are associated with a deactivated account. OpenAI以账户失效为由": "You are associated with a deactivated account. OpenAI considers it as an account expiration",
+    "它*必须*被包含在AVAIL_LLM_MODELS列表中": "It *must* be included in the AVAIL_LLM_MODELS list",
+    "未知指令": "Unknown command",
+    "尝试执行Latex指令失败": "Failed to execute the LaTeX command",
+    "摘要生成后的文档路径": "Path of the document after summary generation",
+    "GPT结果已输出": "GPT result has been outputted",
+    "使用Newbing": "Using Newbing",
+    "其他模型转化效果未知": "Unknown conversion effect of other models",
+    "P.S. 但愿没人把latex模板放在里面传进来": "P.S. Hopefully, no one passes a LaTeX template in it",
+    "定位主Latex文件": "Locate the main LaTeX file",
+    "后面是英文冒号": "English colon follows",
+    "文档越长耗时越长": "The longer the document, the longer it takes.",
+    "压缩包": "Compressed file",
+    "但通常不会出现在正文": "But usually does not appear in the body.",
+    "正在预热文本向量化模组": "Preheating text vectorization module",
+    "5刀": "5 dollars",
+    "提问吧! 但注意": "Ask questions! But be careful",
+    "发送至AZURE OPENAI API": "Send to AZURE OPENAI API",
+    "请仔细鉴别并以原文为准": "Please carefully verify and refer to the original text",
+    "如果需要使用AZURE 详情请见额外文档 docs\\use_azure.md": "If you need to use AZURE, please refer to the additional document docs\\use_azure.md for details",
+    "使用正则表达式查找半行注释": "Use regular expressions to find inline comments",
+    "只有第二步成功": "Only the second step is successful",
+    "P.S. 顺便把CTEX塞进去以支持中文": "P.S. By the way, include CTEX to support Chinese",
+    "安装方法https": "Installation method: https",
+    "则跳过GPT请求环节": "Then skip the GPT request process",
+    "请切换至“UpdateKnowledgeArchive”插件进行知识库访问": "Please switch to the 'UpdateKnowledgeArchive' plugin for knowledge base access",
+    "=================================== 工具函数 ===============================================": "=================================== Utility functions ===============================================",
+    "填入azure openai api的密钥": "Fill in the Azure OpenAI API key",
+    "上传Latex压缩包": "Upload LaTeX compressed file",
+    "远程云服务器部署": "Deploy to remote cloud server",
+    "用黑色标注转换区": "Use black color to annotate the conversion area",
+    "音频文件的路径": "Path to the audio file",
+    "必须包含documentclass": "Must include documentclass",
+    "再列出用户可能提出的三个问题": "List three more questions that the user might ask",
+    "根据需要切换prompt": "Switch the prompt as needed",
+    "将文件复制一份到下载区": "Make a copy of the file in the download area",
+    "次编译": "Second compilation",
+    "Latex文件融合完成": "LaTeX file merging completed",
+    "返回": "Return",
+    "后面是英文逗号": "Comma after this",
+    "对不同latex源文件扣分": "Deduct points for different LaTeX source files",
+    "失败啦": "Failed",
+    "编译BibTex": "Compile BibTeX",
+    "Linux下必须使用Docker安装": "Must install using Docker on Linux",
+    "报错信息": "Error message",
+    "删除或修改歧义文件": "Delete or modify ambiguous files",
+    "-预热文本向量化模组": "- Preheating text vectorization module",
+    "将每次对话记录写入Markdown格式的文件中": "Write each conversation record into a file in Markdown format",
+    "其他类型文献转化效果未知": "Unknown conversion effect for other types of literature",
+    "获取线程锁": "Acquire thread lock",
+    "使用英文": "Use English",
+    "如果存在调试缓存文件": "If there is a debug cache file",
+    "您需要首先调用构建知识库": "You need to call the knowledge base building first",
+    "原始PDF编译是否成功": "Whether the original PDF compilation is successful",
+    "生成 azure openai api请求": "Generate Azure OpenAI API requests",
+    "正在编译PDF": "Compiling PDF",
+    "仅调试": "Debug only",
+    "========================================= 插件主程序2 =====================================================": "========================================= Plugin Main Program 2 =====================================================",
+    "多线程翻译开始": "Multithreaded translation begins",
+    "出问题了": "There is a problem",
+    "版权归原文作者所有": "Copyright belongs to the original author",
+    "当前大语言模型": "Current large language model",
+    "目前对机器学习类文献转化效果最好": "Currently, the best conversion effect for machine learning literature",
+    "这个paper有个input命令文件名大小写错误！": "This paper has an input command with a filename case error!",
+    "期望格式例如": "Expected format, for example",
+    "解决部分词汇翻译不准确的问题": "Resolve the issue of inaccurate translation for some terms",
+    "待注入的知识库名称id": "Name/ID of the knowledge base to be injected",
+    "精细切分latex文件": "Fine-grained segmentation of LaTeX files",
+    "永远给定None": "Always given None",
+    "work_folder = Latex预处理": "work_folder = LaTeX preprocessing",
+    "请直接去该路径下取回翻译结果": "Please directly go to the path to retrieve the translation results",
+    "寻找主tex文件": "Finding the main .tex file",
+    "模型参数": "Model parameters",
+    "返回找到的第一个": "Return the first one found",
+    "编译转化后的PDF": "Compile the converted PDF",
+    "\\SEAFILE_LOCALŅ03047\\我的资料库\\music\\Akie秋绘-未来轮廓.mp3": "\\SEAFILE_LOCALŅ03047\\My Library\\music\\Akie秋绘-未来轮廓.mp3",
+    "拆分过长的latex片段": "Splitting overly long LaTeX fragments",
+    "没有找到任何可读取文件": "No readable files found",
+    "暗色模式 / 亮色模式": "Dark mode / Light mode",
+    "检测到arxiv文档连接": "Detected arXiv document link",
+    "此插件Windows支持最佳": "This plugin has best support for Windows",
+    "from crazy_functions.虚空终端 import 终端": "from crazy_functions.null_terminal import Terminal",
+    "本地论文翻译": "Local paper translation",
+    "输出html调试文件": "Output HTML debugging file",
+    "以下所有配置也都支持利用环境变量覆写": "All the following configurations can also be overridden using environment variables",
+    "PDF文件所在的路径": "Path of the PDF file",
+    "也是可读的": "It is also readable",
+    "将消耗较长时间下载中文向量化模型": "Downloading Chinese vectorization model will take a long time",
+    "环境变量配置格式见docker-compose.yml": "See docker-compose.yml for the format of environment variable configuration",
+    "编译文献交叉引用": "Compile bibliographic cross-references",
+    "默认为default": "Default is 'default'",
+    "或者使用此插件继续上传更多文件": "Or use this plugin to continue uploading more files",
+    "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": "This PDF is generated by the GPT-Academic open-source project using a large language model + LaTeX translation plugin",
+    "使用latexdiff生成论文转化前后对比": "Use latexdiff to generate before and after comparison of paper transformation",
+    "正在编译PDF文档": "Compiling PDF document",
+    "读取config.py文件中关于AZURE OPENAI API的信息": "Read the information about AZURE OPENAI API from the config.py file",
+    "配置教程&视频教程": "Configuration tutorial & video tutorial",
+    "临时地启动代理网络": "Temporarily start proxy network",
+    "临时地激活代理网络": "Temporarily activate proxy network",
+    "功能尚不稳定": "Functionality is unstable",
+    "默认为Chinese": "Default is Chinese",
+    "请查收结果": "Please check the results",
+    "将 chatglm 直接对齐到 chatglm2": "Align chatglm directly to chatglm2",
+    "中读取数据构建知识库": "Build a knowledge base by reading data in",
+    "用于给一小段代码上代理": "Used to proxy a small piece of code",
+    "分析结果": "Analysis results",
+    "依赖不足": "Insufficient dependencies",
+    "Markdown翻译": "Markdown translation",
+    "除非您是论文的原作者": "Unless you are the original author of the paper",
+    "test_LangchainKnowledgeBase读取": "test_LangchainKnowledgeBase read",
+    "将多文件tex工程融合为一个巨型tex": "Merge multiple tex projects into one giant tex",
+    "吸收iffalse注释": "Absorb iffalser comments",
+    "您接下来不能再使用其他插件了": "You can no longer use other plugins next",
+    "正在构建知识库": "Building knowledge base",
+    "需Latex": "Requires Latex",
+    "即找不到": "That is not found",
+    "保证括号正确": "Ensure parentheses are correct",
+    "= 2 通过一些Latex模板中常见": "= 2 through some common Latex templates",
+    "请立即终止程序": "Please terminate the program immediately",
+    "解压失败! 需要安装pip install rarfile来解压rar文件": "Decompression failed! Install 'pip install rarfile' to decompress rar files",
+    "请在此处给出自定义翻译命令": "Please provide custom translation command here",
+    "解压失败! 需要安装pip install py7zr来解压7z文件": "Decompression failed! Install 'pip install py7zr' to decompress 7z files",
+    "执行错误": "Execution error",
+    "目前仅支持GPT3.5/GPT4": "Currently only supports GPT3.5/GPT4",
+    "P.S. 顺便把Latex的注释去除": "P.S. Also remove comments from Latex",
+    "写出文件": "Write out the file",
+    "当前报错的latex代码处于第": "The current error in the LaTeX code is on line",
+    "主程序即将开始": "Main program is about to start",
+    "详情信息见requirements.txt": "See details in requirements.txt",
+    "释放线程锁": "Release thread lock",
+    "由于最为关键的转化PDF编译失败": "Due to the critical failure of PDF conversion and compilation",
+    "即将退出": "Exiting soon",
+    "尝试下载": "Attempting to download",
+    "删除整行的空注释": "Remove empty comments from the entire line",
+    "也找不到": "Not found either",
+    "从一批文件": "From a batch of files",
+    "编译结束": "Compilation finished",
+    "调用缓存": "Calling cache",
+    "只有GenerateImage和生成图像相关": "Only GenerateImage and image generation related",
+    "待处理的word文档路径": "Path of the word document to be processed",
+    "是否在提交时自动清空输入框": "Whether to automatically clear the input box upon submission",
+    "检查结果": "Check the result",
+    "生成时间戳": "Generate a timestamp",
+    "编译原始PDF": "Compile the original PDF",
+    "填入ENGINE": "Fill in ENGINE",
+    "填入api版本": "Fill in the API version",
+    "中文Bing版": "Chinese Bing version",
+    "当前支持的格式包括": "Currently supported formats include",
+    "交互功能模板函数": "InteractiveFunctionTemplateFunction",
+    "交互功能函数模板": "InteractiveFunctionFunctionTemplate",
+    "语音助手": "VoiceAssistant",
+    "微调数据集生成": "FineTuneDatasetGeneration",
+    "chatglm微调工具": "ChatGLMFineTuningTool",
+    "启动微调": "StartFineTuning",
+    "请讲话": "Please speak",
+    "正在听您讲话": "Listening to you",
+    "对这个人外貌、身处的环境、内心世界、过去经历进行描写": "Describe the appearance, environment, inner world, and past experiences of this person",
+    "请向下翻": "Please scroll down",
+    "实时音频采集": "Real-time audio collection",
+    "找不到": "Not found",
+    "在一个异步线程中采集音频": "Collect audio in an asynchronous thread",
+    "azure和api2d请求源": "Azure and API2D request source",
+    "等待ChatGLMFT响应中": "Waiting for ChatGLMFT response",
+    "如果使用ChatGLM2微调模型": "If using ChatGLM2 fine-tuning model",
+    "把文件复制过去": "Copy the file over",
+    "可选": "Optional",
+    "ChatGLMFT响应异常": "ChatGLMFT response exception",
+    "上传本地文件/压缩包供函数插件调用": "Upload local files/compressed packages for function plugin calls",
+    "例如 f37f30e0f9934c34a992f6f64f7eba4f": "For example, f37f30e0f9934c34a992f6f64f7eba4f",
+    "正在等您说完问题": "Waiting for you to finish the question",
+    "解除插件状态": "Release plugin status",
+    "详情见https": "See details at https",
+    "避免线程阻塞": "Avoid thread blocking",
+    "先上传数据集": "Upload dataset first",
+    "请直接提交即可": "Submit directly",
+    "Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数": "Call ChatGLMFT fail, cannot load ChatGLMFT parameters",
+    "插件可读取“输入区”文本/路径作为参数": "The plugin can read text/path in the input area as parameters",
+    "给出指令": "Give instructions",
+    "暂不提交": "Do not submit for now",
+    "如 绿帽子*深蓝色衬衫*黑色运动裤": "E.g. green hat * dark blue shirt * black sports pants",
+    "阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https": "Aliyun real-time speech recognition has high configuration difficulty and is only recommended for advanced users. Refer to https",
+    "ChatGLMFT尚未加载": "ChatGLMFT has not been loaded yet",
+    "输入 clear 以清空对话历史": "Enter 'clear' to clear the conversation history",
+    "可以将自身的状态存储到cookie中": "You can store your own status in cookies",
+    "填入你亲手写的部署名": "Fill in the deployment name you wrote by yourself",
+    "该选项即将被弃用": "This option will be deprecated soon",
+    "代理网络配置": "Proxy network configuration",
+    "每秒采样数量": "Number of samples per second",
+    "使用时": "When using",
+    "想象一个穿着者": "Imagine a wearer",
+    "如果已经存在": "If it already exists",
+    "例如您可以将以下命令复制到下方": "For example, you can copy the following command below",
+    "正在锁定插件": "Locking plugin",
+    "使用": "Use",
+    "读 docs\\use_azure.md": "Read docs\\use_azure.md",
+    "开始最终总结": "Start final summary",
+    "openai的官方KEY需要伴随组织编码": "Openai's official KEY needs to be accompanied by organizational code",
+    "将子线程的gpt结果写入chatbot": "Write the GPT result of the sub-thread into the chatbot",
+    "Arixv论文精细翻译": "Fine translation of Arixv paper",
+    "开始接收chatglmft的回复": "Start receiving replies from chatglmft",
+    "请先将.doc文档转换为.docx文档": "Please convert .doc documents to .docx documents first",
+    "避免多用户干扰": "Avoid multiple user interference",
+    "清空label": "Clear label",
+    "解除插件锁定": "Unlock plugin",
+    "请以以下方式load模型！！！": "Please load the model in the following way!!!",
+    "没给定指令": "No instruction given",
+    "100字以内": "Within 100 words",
+    "获取关键词": "Get keywords",
+    "欢迎使用 MOSS 人工智能助手！": "Welcome to use MOSS AI assistant!",
+    "音频助手": "Audio assistant",
+    "上传Latex项目": "Upload Latex project",
+    "对话助手函数插件": "Chat assistant function plugin",
+    "如果一句话小于7个字": "If a sentence is less than 7 words",
+    "640个字节为一组": "640 bytes per group",
+    "右下角更换模型菜单中可切换openai": "OpenAI can be switched in the model menu in the lower right corner",
+    "双手离开鼠标键盘吧": "Take your hands off the mouse and keyboard",
+    "先删除": "Delete first",
+    "如果要使用ChatGLMFT": "If you want to use ChatGLMFT",
+    "例如 RoPlZrM88DnAFkZK": "For example, RoPlZrM88DnAFkZK",
+    "提取总结": "Extract summary",
+    "ChatGLMFT消耗大量的内存": "ChatGLMFT consumes a lot of memory",
+    "格式如org-123456789abcdefghijklmno的": "In the format of org-123456789abcdefghijklmno",
+    "在执行完成之后": "After execution is complete",
+    "此处填API密钥": "Fill in the API key here",
+    "chatglmft 没有 sys_prompt 接口": "ChatGLMFT does not have a sys_prompt interface",
+    "用第二人称": "Use the second person",
+    "Chuanhu-Small-and-Beautiful主题": "Chuanhu-Small-and-Beautiful theme",
+    "请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期": "Please check if ALIYUN_TOKEN and ALIYUN_APPKEY have expired",
+    "还需要填写组织": "You also need to fill in the organization",
+    "会直接转到该函数": "Will directly jump to the function",
+    "初始化插件状态": "Initializing plugin status",
+    "插件锁定中": "Plugin is locked",
+    "如果这里报错": "If there is an error here",
+    "本地Latex论文精细翻译": "Local Latex paper fine translation",
+    "极少数情况下": "In very few cases",
+    "首先你在中文语境下通读整篇论文": "First, read the entire paper in a Chinese context",
+    "点击“停止”键可终止程序": "Click the 'Stop' button to terminate the program",
+    "建议排查": "Suggested troubleshooting",
+    "没有阿里云语音识别APPKEY和TOKEN": "No Aliyun voice recognition APPKEY and TOKEN",
+    "避免遗忘导致死锁": "Avoid forgetting to cause deadlock",
+    "第一次调用": "First call",
+    "解决插件锁定时的界面显示问题": "Solve the interface display problem when the plugin is locked",
+    "初始化音频采集线程": "Initialize audio capture thread",
+    "找不到微调模型检查点": "Cannot find fine-tuning model checkpoint",
+    "色彩主体": "Color theme",
+    "上传文件自动修正路径": "Automatically correct the path when uploading files",
+    "将文件添加到chatbot cookie中": "Add files to chatbot cookie",
+    "正常状态": "Normal state",
+    "建议使用英文单词": "Suggest using English words",
+    "Aliyun音频服务异常": "Aliyun audio service exception",
+    "格式如org-xxxxxxxxxxxxxxxxxxxxxxxx": "Format like org-xxxxxxxxxxxxxxxxxxxxxxxx",
+    "GPT 学术优化": "GPT academic optimization",
+    "要求": "Requirement",
+    "赋予插件状态": "Assign plugin status",
+    "等待GPT响应": "Waiting for GPT response",
+    "MOSS can understand and communicate fluently in the language chosen by the user such as English and 中文. MOSS can perform any language-based tasks.": "MOSS can understand and communicate fluently in the language chosen by the user such as English and Chinese. MOSS can perform any language-based tasks.",
+    "我将为您查找相关壁纸": "I will search for related wallpapers for you",
+    "当下一次用户提交时": "When the next user submits",
+    "赋予插件锁定 锁定插件回调路径": "Assign plugin lock, lock plugin callback path",
+    "处理个别特殊插件的锁定状态": "Handle the lock status of individual special plugins",
+    "add gpt task 创建子线程请求gpt": "Add GPT task, create sub-thread to request GPT",
+    "等待用户的再次调用": "Waiting for the user to call again",
+    "只读": "Read-only",
+    "用于灵活调整复杂功能的各种参数": "Various parameters used to flexibly adjust complex functions",
+    "输入 stop 以终止对话": "Enter stop to terminate the conversation",
+    "缺少ChatGLMFT的依赖": "Missing dependency of ChatGLMFT",
+    "找 API_ORG 设置项": "Find API_ORG setting item",
+    "检查config中的AVAIL_LLM_MODELS选项": "Check the AVAIL_LLM_MODELS option in config",
+    "对这个人外貌、身处的环境、内心世界、人设进行描写": "Describe the appearance, environment, inner world, and character of this person.",
+    "请输入关键词": "Please enter a keyword.",
+    "！！！如果需要运行量化版本": "!!! If you need to run the quantitative version.",
+    "为每一位访问的用户赋予一个独一无二的uuid编码": "Assign a unique uuid code to each visiting user.",
+    "由于提问含不合规内容被Azure过滤": "Due to Azure filtering out questions containing non-compliant content.",
+    "欢迎使用 MOSS 人工智能助手！输入内容即可进行对话": "Welcome to use MOSS AI assistant! Enter the content to start the conversation.",
+    "记住当前的label": "Remember the current label.",
+    "不能正常加载ChatGLMFT的参数！": "Cannot load ChatGLMFT parameters normally!",
+    "建议直接在API_KEY处填写": "It is recommended to fill in directly at API_KEY."
 }

docs/translate_traditionalchinese.json

@@ -150,26 +150,7 @@
     "使用中文回答我的问题": "使用中文回答我的問題",
     "备份一个文件": "備份一個文件",
     "未知": "未知",
-    "如.md": "#",
-    "**输入参数说明**": "#",
-    "如果这裡拋出異常": "#",
-    "多線程操作已經開始": "#",
-    "備份和下載": "#",
-    "新版本可用": "#",
-    "將要忽略匹配的文件後綴": "#",
-    "可調節線程池的大小避免openai的流量限制錯誤": "#",
-    "使用Unsplash API": "#",
-    "ChatGPT綜合": "#",
-    "從摘要中提取高價值信息": "#",
-    "借助此參數": "#",
-    "知乎": "#",
-    "其他錯誤": "#",
-    "退出": "#",
-    "對話歷史寫入": "#",
-    "問詢記錄": "#",
-    "依次訪問網頁": "#",
-    "NewBing響應異常": "#",
-    "jittorllms尚未加載": "#",
+    "其他錯誤": "其他錯誤",
     "等待NewBing响应": "等待NewBing回應",
     "找不到任何CSharp文件": "找不到任何CSharp檔案",
     "插件demo": "插件範例",
@@ -300,12 +281,12 @@
     "上傳本地文件可供紅色函數插件調用": "上傳本地文件供紅色函數插件調用",
     "生成圖像": "生成圖像",
     "追加歷史": "追加歷史",
-    "網絡代理狀態": "網路代理狀態",
+    "網絡代理狀態": "網絡代理狀態",
     "不需要再次轉化": "不需要再次轉換",
     "帶超時倒計時": "帶有超時倒數計時",
     "保存當前對話": "儲存目前對話",
     "等待響應": "等待回應",
-    "依賴檢測通過": "依賴檢查通過",
+    "依賴檢測通過": "依賴檢測通過",
     "如果要使用ChatGLM": "如果要使用ChatGLM",
     "對IPynb文件進行解析": "對IPynb檔案進行解析",
     "先切換模型到openai或api2d": "先切換模型到openai或api2d",
@@ -411,7 +392,7 @@
     "中转网址预览": "中轉網址預覽",
     "自动截断": "自動截斷",
     "当無法用標點、空行分割時": "當無法用標點、空行分割時",
-    "意外Json結構": "意外的Json結構",
+    "意外Json結構": "意外Json結構",
     "需要讀取和清理文本的pdf文件路徑": "需要讀取和清理文本的pdf文件路徑",
     "HotReload的裝飾器函數": "HotReload的裝飾器函數",
     "chatGPT 分析報告": "chatGPT 分析報告",
@@ -423,7 +404,7 @@
     "這個bug沒找到觸發條件": "這個bug沒找到觸發條件",
     "喚起高級參數輸入區": "喚起高級參數輸入區",
     "但大部分場合下並不需要修改": "但大部分場合下並不需要修改",
-    "盡量是完整的一個section": "盡量是完整的一個section",
+    "盡量是完整的一個section": "盡量選擇完整的一個章節",
     "如果OpenAI不響應": "如果OpenAI不響應",
     "等文本特殊符號轉換為其基本形式來對文本進行歸一化處理": "等文本特殊符號轉換為其基本形式來對文本進行歸一化處理",
     "你的回答必須簡單明了": "你的回答必須簡單明了",
@@ -517,7 +498,7 @@
     "正在提取摘要並下載PDF文檔……": "正在提取摘要並下載PDF文件……",
     "1. 對原始文本進行歸一化處理": "1. 正規化原始文本",
     "問題": "問題",
-    "用於基礎的對話功能": "基本對話功能",
+    "用於基礎的對話功能": "用於基礎的對話功能",
     "獲取設置": "獲取設置",
     "如果缺少依賴": "如果缺少依賴項",
     "第6步": "第6步",
@@ -1111,26 +1092,9 @@
     "清理规则包括": "清理規則包括",
     "新版配置": "新版配置",
     "如果有": "如果有",
-    "高級參數輸入區": "#",
-    "您提供的api-key不滿足要求": "#",
-    "“喂狗”": "#",
-    "有線程鎖": "#",
-    "解析整個CSharp項目": "#",
-    "上下文管理器必須實現兩個方法": "#",
-    "Call MOSS fail 不能正常加載MOSS的參數": "#",
-    "獲取圖片URL": "#",
-    "輸入部分太自由": "#",
-    "Not enough point. API2D賬戶點數不足": "#",
-    "網絡錯誤": "#",
-    "請開始多線程操作": "#",
-    "authors獲取失敗": "#",
-    "、地址": "#",
-    "根據以上分析": "#",
-    "1、英文題目；2、中文題目翻譯；3、作者；4、arxiv公開": "#",
-    "一些普通功能模塊": "#",
-    "參數簡單": "#",
-    "具備以下功能": "#",
-    "優先級2. 獲取config_private中的配置": "#",
+    "Call MOSS fail 不能正常加載MOSS的參數": "Call MOSS fail 不能正常加載MOSS的參數",
+    "根據以上分析": "根據以上分析",
+    "一些普通功能模塊": "一些普通功能模塊",
     "汇总报告如何远程获取": "如何遠程獲取匯總報告",
     "热更新prompt": "熱更新提示",
     "插件调度异常": "插件調度異常",
@@ -1191,26 +1155,9 @@
     "函数插件区": "函數插件區",
     "*** API_KEY 导入成功": "*** API_KEY 導入成功",
     "请对下面的程序文件做一个概述文件名是": "請對下面的程序文件做一個概述文件名是",
-    "替換跨行的連詞": "#",
-    "內容太長了都會觸發token數量溢出的錯誤": "#",
-    "尚未完成全部響應": "#",
-    "生成帶有段落標籤的HTML代碼": "#",
-    "函數熱更新是指在不停止程序運行的情況下": "#",
-    "將Unsplash API中的PUT_YOUR_QUERY_HERE替換成描述該事件的一個最重要的單詞": "#",
-    "沒有提供高級參數功能說明": "#",
-    "條": "#",
-    "請刷新界面重試": "#",
-    "和openai的連接容易斷掉": "#",
-    "使用 Unsplash API": "#",
-    "完成情況": "#",
-    "迭代上一次的結果": "#",
-    "每個線程都要“餵狗”": "#",
-    "最多收納多少個網頁的結果": "#",
-    "日": "#",
-    "第4步": "#",
-    "找不到任何python文件": "#",
-    "經過充分測試": "#",
-    "缺少的依賴": "#",
+    "內容太長了都會觸發token數量溢出的錯誤": "內容太長了都會觸發token數量溢出的錯誤",
+    "沒有提供高級參數功能說明": "未提供高級參數功能說明",
+    "和openai的連接容易斷掉": "和openai的連接容易斷掉",
     "分组+迭代处理": "分組+迭代處理",
     "安装Newbing的依赖": "安裝Newbing的依賴",
     "批": "批",
@@ -1511,5 +1458,760 @@
     "包括": "包括",
     "或者": "或者",
     "并执行函数的新版本": "並執行函數的新版本",
-    "论文": "論文"
+    "论文": "論文",
+    "解析一个Golang项目": "ParseAGolangProject",
+    "Latex英文纠错": "LatexEnglishCorrection",
+    "连接bing搜索回答问题": "ConnectToBingSearchForAnswer",
+    "联网的ChatGPT_bing版": "ChatGPT_BingVersionOnline",
+    "总结音视频": "SummarizeAudioAndVideo",
+    "动画生成": "GenerateAnimations",
+    "数学动画生成manim": "GenerateMathematicalAnimationsWithManim",
+    "Markdown翻译指定语言": "TranslateMarkdownToSpecifiedLanguage",
+    "知识库问答": "KnowledgeBaseQA",
+    "Langchain知识库": "LangchainKnowledgeBase",
+    "读取知识库作答": "ReadKnowledgeBaseAndAnswerQuestions",
+    "交互功能模板函数": "InteractiveFunctionTemplateFunctions",
+    "交互功能函数模板": "InteractiveFunctionFunctionTemplates",
+    "Latex英文纠错加PDF对比": "LatexEnglishCorrectionWithPDFComparison",
+    "Latex输出PDF结果": "OutputPDFFromLatex",
+    "Latex翻译中文并重新编译PDF": "TranslateLatexToChineseAndRecompilePDF",
+    "语音助手": "VoiceAssistant",
+    "微调数据集生成": "FineTuneDatasetGeneration",
+    "chatglm微调工具": "ChatGLM_FineTuningTool",
+    "启动微调": "StartFineTuning",
+    "sprint亮靛": "SprintLiangDian",
+    "寻找Latex主文件": "FindLatexMainFile",
+    "专业词汇声明": "ProfessionalTerminologyDeclaration",
+    "Latex精细分解与转化": "LatexFineDecompositionAndConversion",
+    "编译Latex": "CompileLatex",
+    "正在等您说完问题": "正在等您說完問題",
+    "最多同时执行5个": "最多同時執行5個",
+    "将文件复制一份到下载区": "將檔案複製一份到下載區",
+    "您接下来不能再使用其他插件了": "您接下來不能再使用其他插件了",
+    "如 绿帽子*深蓝色衬衫*黑色运动裤": "如 綠帽子*深藍色襯衫*黑色運動褲",
+    "首先你在中文语境下通读整篇论文": "首先您在中文語境下通讀整篇論文",
+    "根据给定的切割时长将音频文件切割成多个片段": "根據給定的切割時長將音訊檔切割成多個片段",
+    "接下来两句话只显示在界面上": "接下來兩句話只顯示在介面上",
+    "清空label": "清空標籤",
+    "正在尝试自动安装": "正在嘗試自動安裝",
+    "MOSS消耗大量的内存": "MOSS消耗大量的記憶體",
+    "如果这里报错": "如果這裡報錯",
+    "其他类型文献转化效果未知": "其他類型文獻轉換效果未知",
+    "ChatGPT综合": "ChatGPT綜合",
+    "音频文件的路径": "音訊檔案的路徑",
+    "执行错误": "執行錯誤",
+    "因此选择GenerateImage函数": "因此選擇GenerateImage函數",
+    "从摘要中提取高价值信息": "從摘要中提取高價值資訊",
+    "使用英文": "使用英文",
+    "是否在提交时自动清空输入框": "是否在提交時自動清空輸入框",
+    "生成数学动画": "生成數學動畫",
+    "正在加载Claude组件": "正在載入Claude元件",
+    "参数说明": "參數說明",
+    "建议排查": "建議排查",
+    "将消耗较长时间下载中文向量化模型": "將消耗較長時間下載中文向量化模型",
+    "test_LangchainKnowledgeBase读取": "test_LangchainKnowledgeBase讀取",
+    "安装Claude的依赖": "安裝Claude的相依性",
+    "以下所有配置也都支持利用环境变量覆写": "以下所有配置也都支持利用環境變數覆寫",
+    "需要被切割的音频文件名": "需要被切割的音頻文件名",
+    "保存当前对话": "保存當前對話",
+    "功能、贡献者": "功能、貢獻者",
+    "Chuanhu-Small-and-Beautiful主题": "Chuanhu-小而美主題",
+    "等待Claude响应": "等待Claude響應",
+    "其他模型转化效果未知": "其他模型轉換效果未知",
+    "版权归原文作者所有": "版權歸原文作者所有",
+    "回答完问题后": "回答完問題後",
+    "请先上传文件素材": "請先上傳文件素材",
+    "上传本地文件/压缩包供函数插件调用": "上傳本地文件/壓縮包供函數插件調用",
+    "P.S. 顺便把Latex的注释去除": "P.S. 順便把Latex的註釋去除",
+    "您提供的api-key不满足要求": "您提供的api-key不滿足要求",
+    "切割音频文件": "切割音頻文件",
+    "对不同latex源文件扣分": "對不同latex源文件扣分",
+    "以下是一篇学术论文的基础信息": "以下是一篇學術論文的基礎信息",
+    "问题": "問題",
+    "待注入的知识库名称id": "待注入的知識庫名稱id",
+    "”的主要内容": "”的主要內容",
+    "获取设置": "獲取設置",
+    "str类型": "str類型",
+    "多线程": "多線程",
+    "尝试执行Latex指令失败": "嘗試執行Latex指令失敗",
+    "然后再写一段英文摘要": "然後再寫一段英文摘要",
+    "段音频的主要内容": "段音頻的主要內容",
+    "临时地激活代理网络": "臨時地激活代理網絡",
+    "网络的远程文件": "網絡的遠程文件",
+    "不能正常加载ChatGLMFT的参数！": "無法正常載入ChatGLMFT的參數！",
+    "正在编译PDF文档": "正在編譯PDF文件",
+    "等待ChatGLMFT响应中": "等待ChatGLMFT回應中",
+    "将": "將",
+    "片段": "片段",
+    "修复括号": "修復括號",
+    "条": "條",
+    "建议直接在API_KEY处填写": "建議直接在API_KEY處填寫",
+    "根据需要切换prompt": "根據需要切換prompt",
+    "使用": "使用",
+    "请输入要翻译成哪种语言": "請輸入要翻譯成哪種語言",
+    "实际得到格式": "實際得到格式",
+    "例如 f37f30e0f9934c34a992f6f64f7eba4f": "例如 f37f30e0f9934c34a992f6f64f7eba4f",
+    "请切换至“KnowledgeBaseQA”插件进行知识库访问": "請切換至“KnowledgeBaseQA”插件進行知識庫訪問",
+    "用户填3": "用戶填3",
+    "远程云服务器部署": "遠程雲服務器部署",
+    "未知指令": "未知指令",
+    "每个线程都要“喂狗”": "每個線程都要“喂狗”",
+    "该项目的Latex主文件是": "該項目的Latex主文件是",
+    "设置OpenAI密钥和模型": "設置OpenAI密鑰和模型",
+    "填入你亲手写的部署名": "填入你親手寫的部署名",
+    "仅调试": "僅調試",
+    "依赖不足": "依賴不足",
+    "右下角更换模型菜单中可切换openai": "右下角更換模型菜單中可切換openai",
+    "解析整个CSharp项目": "解析整個CSharp項目",
+    "唤起高级参数输入区": "喚起高級參數輸入區",
+    "这个bug没找到触发条件": "這個bug沒找到觸發條件",
+    "========================================= 插件主程序2 =====================================================": "========================================= 插件主程序2 =====================================================",
+    "经过充分测试": "經過充分測試",
+    "该文件中主要包含三个函数": "該文件中主要包含三個函數",
+    "您可以到Github Issue区": "您可以到Github Issue區",
+    "避免线程阻塞": "避免線程阻塞",
+    "吸收iffalse注释": "吸收iffalse註釋",
+    "from crazy_functions.虚空终端 import 终端": "from crazy_functions.虛空終端 import 終端",
+    "异步方法": "異步方法",
+    "块元提取": "塊元提取",
+    "Your account is not active. OpenAI以账户失效为由": "您的帳戶未啟用。OpenAI以帳戶失效為由",
+    "还原部分原文": "還原部分原文",
+    "如果要使用Claude": "如果要使用Claude",
+    "把文件复制过去": "把文件複製過去",
+    "解压失败! 需要安装pip install rarfile来解压rar文件": "解壓失敗！需要安裝pip install rarfile來解壓rar文件",
+    "正在锁定插件": "正在鎖定插件",
+    "输入 clear 以清空对话历史": "輸入 clear 以清空對話歷史",
+    "P.S. 但愿没人把latex模板放在里面传进来": "P.S. 但願沒人把latex模板放在裡面傳進來",
+    "实时音频采集": "實時音頻採集",
+    "开始最终总结": "開始最終總結",
+    "拒绝服务": "拒絕服務",
+    "配置教程&视频教程": "配置教程&視頻教程",
+    "所有音频都总结完成了吗": "所有音頻都總結完成了嗎",
+    "返回": "返回",
+    "避免不小心传github被别人看到": "避免不小心傳github被別人看到",
+    "否则将导致每个人的Claude问询历史互相渗透": "否則將導致每個人的Claude問詢歷史互相滲透",
+    "提问吧! 但注意": "提問吧！但注意",
+    "待处理的word文档路径": "待處理的word文檔路徑",
+    "欢迎加REAME中的QQ联系开发者": "歡迎加REAME中的QQ聯繫開發者",
+    "建议暂时不要使用": "建議暫時不要使用",
+    "Latex没有安装": "Latex沒有安裝",
+    "在这里放一些网上搜集的demo": "在這裡放一些網上搜集的demo",
+    "实现消息发送、接收等功能": "實現消息發送、接收等功能",
+    "用于与with语句一起使用": "用於與with語句一起使用",
+    "解压失败! 需要安装pip install py7zr来解压7z文件": "解壓失敗! 需要安裝pip install py7zr來解壓7z文件",
+    "借助此参数": "借助此參數",
+    "判定为数据流的结束": "判定為數據流的結束",
+    "提取文件扩展名": "提取文件擴展名",
+    "GPT结果已输出": "GPT結果已輸出",
+    "读取文件": "讀取文件",
+    "如果OpenAI不响应": "如果OpenAI不響應",
+    "输入部分太自由": "輸入部分太自由",
+    "用于给一小段代码上代理": "用於給一小段代碼上代理",
+    "输入 stop 以终止对话": "輸入 stop 以終止對話",
+    "这个paper有个input命令文件名大小写错误！": "這個paper有個input命令文件名大小寫錯誤！",
+    "等待Claude回复的片段": "等待Claude回復的片段",
+    "开始": "開始",
+    "将根据报错信息修正tex源文件并重试": "將根據報錯信息修正tex源文件並重試",
+    "建议更换代理协议": "建議更換代理協議",
+    "递归地切割PDF文件": "遞歸地切割PDF文件",
+    "读 docs\\use_azure.md": "讀 docs\\use_azure.md",
+    "参数": "參數",
+    "屏蔽空行和太短的句子": "屏蔽空行和太短的句子",
+    "分析上述回答": "分析上述回答",
+    "因为在同一个频道里存在多人使用时历史消息渗透问题": "因為在同一個頻道裡存在多人使用時歷史消息滲透問題",
+    "使用latexdiff生成論文轉化前後對比": "使用latexdiff生成論文轉化前後對比",
+    "檢查結果": "檢查結果",
+    "請在此處追加更細緻的校錯指令": "請在此處追加更細緻的校錯指令",
+    "報告如何遠程獲取": "報告如何遠程獲取",
+    "發現已經存在翻譯好的PDF文檔": "發現已經存在翻譯好的PDF文檔",
+    "插件鎖定中": "插件鎖定中",
+    "正在精細切分latex文件": "正在精細切分latex文件",
+    "數學GenerateAnimations": "數學GenerateAnimations",
+    "上傳文件自動修正路徑": "上傳文件自動修正路徑",
+    "請檢查ALIYUN_TOKEN和ALIYUN_APPKEY是否過期": "請檢查ALIYUN_TOKEN和ALIYUN_APPKEY是否過期",
+    "上傳Latex項目": "上傳LaTeX項目",
+    "Aliyun音頻服務異常": "Aliyun音頻服務異常",
+    "為了防止大語言模型的意外謬誤產生擴散影響": "為了防止大語言模型的意外謬誤產生擴散影響",
+    "調用Claude時": "調用Claude時",
+    "解除插件鎖定": "解除插件鎖定",
+    "暗色模式 / 亮色模式": "暗色模式 / 亮色模式",
+    "只有第二步成功": "只有第二步成功",
+    "分析结果": "分析結果",
+    "用第二人称": "使用第二人稱",
+    "详情见https": "詳情請見https",
+    "记住当前的label": "記住當前的標籤",
+    "当无法用标点、空行分割时": "當無法用標點符號、空行分割時",
+    "如果分析错误": "如果分析錯誤",
+    "如果有必要": "如果有必要",
+    "不要修改!! 高危设置！通过修改此设置": "不要修改!! 高危設置！通過修改此設置",
+    "ChatGLMFT消耗大量的内存": "ChatGLMFT消耗大量的內存",
+    "摘要生成后的文档路径": "摘要生成後的文件路徑",
+    "对全文进行概括": "對全文進行概述",
+    "LLM_MODEL是默认选中的模型": "LLM_MODEL是默認選中的模型",
+    "640个字节为一组": "640個字節為一組",
+    "获取关键词": "獲取關鍵詞",
+    "解析为简体中文": "解析為簡體中文",
+    "将 \\include 命令转换为 \\input 命令": "將 \\include 命令轉換為 \\input 命令",
+    "默认值为1000": "默認值為1000",
+    "手动指定语言": "手動指定語言",
+    "请登录OpenAI查看详情 https": "請登錄OpenAI查看詳情 https",
+    "尝试第": "嘗試第",
+    "每秒采样数量": "每秒採樣數量",
+    "加载失败!": "加載失敗!",
+    "方法": "方法",
+    "对这个人外貌、身处的环境、内心世界、过去经历进行描写": "對這個人外貌、身處的環境、內心世界、過去經歷進行描寫",
+    "请先将.doc文档转换为.docx文档": "請先將.doc文檔轉換為.docx文檔",
+    "定位主Latex文件": "定位主Latex文件",
+    "批量SummarizeAudioAndVideo": "批量摘要音视频",
+    "终端": "終端",
+    "即将退出": "即將退出",
+    "找不到": "找不到",
+    "正在听您讲话": "正在聆聽您講話",
+    "请您不要删除或修改这行警告": "請勿刪除或修改此警告",
+    "没有阿里云语音识别APPKEY和TOKEN": "沒有阿里雲語音識別APPKEY和TOKEN",
+    "临时地启动代理网络": "臨時啟動代理網絡",
+    "请尝试把以下指令复制到高级参数区": "請將以下指令複製到高級參數區",
+    "中文Bing版": "中文Bing版",
+    "计算文件总时长和切割点": "計算文件總時長和切割點",
+    "寻找主文件": "尋找主文件",
+    "jittorllms尚未加载": "jittorllms尚未加載",
+    "使用正则表达式查找半行注释": "使用正則表達式查找半行註釋",
+    "文档越长耗时越长": "文檔越長耗時越長",
+    "生成中文PDF": "生成中文PDF",
+    "写入文件": "寫入文件",
+    "第三组插件": "第三組插件",
+    "开始接收chatglmft的回复": "開始接收chatglmft的回覆",
+    "由于提问含不合规内容被Azure过滤": "由於提問含不合規內容被Azure過濾",
+    "安装方法https": "安裝方法https",
+    "是否自动处理token溢出的情况": "是否自動處理token溢出的情況",
+    "如果需要使用AZURE 详情请见额外文档 docs\\use_azure.md": "如果需要使用AZURE 詳情請見額外文檔 docs\\use_azure.md",
+    "将要忽略匹配的文件后缀": "將要忽略匹配的文件後綴",
+    "authors获取失败": "authors獲取失敗",
+    "发送到openai音频解析终端": "發送到openai音頻解析終端",
+    "请开始多线程操作": "請開始多線程操作",
+    "对这个人外貌、身处的环境、内心世界、人设进行描写": "對這個人外貌、身處的環境、內心世界、人設進行描寫",
+    "MOSS can understand and communicate fluently in the language chosen by the user such as English and 中文. MOSS can perform any language-based tasks.": "MOSS可以流利地理解和使用用戶選擇的語言，例如英語和中文。MOSS可以執行任何基於語言的任務。",
+    "work_folder = Latex預處理": "設置工作目錄為Latex預處理",
+    "然後轉移到指定的另一個路徑中": "然後轉移到指定的另一個路徑中",
+    "使用Newbing": "使用Newbing",
+    "詳情信息見requirements.txt": "詳細信息請參閱requirements.txt",
+    "開始下載": "開始下載",
+    "多線程翻譯開始": "多線程翻譯開始",
+    "當前大語言模型": "當前大語言模型",
+    "格式如org-123456789abcdefghijklmno的": "格式如org-123456789abcdefghijklmno的",
+    "當下一次用戶提交時": "當下一次用戶提交時",
+    "需要特殊依賴": "需要特殊依賴",
+    "次編譯": "次編譯",
+    "先上傳數據集": "先上傳數據集",
+    "gpt寫的": "gpt寫的",
+    "調用緩存": "調用緩存",
+    "优先级1. 获取环境变量作为配置": "優先級1. 獲取環境變量作為配置",
+    "检查config中的AVAIL_LLM_MODELS选项": "檢查config中的AVAIL_LLM_MODELS選項",
+    "并且对于网络上的文件": "並且對於網絡上的文件",
+    "根据文本使用GPT模型生成相应的图像": "根據文本使用GPT模型生成相應的圖像",
+    "功能描述": "功能描述",
+    "翻译结果": "翻譯結果",
+    "需要预先pip install rarfile": "需要預先pip install rarfile",
+    "等待响应": "等待響應",
+    "我们剥离Introduction之后的部分": "我們剝離Introduction之後的部分",
+    "函数插件-固定按钮区": "函數插件-固定按鈕區",
+    "临时存储用于调试": "臨時存儲用於調試",
+    "比正文字体小": "比正文字體小",
+    "会直接转到该函数": "會直接轉到該函數",
+    "请以以下方式load模型！！！": "請以以下方式load模型！！！",
+    "请输入关键词": "請輸入關鍵詞",
+    "返回找到的第一个": "返回找到的第一個",
+    "高级参数输入区": "高級參數輸入區",
+    "精细切分latex文件": "精細切分latex文件",
+    "赋予插件锁定 锁定插件回调路径": "賦予插件鎖定 鎖定插件回調路徑",
+    "尝试下载": "嘗試下載",
+    "包含documentclass关键字": "包含documentclass關鍵字",
+    "在一个异步线程中采集音频": "在一個異步線程中採集音頻",
+    "先删除": "先刪除",
+    "则跳过GPT请求环节": "則跳過GPT請求環節",
+    "Not enough point. API2D账户点数不足": "Not enough point. API2D帳戶點數不足",
+    "如果一句话小于7个字": "如果一句話小於7個字",
+    "具备以下功能": "具備以下功能",
+    "请查看终端的输出或耐心等待": "請查看終端的輸出或耐心等待",
+    "对输入的word文档进行摘要生成": "對輸入的word文檔進行摘要生成",
+    "只读": "只讀",
+    "文本碎片重组为完整的tex文件": "文本碎片重組為完整的tex文件",
+    "通过调用conversations_open方法打开一个频道": "通過調用conversations_open方法打開一個頻道",
+    "对话历史文件损坏！": "對話歷史文件損壞！",
+    "再失败就没办法了": "再失敗就沒辦法了",
+    "原始PDF编译是否成功": "原始PDF編譯是否成功",
+    "不能正常加载jittorllms的参数！": "不能正常加載jittorllms的參數！",
+    "正在编译对比PDF": "正在編譯對比PDF",
+    "找不到微调模型检查点": "找不到微調模型檢查點",
+    "将生成的报告自动投射到文件上传区": "將生成的報告自動投射到文件上傳區",
+    "请对这部分内容进行语法矫正": "請對這部分內容進行語法校正",
+    "编译已经开始": "編譯已經開始",
+    "需要读取和清理文本的pdf文件路径": "需要讀取和清理文本的pdf文件路徑",
+    "读取文件内容到内存": "讀取文件內容到內存",
+    "用&符号分隔": "用&符號分隔",
+    "输入arxivID": "輸入arxivID",
+    "找 API_ORG 设置项": "找API_ORG設置項",
+    "分析用户提供的谷歌学术": "分析用戶提供的谷歌學術",
+    "欢迎使用 MOSS 人工智能助手！输入内容即可进行对话": "歡迎使用 MOSS 人工智能助手！輸入內容即可進行對話",
+    "段音频的第": "段音頻的第",
+    "没有找到任何可读取文件": "沒有找到任何可讀取文件",
+    "目前仅支持GPT3.5/GPT4": "目前僅支持GPT3.5/GPT4",
+    "为每一位访问的用户赋予一个独一无二的uuid编码": "為每一位訪問的用戶賦予一個獨一無二的uuid編碼",
+    "内含已经翻译的Tex文档": "內含已經翻譯的Tex文檔",
+    "消耗时间的函数": "消耗時間的函數",
+    "成功啦": "成功啦",
+    "环境变量配置格式见docker-compose.yml": "環境變量配置格式見docker-compose.yml",
+    "将每次对话记录写入Markdown格式的文件中": "將每次對話記錄寫入Markdown格式的文件中",
+    "报告已经添加到右侧“文件上传区”": "報告已經添加到右側“文件上傳區”",
+    "此处可以输入解析提示": "此處可以輸入解析提示",
+    "缺少MOSS的依赖": "缺少MOSS的依賴",
+    "仅在Windows系统进行了测试": "僅在Windows系統進行了測試",
+    "然后重启程序": "然後重啟程序",
+    "此处不修改": "此處不修改",
+    "输出html调试文件": "輸出html調試文件",
+    "6.25 加入判定latex模板的代码": "6.25 加入判定latex模板的代碼",
+    "提取总结": "提取總結",
+    "要求": "要求",
+    "由于最为关键的转化PDF编译失败": "由於最為關鍵的轉化PDF編譯失敗",
+    "除非您是论文的原作者": "除非您是論文的原作者",
+    "输入问题后点击该插件": "輸入問題後點擊該插件",
+    "该选项即将被弃用": "該選項即將被棄用",
+    "再列出用户可能提出的三个问题": "再列出用戶可能提出的三個問題",
+    "所有文件都总结完成了吗": "所有文件都總結完成了嗎",
+    "请稍候": "請稍候",
+    "向chatbot中添加简单的意外错误信息": "向chatbot中添加簡單的意外錯誤信息",
+    "快捷的调试函数": "快捷的調試函數",
+    "LatexEnglishCorrection+高亮修正位置": "Latex英文校正+高亮修正位置",
+    "循环监听已打开频道的消息": "循環監聽已打開頻道的消息",
+    "将指定目录下的PDF文件从英文翻译成中文": "將指定目錄下的PDF文件從英文翻譯成中文",
+    "请对下面的音频片段做概述": "請對下面的音頻片段做概述",
+    "openai的官方KEY需要伴隨组织编码": "openai的官方KEY需要伴隨組織編碼",
+    "表示频道ID": "頻道ID",
+    "当前支持的格式包括": "目前支援的格式包括",
+    "只有GenerateImage和生成图像相关": "僅限GenerateImage和生成圖像相關",
+    "删除中间文件夹": "刪除中間資料夾",
+    "解除插件状态": "解除插件狀態",
+    "正在预热文本向量化模组": "正在預熱文本向量化模組",
+    "100字以内": "限制100字內",
+    "如果缺少依赖": "如果缺少相依性",
+    "寻找主tex文件": "尋找主要tex檔案",
+    "gpt 多线程请求": "gpt 多線程請求",
+    "已知某些代码的局部作用是": "已知某些程式碼的局部作用是",
+    "--读取文件": "--讀取檔案",
+    "前面是中文冒号": "前面是中文冒號",
+    "*{\\scriptsize\\textbf{警告": "*{\\scriptsize\\textbf{警告",
+    "OpenAI所允许的最大并行过载": "OpenAI所允許的最大並行過載",
+    "请直接去该路径下取回翻译结果": "請直接前往該路徑取回翻譯結果",
+    "以免输入溢出": "以免輸入溢出",
+    "把某个路径下所有文件压缩": "壓縮某個路徑下的所有檔案",
+    "问询记录": "詢問記錄",
+    "Tex源文件缺失！": "Tex原始檔案遺失！",
+    "当前参数": "目前參數",
+    "处理markdown文本格式的转变": "處理markdown文本格式的轉換",
+    "尝试加载": "嘗試載入",
+    "请在此处给出自定义翻译命令": "請在此處提供自訂翻譯命令",
+    "这需要一段时间计算": "這需要一段時間計算",
+    "-构建知识库": "-建立知識庫",
+    "还需要填写组织": "還需要填寫組織",
+    "当前知识库内的有效文件": "當前知識庫內的有效文件",
+    "第一次调用": "第一次調用",
+    "从一批文件": "從一批文件",
+    "json等": "json等",
+    "翻译-": "翻譯-",
+    "编译文献交叉引用": "編譯文獻交叉引用",
+    "优先级2. 获取config_private中的配置": "優先級2. 獲取config_private中的配置",
+    "可选": "可選",
+    "我们": "我們",
+    "编译结束": "編譯結束",
+    "或代理节点": "或代理節點",
+    "chatGPT 分析报告": "chatGPT 分析報告",
+    "调用openai api 使用whisper-1模型": "調用openai api 使用whisper-1模型",
+    "这段代码定义了一个名为TempProxy的空上下文管理器": "這段代碼定義了一個名為TempProxy的空上下文管理器",
+    "生成的视频文件路径": "生成的視頻文件路徑",
+    "请直接提交即可": "請直接提交即可",
+    "=================================== 工具函数 ===============================================": "=================================== 工具函數 ===============================================",
+    "报错信息如下. 如果是与网络相关的问题": "報錯信息如下. 如果是與網絡相關的問題",
+    "python 版本建议3.9+": "python 版本建議3.9+",
+    "多线程函数插件中": "多線程函數插件中",
+    "对话助手函数插件": "對話助手函數插件",
+    "或者重启之后再度尝试": "或者重啟之後再度嘗試",
+    "拆分过长的latex片段": "拆分過長的latex片段",
+    "调用whisper模型音频转文字": "調用whisper模型音頻轉文字",
+    "失败啦": "失敗啦",
+    "正在编译PDF": "正在編譯PDF",
+    "请刷新界面重试": "請刷新界面重試",
+    "模型参数": "模型參數",
+    "写出文件": "寫出文件",
+    "第二组插件": "第二組插件",
+    "在多Tex文档中": "在多Tex文檔中",
+    "有线程锁": "有線程鎖",
+    "释放线程锁": "釋放線程鎖",
+    "读取优先级": "讀取優先級",
+    "Linux下必须使用Docker安装": "Linux下必須使用Docker安裝",
+    "例如您可以将以下命令复制到下方": "例如您可以將以下命令複製到下方",
+    "导入依赖失败": "導入依賴失敗",
+    "给出一些判定模板文档的词作为扣分项": "給出一些判定模板文檔的詞作為扣分項",
+    "等待Claude响应中": "等待Claude響應中",
+    "Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数": "Call ChatGLMFT fail 不能正常加載ChatGLMFT的參數",
+    "但本地存储了以下历史文件": "但本地存儲了以下歷史文件",
+    "如果存在调试缓存文件": "如果存在調試緩存文件",
+    "如果这里抛出异常": "如果這裡拋出異常",
+    "详见项目主README.md": "詳見項目主README.md",
+    "作者": "作者",
+    "现在您点击任意“红颜色”标识的函数插件时": "現在您點擊任意“紅顏色”標識的函數插件時",
+    "上下文管理器必须实现两个方法": "上下文管理器必須實現兩個方法",
+    "匹配^数字^": "匹配^數字^",
+    "也是可读的": "也是可讀的",
+    "将音频解析为简体中文": "將音頻解析為簡體中文",
+    "依次访问网页": "依次訪問網頁",
+    "P.S. 顺便把CTEX塞进去以支持中文": "P.S. 順便把CTEX塞進去以支持中文",
+    "NewBing响应异常": "NewBing響應異常",
+    "获取已打开频道的最新消息并返回消息列表": "獲取已打開頻道的最新消息並返回消息列表",
+    "请使用Markdown": "請使用Markdown",
+    "例如 RoPlZrM88DnAFkZK": "例如 RoPlZrM88DnAFkZK",
+    "编译BibTex": "編譯BibTex",
+    "Claude失败": "Claude失敗",
+    "请更换为API_URL_REDIRECT配置": "請更換為API_URL_REDIRECT配置",
+    "P.S. 其他可用的模型还包括": "P.S. 其他可用的模型還包括",
+    "色彩主体": "色彩主體",
+    "后面是英文逗号": "後面是英文逗號",
+    "下载pdf文件未成功": "下載pdf文件未成功",
+    "删除整行的空注释": "刪除整行的空注釋",
+    "吸收匿名公式": "吸收匿名公式",
+    "从而更全面地理解项目的整体功能": "從而更全面地理解項目的整體功能",
+    "不需要再次转化": "不需要再次轉化",
+    "可以将自身的状态存储到cookie中": "可以將自身的狀態存儲到cookie中",
+    "1、英文题目；2、中文题目翻译；3、作者；4、arxiv公开": "1、英文題目；2、中文題目翻譯；3、作者；4、arxiv公開",
+    "GPT 学术优化": "GPT 學術優化",
+    "解析整个Python项目": "解析整個Python項目",
+    "吸收其他杂项": "吸收其他雜項",
+    "-预热文本向量化模组": "-預熱文本向量化模組",
+    "Claude组件初始化成功": "Claude組件初始化成功",
+    "此处填API密钥": "此處填API密鑰",
+    "请继续分析其他源代码": "請繼續分析其他源代碼",
+    "质能方程式": "質能方程式",
+    "功能尚不稳定": "功能尚不穩定",
+    "使用教程详情见 request_llm/README.md": "使用教程詳情見 request_llm/README.md",
+    "从以上搜索结果中抽取信息": "從以上搜索結果中抽取信息",
+    "虽然PDF生成失败了": "雖然PDF生成失敗了",
+    "找图片": "尋找圖片",
+    "还原原文": "還原原文",
+    "可调节线程池的大小避免openai的流量限制错误": "可調整線程池大小以避免openai流量限制錯誤",
+    "正在提取摘要并下载PDF文档……": "正在提取摘要並下載PDF文件......",
+    "缺少ChatGLMFT的依赖": "缺少ChatGLMFT的依賴",
+    "不会实时显示在界面上": "不會即時顯示在界面上",
+    "解决部分词汇翻译不准确的问题": "解決部分詞彙翻譯不準確的問題",
+    "等待多线程操作": "等待多線程操作",
+    "吸收title与作者以上的部分": "吸收標題與作者以上的部分",
+    "如果需要使用Slack Claude": "如果需要使用Slack Claude",
+    "一、论文概况": "一、論文概況",
+    "默认为Chinese": "默認為中文",
+    "图像生成所用到的提示文本": "圖像生成所用到的提示文本",
+    "向已打开的频道发送一条文本消息": "向已打開的頻道發送一條文本消息",
+    "如果某个子任务出错": "如果某個子任務出錯",
+    "chatglmft 没有 sys_prompt 接口": "chatglmft沒有sys_prompt接口",
+    "对比PDF编译是否成功": "對比PDF編譯是否成功",
+    "免费": "免費",
+    "请讲话": "請講話",
+    "安装ChatGLM的依赖": "安裝ChatGLM的依賴",
+    "对IPynb文件进行解析": "對IPynb文件進行解析",
+    "文件路径列表": "文件路徑列表",
+    "或者使用此插件继续上传更多文件": "或者使用此插件繼續上傳更多文件",
+    "随机负载均衡": "隨機負載均衡",
+    "！！！如果需要运行量化版本": "！！！如果需要運行量化版本",
+    "注意目前不能多人同时调用Claude接口": "注意目前不能多人同時調用Claude接口",
+    "文件读取完成": "文件讀取完成",
+    "用于灵活调整复杂功能的各种参数": "用於靈活調整複雜功能的各種參數",
+    "**函数功能**": "**函數功能**",
+    "先切换模型到openai或api2d": "先切換模型到openai或api2d",
+    "You are associated with a deactivated account. OpenAI以账户失效为由": "您的帳戶已停用。OpenAI以帳戶失效為由",
+    "你的回答必须简单明了": "您的回答必須簡單明了",
+    "是否丢弃掉 不是正文的内容": "是否丟棄掉 不是正文的內容",
+    "但请查收结果": "但請查收結果",
+    "Claude响应缓慢": "Claude響應緩慢",
+    "需Latex": "需Latex",
+    "Claude回复的片段": "Claude回復的片段",
+    "如果要使用ChatGLMFT": "如果要使用ChatGLMFT",
+    "它*必须*被包含在AVAIL_LLM_MODELS列表中": "它*必須*被包含在AVAIL_LLM_MODELS列表中",
+    "前面是中文逗号": "前面是中文逗號",
+    "需要预先pip install py7zr": "需要預先pip install py7zr",
+    "将前后断行符脱离": "將前後斷行符脫離",
+    "防止丢失最后一条消息": "防止丟失最後一條消息",
+    "初始化插件状态": "初始化插件狀態",
+    "以秒为单位": "以秒為單位",
+    "中文Latex项目全文润色": "中文Latex項目全文潤色",
+    "对整个Latex项目进行纠错": "對整個Latex項目進行校對",
+    "NEWBING_COOKIES未填写或有格式错误": "NEWBING_COOKIES未填寫或有格式錯誤",
+    "函数插件作者": "函數插件作者",
+    "结束": "結束",
+    "追加历史": "追加歷史",
+    "您需要首先调用构建知识库": "您需要首先調用構建知識庫",
+    "如果程序停顿5分钟以上": "如果程序停頓5分鐘以上",
+    "ChatGLMFT响应异常": "ChatGLMFT響應異常",
+    "根据当前的模型类别": "根據當前的模型類別",
+    "才能继续下面的步骤": "才能繼續下面的步驟",
+    "并将返回的频道ID保存在属性CHANNEL_ID中": "並將返回的頻道ID保存在屬性CHANNEL_ID中",
+    "请查收结果": "請查收結果",
+    "解决插件锁定时的界面显示问题": "解決插件鎖定時的界面顯示問題",
+    "待提取的知识库名称id": "待提取的知識庫名稱id",
+    "Claude响应异常": "Claude響應異常",
+    "当前代理可用性": "當前代理可用性",
+    "代理网络配置": "代理網絡配置",
+    "我将为您查找相关壁纸": "我將為您查找相關壁紙",
+    "没给定指令": "沒給定指令",
+    "音频内容是": "音頻內容是",
+    "用该压缩包+ConversationHistoryArchive进行反馈": "用該壓縮包+ConversationHistoryArchive進行反饋",
+    "总结音频": "總結音頻",
+    "等待用户的再次调用": "等待用戶的再次調用",
+    "永远给定None": "永遠給定None",
+    "论文概况": "論文概況",
+    "建议使用英文单词": "建議使用英文單詞",
+    "刷新Gradio前端界面": "刷新Gradio前端界面",
+    "列表递归接龙": "列表遞歸接龍",
+    "赋予插件状态": "賦予插件狀態",
+    "构建完成": "構建完成",
+    "避免多用户干扰": "避免多用戶干擾",
+    "当前工作路径为": "當前工作路徑為",
+    "用黑色标注转换区": "用黑色標注轉換區",
+    "压缩包": "壓縮包",
+    "刷新页面即可以退出KnowledgeBaseQA模式": "刷新頁面即可以退出KnowledgeBaseQA模式",
+    "拆分过长的Markdown文件": "拆分過長的Markdown文件",
+    "生成时间戳": "生成時間戳",
+    "尚未完成全部响应": "尚未完成全部響應",
+    "HotReload的装饰器函数": "HotReload的裝飾器函數",
+    "请务必用 pip install -r requirements.txt 指令安装依赖": "請務必用 pip install -r requirements.txt 指令安裝依賴",
+    "TGUI不支持函数插件的实现": "TGUI不支持函數插件的實現",
+    "音频文件名": "音頻文件名",
+    "找不到任何音频或视频文件": "找不到任何音頻或視頻文件",
+    "音频解析结果": "音頻解析結果",
+    "如果使用ChatGLM2微调模型": "如果使用ChatGLM2微調模型",
+    "限制的3/4时": "限制的3/4時",
+    "获取回复": "獲取回復",
+    "对话历史写入": "對話歷史寫入",
+    "记录删除注释后的文本": "記錄刪除註釋後的文本",
+    "整理结果为压缩包": "整理結果為壓縮包",
+    "注意事项": "注意事項",
+    "请耐心等待": "請耐心等待",
+    "在执行完成之后": "在執行完成之後",
+    "参数简单": "參數簡單",
+    "Arixv论文精细翻译": "Arixv論文精細翻譯",
+    "备份和下载": "備份和下載",
+    "当前报错的latex代码处于第": "當前報錯的latex代碼處於第",
+    "Markdown翻译": "Markdown翻譯",
+    "英文Latex项目全文纠错": "英文Latex項目全文校對",
+    "获取预处理函数": "獲取預處理函數",
+    "add gpt task 创建子线程请求gpt": "add gpt task 創建子線程請求gpt",
+    "一个包含所有切割音频片段文件路径的列表": "一個包含所有切割音頻片段文件路徑的列表",
+    "解析arxiv网址失败": "解析arxiv網址失敗",
+    "PDF文件所在的路径": "PDF文件所在路徑",
+    "取评分最高者返回": "取評分最高者返回",
+    "此插件处于开发阶段": "此插件處於開發階段",
+    "如果已经存在": "如果已經存在",
+    "或者不在环境变量PATH中": "或者不在環境變量PATH中",
+    "目前支持的格式": "目前支持的格式",
+    "将多文件tex工程融合为一个巨型tex": "將多文件tex工程融合為一個巨型tex",
+    "暂不提交": "暫不提交",
+    "调用函数": "調用函數",
+    "编译转化后的PDF": "編譯轉化後的PDF",
+    "将代码转为动画": "將代碼轉為動畫",
+    "本地Latex论文精细翻译": "本地Latex論文精細翻譯",
+    "删除或修改歧义文件": "刪除或修改歧義文件",
+    "其他操作系统表现未知": "其他操作系統表現未知",
+    "此插件Windows支持最佳": "此插件Windows支持最佳",
+    "构建知识库": "構建知識庫",
+    "每个切割音频片段的时长": "每個切割音頻片段的時長",
+    "用latex编译为PDF对修正处做高亮": "用latex編譯為PDF對修正處做高亮",
+    "行": "行",
+    "= 2 通过一些Latex模板中常见": "= 2 通過一些Latex模板中常見",
+    "如参考文献、脚注、图注等": "如參考文獻、腳註、圖註等",
+    "期望格式例如": "期望格式例如",
+    "翻译内容可靠性无保障": "翻譯內容可靠性無保障",
+    "请用一句话概括这些文件的整体功能": "請用一句話概括這些文件的整體功能",
+    "段音频完成了吗": "段音頻完成了嗎",
+    "填入azure openai api的密钥": "填入azure openai api的密鑰",
+    "文本碎片重组为完整的tex片段": "文本碎片重組為完整的tex片段",
+    "吸收在42行以內的begin-end組合": "吸收在42行以內的begin-end組合",
+    "屬性": "屬性",
+    "必須包含documentclass": "必須包含documentclass",
+    "等待GPT響應": "等待GPT響應",
+    "當前語言模型溫度設定": "當前語言模型溫度設定",
+    "模型選擇是": "選擇的模型為",
+    "reverse 操作必須放在最後": "reverse 操作必須放在最後",
+    "將子線程的gpt結果寫入chatbot": "將子線程的gpt結果寫入chatbot",
+    "默認為default": "默認為default",
+    "目前對機器學習類文獻轉化效果最好": "目前對機器學習類文獻轉化效果最好",
+    "主程序即將開始": "主程序即將開始",
+    "點擊“停止”鍵可終止程序": "點擊“停止”鍵可終止程序",
+    "正在處理": "正在處理",
+    "請立即終止程序": "請立即停止程序",
+    "將 chatglm 直接對齊到 chatglm2": "將 chatglm 直接對齊到 chatglm2",
+    "音頻助手": "音頻助手",
+    "正在構建知識庫": "正在構建知識庫",
+    "請向下翻": "請向下滾動頁面",
+    "後面是英文冒號": "後面是英文冒號",
+    "無法找到一個主Tex文件": "無法找到一個主Tex文件",
+    "使用中文总结音频“": "使用中文總結音頻",
+    "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": "該PDF由GPT-Academic開源項目調用大語言模型+Latex翻譯插件一鍵生成",
+    "开始生成动画": "開始生成動畫",
+    "完成情况": "完成情況",
+    "然后进行问答": "然後進行問答",
+    "为啥chatgpt会把cite里面的逗号换成中文逗号呀": "為啥chatgpt會把cite裡面的逗號換成中文逗號呀",
+    "暂时不支持历史消息": "暫時不支持歷史消息",
+    "项目Github地址 \\url{https": "項目Github地址 \\url{https",
+    "Newbing 请求失败": "Newbing 請求失敗",
+    "根据自然语言执行插件命令": "根據自然語言執行插件命令",
+    "迭代上一次的结果": "迭代上一次的結果",
+    "azure和api2d请求源": "azure和api2d請求源",
+    "格式如org-xxxxxxxxxxxxxxxxxxxxxxxx": "格式如org-xxxxxxxxxxxxxxxxxxxxxxxx",
+    "推荐http": "推薦http",
+    "将要匹配的模式": "將要匹配的模式",
+    "代理数据解析失败": "代理數據解析失敗",
+    "创建存储切割音频的文件夹": "創建存儲切割音頻的文件夾",
+    "用红色标注处保留区": "用紅色標注處保留區",
+    "至少一个线程任务Token溢出而失败": "至少一個線程任務Token溢出而失敗",
+    "获取Slack消息失败": "獲取Slack消息失敗",
+    "极少数情况下": "極少數情況下",
+    "辅助gpt生成代码": "輔助gpt生成代碼",
+    "生成图像": "生成圖像",
+    "最多收纳多少个网页的结果": "最多收納多少個網頁的結果",
+    "获取图片URL": "獲取圖片URL",
+    "正常状态": "正常狀態",
+    "编译原始PDF": "編譯原始PDF",
+    "SummarizeAudioAndVideo内容": "音視頻摘要內容",
+    "Latex文件融合完成": "Latex文件融合完成",
+    "获取线程锁": "獲取線程鎖",
+    "SlackClient类用于与Slack API进行交互": "SlackClient類用於與Slack API進行交互",
+    "检测到arxiv文档连接": "檢測到arxiv文檔連接",
+    "--读取参数": "--讀取參數",
+    "如果您是论文原作者": "如果您是論文原作者",
+    "5刀": "5美元",
+    "转化PDF编译是否成功": "轉換PDF編譯是否成功",
+    "生成带有段落标签的HTML代码": "生成帶有段落標籤的HTML代碼",
+    "目前不支持历史消息查询": "目前不支持歷史消息查詢",
+    "将文件添加到chatbot cookie中": "將文件添加到chatbot cookie中",
+    "多线程操作已经开始": "多線程操作已經開始",
+    "请求子进程": "請求子進程",
+    "将Unsplash API中的PUT_YOUR_QUERY_HERE替换成描述该事件的一个最重要的单词": "將Unsplash API中的PUT_YOUR_QUERY_HERE替換成描述該事件的一個最重要的單詞",
+    "不能加载Claude组件": "不能加載Claude組件",
+    "请仔细鉴别并以原文为准": "請仔細鑒別並以原文為準",
+    "否则结束循环": "否則結束循環",
+    "插件可读取“输入区”文本/路径作为参数": "插件可讀取“輸入區”文本/路徑作為參數",
+    "网络错误": "網絡錯誤",
+    "想象一个穿着者": "想像一個穿著者",
+    "避免遗忘导致死锁": "避免遺忘導致死鎖",
+    "保证括号正确": "保證括號正確",
+    "报错信息": "錯誤信息",
+    "提取视频中的音频": "提取視頻中的音頻",
+    "初始化音频采集线程": "初始化音頻採集線程",
+    "参考文献转Bib": "參考文獻轉Bib",
+    "阿里云实时语音识别 配置难度较高 仅建议高手用户使用 参考 https": "阿里云即時語音識別配置難度較高，僅建議高手用戶使用，參考 https",
+    "使用时": "使用時",
+    "处理个别特殊插件的锁定状态": "處理個別特殊插件的鎖定狀態",
+    "但通常不会出现在正文": "但通常不會出現在正文",
+    "此函数逐渐地搜索最长的条目进行剪辑": "此函數逐漸地搜索最長的條目進行剪輯",
+    "给出指令": "給出指令",
+    "读取音频文件": "讀取音頻文件",
+    "========================================= 插件主程序1 =====================================================": "========================================= 插件主程序1 =====================================================",
+    "带超时倒计时": "帶超時倒計時",
+    "禁止移除或修改此警告": "禁止移除或修改此警告",
+    "ChatGLMFT尚未加载": "ChatGLMFT尚未加載",
+    "双手离开鼠标键盘吧": "雙手離開鼠標鍵盤吧",
+    "缺少的依赖": "缺少的依賴",
+    "的单词": "的單詞",
+    "中读取数据构建知识库": "中讀取數據構建知識庫",
+    "函数热更新是指在不停止程序运行的情况下": "函數熱更新是指在不停止程序運行的情況下",
+    "建议低于1": "建議低於1",
+    "转化PDF编译已经成功": "轉換PDF編譯已經成功",
+    "出问题了": "出問題了",
+    "欢迎使用 MOSS 人工智能助手！": "歡迎使用 MOSS 人工智能助手！",
+    "正在精细切分latex文件": "正在精細切分LaTeX文件",
+    "”补上": "”補上",
+    "网络代理状态": "網路代理狀態",
+    "依赖检测通过": "依賴檢測通過",
+    "默认为default": "預設為default",
+    "Call MOSS fail 不能正常加载MOSS的参数": "呼叫MOSS失敗，無法正常載入MOSS參數",
+    "音频助手": "音頻助手",
+    "次编译": "次編譯",
+    "其他错误": "其他錯誤",
+    "属性": "屬性",
+    "主程序即将开始": "主程式即將開始",
+    "Aliyun音频服务异常": "Aliyun音頻服務異常",
+    "response中会携带traceback报错信息": "response中會攜帶traceback錯誤信息",
+    "一些普通功能模块": "一些普通功能模組",
+    "和openai的连接容易断掉": "和openai的連線容易斷掉",
+    "请检查ALIYUN_TOKEN和ALIYUN_APPKEY是否过期": "請檢查ALIYUN_TOKEN和ALIYUN_APPKEY是否過期",
+    "调用Claude时": "呼叫Claude時",
+    "插件锁定中": "插件鎖定中",
+    "将子线程的gpt结果写入chatbot": "將子線程的gpt結果寫入chatbot",
+    "当下一次用户提交时": "當下一次使用者提交時",
+    "先上传数据集": "先上傳資料集",
+    "请在此处追加更细致的矫错指令": "請在此處追加更細緻的矯錯指令",
+    "无法找到一个主Tex文件": "無法找到一個主Tex文件",
+    "gpt写的": "gpt寫的",
+    "预处理": "預處理",
+    "但大部分场合下并不需要修改": "但大部分場合下並不需要修改",
+    "正在构建知识库": "正在建構知識庫",
+    "开始请求": "開始請求",
+    "根据以上分析": "根據以上分析",
+    "需要特殊依赖": "需要特殊依賴",
+    "用于基础的对话功能": "用於基礎的對話功能",
+    "且没有代码段": "且沒有程式碼段",
+    "取决于": "取決於",
+    "openai的官方KEY需要伴隨組織編碼": "請填入組織編碼",
+    "等待newbing回覆的片段": "等待newbing回覆的片段",
+    "调用缓存": "呼叫快取",
+    "模型选择是": "模型選擇為",
+    "当前大语言模型": "當前大語言模型",
+    "然后转移到指定的另一个路径中": "然後轉移到指定的另一個路徑中",
+    "请向下翻": "請向下滾動",
+    "内容太长了都会触发token数量溢出的错误": "內容太長會觸發token數量溢出的錯誤",
+    "每一块": "每一塊",
+    "详情信息见requirements.txt": "詳細信息見requirements.txt",
+    "没有提供高级参数功能说明": "沒有提供高級參數功能說明",
+    "上传Latex项目": "上傳Latex項目",
+    "请立即终止程序": "請立即終止程式",
+    "解除插件锁定": "解除插件鎖定",
+    "意外Json结构": "意外Json結構",
+    "必须包含documentclass": "必須包含documentclass",
+    "10个文件为一组": "10個文件為一組",
+    "openai的官方KEY需要伴随组织编码": "openai的官方KEY需要伴隨組織編碼",
+    "重置文件的创建时间": "重置文件的創建時間",
+    "尽量是完整的一个section": "盡量是完整的一個section",
+    "报告如何远程获取": "報告如何遠程獲取",
+    "work_folder = Latex预处理": "work_folder = Latex預處理",
+    "吸收在42行以内的begin-end组合": "吸收在42行以內的begin-end組合",
+    "后面是英文冒号": "後面是英文冒號",
+    "使用latexdiff生成论文转化前后对比": "使用latexdiff生成論文轉化前後對比",
+    "首先你在英文语境下通读整篇论文": "首先你在英文語境下通讀整篇論文",
+    "为了防止大语言模型的意外谬误产生扩散影响": "為了防止大語言模型的意外謬誤產生擴散影響",
+    "发现已经存在翻译好的PDF文档": "發現已經存在翻譯好的PDF文檔",
+    "点击“停止”键可终止程序": "點擊“停止”鍵可終止程序",
+    "数学GenerateAnimations": "數學GenerateAnimations",
+    "随变按钮的回调函数注册": "隨變按鈕的回調函數註冊",
+    "history至少释放二分之一": "history至少釋放二分之一",
+    "当前语言模型温度设定": "當前語言模型溫度設定",
+    "等待GPT响应": "等待GPT響應",
+    "正在处理": "正在處理",
+    "多线程翻译开始": "多線程翻譯開始",
+    "reverse 操作必须放在最后": "reverse 操作必須放在最後",
+    "等待newbing回复的片段": "等待newbing回覆的片段",
+    "开始下载": "開始下載",
+    "将 chatglm 直接对齐到 chatglm2": "將 chatglm 直接對齊到 chatglm2",
+    "以上材料已经被写入": "以上材料已經被寫入",
+    "上传文件自动修正路径": "上傳文件自動修正路徑",
+    "然后请使用Markdown格式封装": "然後請使用Markdown格式封裝",
+    "目前对机器学习类文献转化效果最好": "目前對機器學習類文獻轉化效果最好",
+    "检查结果": "檢查結果",
+    "、地址": "地址",
+    "如.md": "如.md",
+    "使用Unsplash API": "使用Unsplash API",
+    "**输入参数说明**": "**輸入參數說明**",
+    "新版本可用": "新版本可用",
+    "找不到任何python文件": "找不到任何python文件",
+    "知乎": "知乎",
+    "日": "日",
+    "“喂狗”": "“喂狗”",
+    "第4步": "第4步",
+    "退出": "退出",
+    "使用 Unsplash API": "使用 Unsplash API"
 }

docs/use_audio.md

@@ -0,0 +1,54 @@
+# 使用音频交互功能
+
+
+## 1. 安装额外依赖
+```
+pip install --upgrade pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
+```
+
+如果因为特色网络问题导致上述命令无法执行：
+1. git clone alibabacloud-nls-python-sdk这个项目（或者直接前往Github对应网址下载压缩包）.
+命令行输入： `git clone https://github.com/aliyun/alibabacloud-nls-python-sdk.git`
+1. 进入alibabacloud-nls-python-sdk目录命令行输入：`python setup.py install`
+
+
+## 2. 配置音频功能开关 和 阿里云APPKEY（config.py/config_private.py/环境变量）
+
+- 注册阿里云账号
+- 开通 智能语音交互 （有免费白嫖时长）
+- 获取token和appkey
+- 未来将逐步用其他更廉价的云服务取代阿里云
+
+```
+ENABLE_AUDIO = True
+ALIYUN_TOKEN = "554a50fcd0bb476c8d07bb630e94d20c"    # 此token已经失效
+ALIYUN_APPKEY = "RoPlZrM88DnAFkZK"   # 此appkey已经失效
+```
+
+参考 https://help.aliyun.com/document_detail/450255.html
+先有阿里云开发者账号，登录之后，需要开通 智能语音交互 的功能，可以免费获得一个token，然后在 全部项目 中，创建一个项目，可以获得一个appkey.
+
+## 3.启动
+
+启动gpt-academic `python main.py`
+
+## 4.点击record from microphe，授权音频采集
+
+I 如果需要监听自己说话（不监听电脑音频），直接在浏览器中选择对应的麦即可
+
+II 如果需要监听电脑音频（不监听自己说话），需要安装`VB-Audio VoiceMeeter`，打开声音控制面板(sound control panel)
+- 1 `[把电脑的所有外放声音用VoiceMeeter截留]` 在输出区（playback）选项卡，把VoiceMeeter Input虚拟设备set as default设为默认播放设备。
+- 2 `[把截留的声音释放到gpt-academic]` 打开gpt-academic主界面，授权音频采集后，在浏览器地址栏或者类似的地方会出现一个麦克风图标，打开后，按照浏览器的提示，选择VoiceMeeter虚拟麦克风。然后刷新页面，重新授权音频采集。
+- 3 `[把截留的声音同时释放到耳机或音响]` 完成第一步之后，您应处于听不到电脑声音的状态。为了在截获音频的同时，避免影响正常使用，请完成这最后一步配置。在声音控制面板(sound control panel)输入区（recording）选项卡，把VoiceMeeter Output虚拟设备set as default。双击进入VoiceMeeter Output虚拟设备的设置。
+  - 3-1 进入VoiceMeeter Output虚拟设备子菜单，打开listen选项卡。
+  - 3-2 勾选Listen to this device。
+  - 3-3 在playback through this device下拉菜单中选择你的正常耳机或音响。
+
+III `[把特殊软件（如腾讯会议）的外放声音用VoiceMeeter截留]` 在完成步骤II的基础上，在特殊软件（如腾讯会议）中，打开声音菜单，选择扬声器VoiceMeeter Input，选择麦克风为正常耳机麦。
+
+VI 两种音频监听模式切换时，需要刷新页面才有效。
+
+## 5.点击函数插件区“实时音频采集” 或者其他音频交互功能
+
+
+

docs/use_azure.md

@@ -90,62 +90,29 @@
 
 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）
+● 密钥（对应AZURE_API_KEY，1或2都可以）
 
-● 终结点
+● 终结点 （对应AZURE_ENDPOINT）
+
+● 部署名（对应AZURE_ENGINE，不是模型名）
 
-● 部署名（不是模型名）
 
 # 修改 config.py
 
 ```
-AZURE_ENDPOINT = "填入终结点"
+LLM_MODEL = "azure-gpt-3.5"  # 指定启动时的默认模型，当然事后从下拉菜单选也ok
+
+AZURE_ENDPOINT = "填入终结点" # 见上述图片
 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'])
+AZURE_ENGINE = "填入部署名" # 见上述图片
 
 ```
 
-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：
-
-![image.png](https://note.youdao.com/yws/res/18095/WEBRESOURCEeba0ab6d3127b79e143ef2d5627c0e44)
+Azure OpenAI API 还是需要一些费用的（免费订阅只有1个月有效期）
 
 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)
 

docs/waifu_plugin/autoload.js

@@ -12,7 +12,7 @@ try {
             live2d_settings['waifuTipsSize']        = '187x52';  
             live2d_settings['canSwitchModel']       = true;
             live2d_settings['canSwitchTextures']    = true;
-            live2d_settings['canSwitchHitokoto']    = true;
+            live2d_settings['canSwitchHitokoto']    = false;
             live2d_settings['canTakeScreenshot']    = false;
             live2d_settings['canTurnToHomePage']    = false;
             live2d_settings['canTurnToAboutPage']   = false;

docs/waifu_plugin/waifu-tips.json

@@ -34,10 +34,10 @@
             "2": ["来自 Potion Maker 的 Tia 酱 ~"]  
         },
         "hitokoto_api_message": {
-            "lwl12.com": ["这句一言来自 <span style=\"color:#ff99da;\">『{source}』</span>", "，是 <span style=\"color:#ff99da;\">{creator}</span> 投稿的", "。"],
-            "fghrsh.net": ["这句一言出处是 <span style=\"color:#ff99da;\">『{source}』</span>，是 <span style=\"color:#ff99da;\">FGHRSH</span> 在 {date} 收藏的！"],
-            "jinrishici.com": ["这句诗词出自 <span style=\"color:#ff99da;\">《{title}》</span>，是 {dynasty}诗人 {author} 创作的！"],
-            "hitokoto.cn": ["这句一言来自 <span style=\"color:#ff99da;\">『{source}』</span>，是 <span style=\"color:#ff99da;\">{creator}</span> 在 hitokoto.cn 投稿的。"]
+            "lwl12.com": ["这句一言来自 <span style=\"color:#0099cc;\">『{source}』</span>", "，是 <span style=\"color:#0099cc;\">{creator}</span> 投稿的", "。"],
+            "fghrsh.net": ["这句一言出处是 <span style=\"color:#0099cc;\">『{source}』</span>，是 <span style=\"color:#0099cc;\">FGHRSH</span> 在 {date} 收藏的！"],
+            "jinrishici.com": ["这句诗词出自 <span style=\"color:#0099cc;\">《{title}》</span>，是 {dynasty}诗人 {author} 创作的！"],
+            "hitokoto.cn": ["这句一言来自 <span style=\"color:#0099cc;\">『{source}』</span>，是 <span style=\"color:#0099cc;\">{creator}</span> 在 hitokoto.cn 投稿的。"]
         }
     },
     "mouseover": [

func_box.py

@@ -1,778 +0,0 @@
-#! .\venv\
-# encoding: utf-8
-# @Time   : 2023/4/18
-# @Author : Spike
-# @Descr   :
-import ast
-import copy
-import hashlib
-import io
-import json
-import os.path
-import subprocess
-import threading
-import time
-from concurrent.futures import ThreadPoolExecutor
-import Levenshtein
-import psutil
-import re
-import tempfile
-import shutil
-from contextlib import ExitStack
-import logging
-import yaml
-import requests
-import tiktoken
-logger = logging
-from sklearn.feature_extraction.text import CountVectorizer
-import numpy as np
-from scipy.linalg import norm
-import pyperclip
-import random
-import gradio as gr
-import toolbox
-from prompt_generator import SqliteHandle
-from bs4 import BeautifulSoup
-import copy
-
-"""contextlib 是 Python 标准库中的一个模块，提供了一些工具函数和装饰器，用于支持编写上下文管理器和处理上下文的常见任务，例如资源管理、异常处理等。
-官网：https://docs.python.org/3/library/contextlib.html"""
-
-
-class Shell(object):
-    def __init__(self, args, stream=False):
-        self.args = args
-        self.subp = subprocess.Popen(args, shell=True,
-                                     stdin=subprocess.PIPE, stderr=subprocess.PIPE,
-                                     stdout=subprocess.PIPE, encoding='utf-8',
-                                     errors='ignore', close_fds=True)
-        self.__stream = stream
-        self.__temp = ''
-
-    def read(self):
-        logger.debug(f'The command being executed is: "{self.args}"')
-        if self.__stream:
-            sysout = self.subp.stdout
-            try:
-                with sysout as std:
-                    for i in std:
-                        logger.info(i.rstrip())
-                        self.__temp += i
-            except KeyboardInterrupt as p:
-                return 3, self.__temp + self.subp.stderr.read()
-            finally:
-                return 3, self.__temp + self.subp.stderr.read()
-        else:
-            sysout = self.subp.stdout.read()
-            syserr = self.subp.stderr.read()
-            self.subp.stdin
-            if sysout:
-                logger.debug(f"{self.args} \n{sysout}")
-                return 1, sysout
-            elif syserr:
-                logger.error(f"{self.args} \n{syserr}")
-                return 0, syserr
-            else:
-                logger.debug(f"{self.args} \n{[sysout], [sysout]}")
-                return 2, '\n{}\n{}'.format(sysout, sysout)
-
-    def sync(self):
-        logger.debug('The command being executed is: "{}"'.format(self.args))
-        for i in self.subp.stdout:
-            logger.debug(i.rstrip())
-            self.__temp += i
-            yield self.__temp
-        for i in self.subp.stderr:
-            logger.debug(i.rstrip())
-            self.__temp += i
-            yield self.__temp
-
-
-def timeStatistics(func):
-    """
-    统计函数执行时常的装饰器
-    """
-
-    def statistics(*args, **kwargs):
-        startTiem = time.time()
-        obj = func(*args, **kwargs)
-        endTiem = time.time()
-        ums = startTiem - endTiem
-        print('func:{} > Time-consuming: {}'.format(func, ums))
-        return obj
-
-    return statistics
-
-
-def copy_temp_file(file):
-    if os.path.exists(file):
-        exdir = tempfile.mkdtemp()
-        temp_ = shutil.copy(file, os.path.join(exdir, os.path.basename(file)))
-        return temp_
-    else:
-        return None
-
-
-def md5_str(st):
-    # 创建一个 MD5 对象
-    md5 = hashlib.md5()
-    # 更新 MD5 对象的内容
-    md5.update(str(st).encode())
-    # 获取加密后的结果
-    result = md5.hexdigest()
-    return result
-
-
-def html_tag_color(tag, color=None, font='black'):
-    """
-    将文本转换为带有高亮提示的html代码
-    """
-    if not color:
-        rgb = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
-        color = f"rgb{rgb}"
-    tag = f'<span style="background-color: {color}; font-weight: bold; color: {font}">&nbsp;{tag}&ensp;</span>'
-    return tag
-
-def html_a_blank(__href, name=''):
-    if not name:
-        name = __href
-    a = f'<a href="{__href}" target="_blank" class="svelte-xrr240">{name}</a>'
-    return a
-
-def html_view_blank(__href, file_name=''):
-    if os.path.exists(__href):
-        __href = f'/file={__href}'
-    if not file_name:
-        file_name = __href.split('/')[-1]
-    a = f'<a href="{__href}" target="_blank" class="svelte-xrr240">{file_name}</a>'
-    return a
-
-def html_iframe_code(html_file):
-    proxy, = toolbox.get_conf('LOCAL_PORT')
-    html_file = f'http://{ipaddr()}:{proxy}/file={html_file}'
-    ifr = f'<iframe width="100%" height="500px" frameborder="0" src="{html_file}"></iframe>'
-    return ifr
-
-
-def html_download_blank(__href, file_name='temp', dir_name=''):
-    if os.path.exists(__href):
-        __href = f'/file={__href}'
-    if not dir_name:
-        dir_name = file_name
-    a = f'<a href="{__href}" target="_blank" download="{dir_name}" class="svelte-xrr240">{file_name}</a>'
-    return a
-
-def html_local_img(__file):
-    a = f'<div align="center"><img src="file={__file}"></div>'
-    return a
-
-def ipaddr():
-    # 获取本地ipx
-    ip = psutil.net_if_addrs()
-    for i in ip:
-        if ip[i][0][3]:
-            return ip[i][0][1]
-
-
-def encryption_str(txt: str):
-    """(关键字)(加密间隔)匹配机制（关键字间隔）"""
-    txt = str(txt)
-    pattern = re.compile(rf"(Authorization|WPS-Sid|Cookie)(:|\s+)\s*(\S+)[\s\S]*?(?=\n|$|\s)", re.IGNORECASE)
-    result = pattern.sub(lambda x: x.group(1) + ": XXXXXXXX", txt)
-    return result
-
-
-def tree_out(dir=os.path.dirname(__file__), line=2, more=''):
-    """
-    获取本地文件的树形结构转化为Markdown代码文本
-    """
-    out = Shell(f'tree {dir} -F -I "__*|.*|venv|*.png|*.xlsx" -L {line} {more}').read()[1]
-    localfile = os.path.join(os.path.dirname(__file__), '.tree.md')
-    with open(localfile, 'w') as f:
-        f.write('```\n')
-        ll = out.splitlines()
-        for i in range(len(ll)):
-            if i == 0:
-                f.write(ll[i].split('/')[-2] + '\n')
-            else:
-                f.write(ll[i] + '\n')
-        f.write('```\n')
-
-
-def chat_history(log: list, split=0):
-    """
-    auto_gpt 使用的代码，后续会迁移
-    """
-    if split:
-        log = log[split:]
-    chat = ''
-    history = ''
-    for i in log:
-        chat += f'{i[0]}\n\n'
-        history += f'{i[1]}\n\n'
-    return chat, history
-
-
-def df_similarity(s1, s2):
-    """弃用，会警告，这个库不会用"""
-    def add_space(s):
-        return ' '.join(list(s))
-
-    # 将字中间加入空格
-    s1, s2 = add_space(s1), add_space(s2)
-    # 转化为TF矩阵
-    cv = CountVectorizer(tokenizer=lambda s: s.split())
-    corpus = [s1, s2]
-    vectors = cv.fit_transform(corpus).toarray()
-    # 计算TF系数
-    return np.dot(vectors[0], vectors[1]) / (norm(vectors[0]) * norm(vectors[1]))
-
-
-def check_json_format(file):
-    """
-    检查上传的Json文件是否符合规范
-    """
-    new_dict = {}
-    data = JsonHandle(file).load()
-    if type(data) is list and len(data) > 0:
-        if type(data[0]) is dict:
-            for i in data:
-                new_dict.update({i['act']: i['prompt']})
-    return new_dict
-
-
-def json_convert_dict(file):
-    """
-    批量将json转换为字典
-    """
-    new_dict = {}
-    for root, dirs, files in os.walk(file):
-        for f in files:
-            if f.startswith('prompt') and f.endswith('json'):
-                new_dict.update(check_json_format(f))
-    return new_dict
-
-
-def draw_results(txt, prompt: gr.Dataset, percent, switch, ipaddr: gr.Request):
-    """
-    绘制搜索结果
-    Args:
-        txt (str): 过滤文本
-        prompt : 原始的dataset对象
-        percent (int): TF系数，用于计算文本相似度
-        switch (list): 过滤个人或所有人的Prompt
-        ipaddr : 请求人信息
-    Returns:
-        注册函数所需的元祖对象
-    """
-    data = diff_list(txt, percent=percent, switch=switch, hosts=ipaddr.client.host)
-    prompt.samples = data
-    return prompt.update(samples=data, visible=True), prompt
-
-
-def diff_list(txt='', percent=0.70, switch: list = None, lst: dict = None, sp=15, hosts=''):
-    """
-    按照搜索结果统计相似度的文本，两组文本相似度>70%的将统计在一起，取最长的作为key
-    Args:
-        txt (str): 过滤文本
-        percent (int): TF系数，用于计算文本相似度
-        switch (list): 过滤个人或所有人的Prompt
-        lst：指定一个列表或字典
-        sp: 截取展示的文本长度
-        hosts : 请求人的ip
-    Returns:
-        返回一个列表
-    """
-    count_dict = {}
-    is_all = toolbox.get_conf('prompt_list')[0]['key'][1]
-    if not lst:
-        lst = {}
-        tabs = SqliteHandle().get_tables()
-        if is_all in switch:
-            lst.update(SqliteHandle(f"ai_common_{hosts}").get_prompt_value(txt))
-        else:
-            for tab in tabs:
-                if tab.startswith('ai_common'):
-                    lst.update(SqliteHandle(f"{tab}").get_prompt_value(txt))
-        lst.update(SqliteHandle(f"ai_private_{hosts}").get_prompt_value(txt))
-    # diff 数据，根据precent系数归类数据
-    str_ = time.time()
-    def tf_factor_calcul(i):
-        found = False
-        dict_copy = count_dict.copy()
-        for key in dict_copy.keys():
-            str_tf = Levenshtein.jaro_winkler(i, key)
-            if str_tf >= percent:
-                if len(i) > len(key):
-                    count_dict[i] = count_dict.copy()[key] + 1
-                    count_dict.pop(key)
-                else:
-                    count_dict[key] += 1
-                found = True
-                break
-        if not found: count_dict[i] = 1
-    with ThreadPoolExecutor(100) as executor:
-        executor.map(tf_factor_calcul, lst)
-    print('计算耗时', time.time()-str_)
-    sorted_dict = sorted(count_dict.items(), key=lambda x: x[1], reverse=True)
-    if switch:
-        sorted_dict += prompt_retrieval(is_all=switch, hosts=hosts, search=True)
-    dateset_list = []
-    for key in sorted_dict:
-        # 开始匹配关键字
-        index = str(key[0]).lower().find(txt.lower())
-        index_ = str(key[1]).lower().find(txt.lower())
-        if index != -1 or index_ != -1:
-            if index == -1: index = index_  # 增加搜索prompt 名称
-            # sp=split 用于判断在哪里启动、在哪里断开
-            if index - sp > 0:
-                start = index - sp
-            else:
-                start = 0
-            if len(key[0]) > sp * 2:
-                end = key[0][-sp:]
-            else:
-                end = ''
-            # 判断有没有传需要匹配的字符串，有则筛选、无则全返
-            if txt == '' and len(key[0]) >= sp:
-                show = key[0][0:sp] + " . . . " + end
-                show = show.replace('<', '')
-            elif txt == '' and len(key[0]) < sp:
-                show = key[0][0:sp]
-                show = show.replace('<', '')
-            else:
-                show = str(key[0][start:index + sp]).replace('<', '').replace(txt, html_tag_color(txt))
-            show += f"  {html_tag_color(' X ' + str(key[1]))}"
-            if lst.get(key[0]):
-                be_value = lst[key[0]]
-            else:
-                be_value = None
-            value = be_value
-            dateset_list.append([show, key[0], value, key[1]])
-    return dateset_list
-
-
-def prompt_upload_refresh(file, prompt, ipaddr: gr.Request):
-    """
-    上传文件，将文件转换为字典，然后存储到数据库，并刷新Prompt区域
-    Args:
-        file： 上传的文件
-        prompt： 原始prompt对象
-        ipaddr：ipaddr用户请求信息
-    Returns:
-        注册函数所需的元祖对象
-    """
-    hosts = ipaddr.client.host
-    if file.name.endswith('json'):
-        upload_data = check_json_format(file.name)
-    elif file.name.endswith('yaml'):
-        upload_data = YamlHandle(file.name).load()
-    else:
-        upload_data = {}
-    if upload_data != {}:
-        SqliteHandle(f'prompt_{hosts}').inset_prompt(upload_data)
-        ret_data = prompt_retrieval(is_all=['个人'], hosts=hosts)
-        return prompt.update(samples=ret_data, visible=True), prompt, ['个人']
-    else:
-        prompt.samples = [[f'{html_tag_color("数据解析失败，请检查文件是否符合规范", color="red")}', '']]
-        return prompt.samples, prompt, []
-
-
-def prompt_retrieval(is_all, hosts='', search=False):
-    """
-    上传文件，将文件转换为字典，然后存储到数据库，并刷新Prompt区域
-    Args:
-        is_all： prompt类型
-        hosts： 查询的用户ip
-        search：支持搜索，搜索时将key作为key
-    Returns:
-        返回一个列表
-    """
-    count_dict = {}
-    if '所有人' in is_all:
-        for tab in SqliteHandle('ai_common').get_tables():
-            if tab.startswith('prompt'):
-                data = SqliteHandle(tab).get_prompt_value(None)
-                if data: count_dict.update(data)
-    elif '个人' in is_all:
-        data = SqliteHandle(f'prompt_{hosts}').get_prompt_value(None)
-        if data: count_dict.update(data)
-    retrieval = []
-    if count_dict != {}:
-        for key in count_dict:
-            if not search:
-                retrieval.append([key, count_dict[key]])
-            else:
-                retrieval.append([count_dict[key], key])
-        return retrieval
-    else:
-        return retrieval
-
-
-def prompt_reduce(is_all, prompt: gr.Dataset, ipaddr: gr.Request):  # is_all, ipaddr: gr.Request
-    """
-    上传文件，将文件转换为字典，然后存储到数据库，并刷新Prompt区域
-    Args:
-        is_all： prompt类型
-        prompt： dataset原始对象
-        ipaddr：请求用户信息
-    Returns:
-        返回注册函数所需的对象
-    """
-    data = prompt_retrieval(is_all=is_all, hosts=ipaddr.client.host)
-    prompt.samples = data
-    return prompt.update(samples=data, visible=True), prompt, is_all
-
-
-def prompt_save(txt, name, prompt: gr.Dataset, ipaddr: gr.Request):
-    """
-    编辑和保存Prompt
-    Args:
-        txt： Prompt正文
-        name： Prompt的名字
-        prompt： dataset原始对象
-        ipaddr：请求用户信息
-    Returns:
-        返回注册函数所需的对象
-    """
-    if txt and name:
-        yaml_obj = SqliteHandle(f'prompt_{ipaddr.client.host}')
-        yaml_obj.inset_prompt({name: txt})
-        result = prompt_retrieval(is_all=['个人'], hosts=ipaddr.client.host)
-        prompt.samples = result
-        return "", "", ['个人'], prompt.update(samples=result, visible=True), prompt, gr.Tabs.update(selected='chatbot')
-    elif not txt or not name:
-        result = [[f'{html_tag_color("编辑框 or 名称不能为空!!!!!", color="red")}', '']]
-        prompt.samples = [[f'{html_tag_color("编辑框 or 名称不能为空!!!!!", color="red")}', '']]
-        return txt, name, [], prompt.update(samples=result, visible=True), prompt, gr.Tabs.update(selected='chatbot')
-
-
-def prompt_input(txt: str, prompt_str, name_str,  index, data: gr.Dataset, tabs_index):
-    """
-    点击dataset的值使用Prompt
-    Args:
-        txt： 输入框正文
-        index： 点击的Dataset下标
-        data： dataset原始对象
-    Returns:
-        返回注册函数所需的对象
-    """
-    data_str = str(data.samples[index][1])
-    data_name = str(data.samples[index][0])
-    rp_str = '{{{v}}}'
-
-    def str_v_handle(__str):
-        if data_str.find(rp_str) != -1 and __str:
-            txt_temp = data_str.replace(rp_str, __str)
-        elif __str:
-            txt_temp = data_str + '\n' + __str
-        else:
-            txt_temp = data_str
-        return txt_temp
-    if tabs_index == 1:
-        new_txt = str_v_handle(prompt_str)
-        return txt, new_txt, data_name
-    else:
-        new_txt = str_v_handle(txt)
-        return new_txt, prompt_str, name_str
-
-
-def copy_result(history):
-    """复制history"""
-    if history != []:
-        pyperclip.copy(history[-1])
-        return '已将结果复制到剪切板'
-    else:
-        return "无对话记录，复制错误！！"
-
-
-def str_is_list(s):
-    try:
-        list_ast = ast.literal_eval(s)
-        return isinstance(list_ast, list)
-    except (SyntaxError, ValueError):
-        return False
-
-
-def show_prompt_result(index, data: gr.Dataset, chatbot, pro_edit, pro_name):
-    """
-    查看Prompt的对话记录结果
-    Args:
-        index： 点击的Dataset下标
-        data： dataset原始对象
-        chatbot：聊天机器人
-    Returns:
-        返回注册函数所需的对象
-    """
-    click = data.samples[index]
-    if str_is_list(click[2]):
-        list_copy = eval(click[2])
-        for i in range(0, len(list_copy), 2):
-            if i + 1 >= len(list_copy):  # 如果下标越界了，单独处理最后一个元素
-                chatbot.append([list_copy[i]])
-            else:
-                chatbot.append([list_copy[i], list_copy[i + 1]])
-    elif click[2] is None and pro_edit == '':
-        pro_edit = click[1]
-        pro_name = click[3]
-    else:
-        chatbot.append((click[1], click[2]))
-    return chatbot, pro_edit, pro_name
-
-
-
-def pattern_html(html):
-    bs = BeautifulSoup(str(html), 'html.parser')
-    md_message = bs.find('div', {'class': 'md-message'})
-    if md_message:
-        return md_message.get_text(separator='')
-    else:
-        return ""
-
-
-def thread_write_chat(chatbot, history):
-    """
-    对话记录写入数据库
-    """
-    chatbot, history = copy.copy(chatbot), copy.copy(history)
-    private_key = toolbox.get_conf('private_key')[0]
-    chat_title = chatbot[0][1].split()
-    i_say = pattern_html(chatbot[-1][0])
-    if history:
-        gpt_result = history
-    else:  # 如果历史对话不存在，那么读取对话框
-        gpt_result = [pattern_html(v) for i in chatbot for v in i]
-    if private_key in chat_title:
-        SqliteHandle(f'ai_private_{chat_title[-2]}').inset_prompt({i_say: gpt_result})
-    else:
-        SqliteHandle(f'ai_common_{chat_title[-2]}').inset_prompt({i_say: gpt_result})
-
-
-base_path = os.path.dirname(__file__)
-prompt_path = os.path.join(base_path, 'users_data')
-users_path = os.path.join(base_path, 'private_upload')
-logs_path = os.path.join(base_path, 'gpt_log')
-
-def reuse_chat(result, chatbot, history, pro_numb, say):
-    """复用对话记录"""
-    if result is None or result == []:
-        return chatbot, history, gr.update(), gr.update(), '', gr.Column.update()
-    else:
-        if pro_numb:
-            chatbot += result
-            history += [pattern_html(_) for i in result for _ in i]
-        else:
-            chatbot.append(result[-1])
-            history += [pattern_html(_) for i in result[-2:] for _ in i]
-        print(chatbot[-1][0])
-        return chatbot, history, say, gr.Tabs.update(selected='chatbot'), '', gr.Column.update(visible=False)
-
-
-def num_tokens_from_string(listing: list, encoding_name: str = 'cl100k_base') -> int:
-    """Returns the number of tokens in a text string."""
-    count_tokens = 0
-    for i in listing:
-        encoding = tiktoken.get_encoding(encoding_name)
-        count_tokens += len(encoding.encode(i))
-    return count_tokens
-
-
-def spinner_chatbot_loading(chatbot):
-    loading = [''.join(['.' * random.randint(1, 5)])]
-    # 将元组转换为列表并修改元素
-    loading_msg = copy.deepcopy(chatbot)
-    temp_list = list(loading_msg[-1])
-
-    temp_list[1] = pattern_html(temp_list[1]) + f'{random.choice(loading)}'
-    # 将列表转换回元组并替换原始元组
-    loading_msg[-1] = tuple(temp_list)
-    return loading_msg
-
-
-def refresh_load_data(chat, history, prompt, crazy_list, request: gr.Request):
-    """
-    Args:
-        chat: 聊天组件
-        history: 对话记录
-        prompt: prompt dataset组件
-
-    Returns:
-        预期是每次刷新页面，加载最新
-    """
-    is_all = toolbox.get_conf('prompt_list')[0]['key'][0]
-    data = prompt_retrieval(is_all=[is_all])
-    prompt.samples = data
-    selected = random.sample(crazy_list, 4)
-    user_agent = request.kwargs['headers']['user-agent'].lower()
-    if user_agent.find('android') != -1 or user_agent.find('iphone') != -1:
-        hied_elem = gr.update(visible=False)
-    else:
-        hied_elem = gr.update()
-    outputs = [prompt.update(samples=data, visible=True), prompt,
-               chat, history, gr.Dataset.update(samples=[[i] for i in selected]), selected,
-               hied_elem, hied_elem]
-    return outputs
-
-
-
-def txt_converter_json(input_string):
-    try:
-        if input_string.startswith("{") and input_string.endswith("}"):
-            # 尝试将字符串形式的字典转换为字典对象
-            dict_object = ast.literal_eval(input_string)
-        else:
-            # 尝试将字符串解析为JSON对象
-            dict_object = json.loads(input_string)
-        formatted_json_string = json.dumps(dict_object, indent=4, ensure_ascii=False)
-        return formatted_json_string
-    except (ValueError, SyntaxError):
-        return input_string
-
-
-def clean_br_string(s):
-    s = re.sub('<\s*br\s*/?>', '\n', s)  # 使用正则表达式同时匹配<br>、<br/>、<br />、< br>和< br/>
-    return s
-
-
-def update_btn(self,
-    value:  str = None,
-    variant:  str = None,
-    visible:  bool = None,
-    interactive: bool = None,
-    elem_id: str = None,
-    label: str = None
-):
-    if not variant: variant = self.variant
-    if not visible: visible = self.visible
-    if not value: value = self.value
-    if not interactive: interactive = self.interactive
-    if not elem_id: elem_id = self.elem_id
-    if not elem_id: label = self.label
-    return {
-        "variant": variant,
-        "visible": visible,
-        "value": value,
-        "interactive": interactive,
-        'elem_id': elem_id,
-        'label': label,
-        "__type__": "update",
-    }
-
-def update_txt(self,
-        value: str = None,
-        lines: int  = None,
-        max_lines: int  = None,
-        placeholder: str  = None,
-        label: str  = None,
-        show_label: bool  = None,
-        visible: bool  = None,
-        interactive: bool  = None,
-        type: str  = None,
-        elem_id: str = None
-    ):
-
-        return {
-            "lines": self.lines,
-            "max_lines": self.max_lines,
-            "placeholder": self.placeholder,
-            "label": self.label,
-            "show_label": self.show_label,
-            "visible": self.visible,
-            "value": self.value,
-            "type": self.type,
-            "interactive": self.interactive,
-            "elem_id": elem_id,
-            "__type__": "update",
-
-        }
-
-
-def get_html(filename):
-    path = os.path.join(base_path, "docs/assets", "html", filename)
-    if os.path.exists(path):
-        with open(path, encoding="utf8") as file:
-            return file.read()
-    return ""
-
-
-def git_log_list():
-    ll = Shell("git log --pretty=format:'%s | %h' -n 10").read()[1].splitlines()
-
-    return [i.split('|') for i in ll if 'branch' not in i][:5]
-
-import qrcode
-from PIL import Image, ImageDraw
-def qr_code_generation(data, icon_path=None, file_name='qc_icon.png'):
-    # 创建qrcode对象
-    qr = qrcode.QRCode(version=2, error_correction=qrcode.constants.ERROR_CORRECT_Q, box_size=10, border=2,)
-    qr.add_data(data)
-    # 创建二维码图片
-    img = qr.make_image()
-    # 图片转换为RGBA格式
-    img = img.convert('RGBA')
-    # 返回二维码图片的大小
-    img_w, img_h = img.size
-    # 打开logo
-    if not icon_path:
-        icon_path = os.path.join(base_path, 'docs/assets/PLAI.jpeg')
-    logo = Image.open(icon_path)
-    # logo大小为二维码的四分之一
-    logo_w = img_w // 4
-    logo_h = img_w // 4
-    # 修改logo图片大小
-    logo = logo.resize((logo_w, logo_h), Image.LANCZOS)  # or Image.Resampling.LANCZOS
-    # 把logo放置在二维码中间
-    w = (img_w - logo_w) // 2
-    h = (img_h - logo_h) // 2
-    img.paste(logo, (w, h))
-    qr_path = os.path.join(logs_path, 'file_name')
-    img.save()
-    return qr_path
-
-
-class YamlHandle:
-
-    def __init__(self, file=os.path.join(prompt_path, 'ai_common.yaml')):
-        if not os.path.exists(file):
-            Shell(f'touch {file}').read()
-        self.file = file
-        self._load = self.load()
-
-    def load(self) -> dict:
-        with open(file=self.file, mode='r') as f:
-            data = yaml.safe_load(f)
-            return data
-
-    def update(self, key, value):
-        date = self._load
-        if not date:
-            date = {}
-        date[key] = value
-        with open(file=self.file, mode='w') as f:
-            yaml.dump(date, f, allow_unicode=True)
-        return date
-
-    def dump_dict(self, new_dict):
-        date = self._load
-        if not date:
-            date = {}
-        date.update(new_dict)
-        with open(file=self.file, mode='w') as f:
-            yaml.dump(date, f, allow_unicode=True)
-        return date
-
-
-class JsonHandle:
-
-    def __init__(self, file):
-        self.file = file
-
-    def load(self) -> object:
-        with open(self.file, 'r') as f:
-            data = json.load(f)
-        return data
-
-
-
-if __name__ == '__main__':
-    pass

main.py

@@ -4,25 +4,28 @@ def main():
     import gradio as gr
     if gr.__version__ not in ['3.28.3','3.32.2']: assert False, "需要特殊依赖，请务必用 pip install -r requirements.txt 指令安装依赖，详情信息见requirements.txt"
     from request_llm.bridge_all import predict
-    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, DummyWith
+    from toolbox import format_io, find_free_port, on_file_uploaded, on_report_generated, get_conf, ArgsGeneralWrapper, load_chat_cookies, DummyWith
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
-    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, API_KEY, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = \
-        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'API_KEY', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
-
+    proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION, CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = \
+        get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION', 'CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
+    ENABLE_AUDIO, AUTO_CLEAR_TXT = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT')
     # 如果WEB_PORT是-1, 则随机选取WEB端口
     PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
     if not AUTHENTICATION: AUTHENTICATION = None
 
     from check_proxy import get_current_version
+    from themes.theme import adjust_theme, advanced_css, theme_declaration
     initial_prompt = "Serve me as a writing and programming assistant."
-    title_html = f"<h1 align=\"center\">ChatGPT 学术优化 {get_current_version()}</h1>"
+    title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
     description =  """代码开源和更新[地址🚀](https://github.com/binary-husky/chatgpt_academic)，感谢热情的[开发者们❤️](https://github.com/binary-husky/chatgpt_academic/graphs/contributors)"""
 
     # 问询记录, python 版本建议3.9+（越新越好）
-    import logging
+    import logging, uuid
     os.makedirs("gpt_log", exist_ok=True)
-    try:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8")
-    except:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO)
+    try:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO, encoding="utf-8", format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    except:logging.basicConfig(filename="gpt_log/chat_secrets.log", level=logging.INFO,  format="%(asctime)s %(levelname)-8s %(message)s", datefmt="%Y-%m-%d %H:%M:%S")
+    # Disable logging output from the 'httpx' logger
+    logging.getLogger("httpx").setLevel(logging.WARNING)
     print("所有问询记录将自动保存在本地目录./gpt_log/chat_secrets.log, 请注意自我隐私保护哦！")
 
     # 一些普通功能模块
@@ -37,7 +40,6 @@ def main():
     gr.Chatbot.postprocess = format_io
 
     # 做一些外观色彩上的调整
-    from theme import adjust_theme, advanced_css
     set_theme = adjust_theme()
 
     # 代理与自动更新
@@ -45,23 +47,23 @@ def main():
     proxy_info = check_proxy(proxies)
 
     gr_L1 = lambda: gr.Row().style()
-    gr_L2 = lambda scale: gr.Column(scale=scale)
+    gr_L2 = lambda scale, elem_id: gr.Column(scale=scale, elem_id=elem_id)
     if LAYOUT == "TOP-DOWN":
         gr_L1 = lambda: DummyWith()
-        gr_L2 = lambda scale: gr.Row()
+        gr_L2 = lambda scale, elem_id: gr.Row()
         CHATBOT_HEIGHT /= 2
 
     cancel_handles = []
-    with gr.Blocks(title="ChatGPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
+    with gr.Blocks(title="GPT 学术优化", theme=set_theme, analytics_enabled=False, css=advanced_css) as demo:
         gr.HTML(title_html)
-        cookies = gr.State({'api_key': API_KEY, 'llm_model': LLM_MODEL})
+        cookies = gr.State(load_chat_cookies())
         with gr_L1():
-            with gr_L2(scale=2):
-                chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}")
-                chatbot.style(height=CHATBOT_HEIGHT)
+            with gr_L2(scale=2, elem_id="gpt-chat"):
+                chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
+                if LAYOUT == "TOP-DOWN":  chatbot.style(height=CHATBOT_HEIGHT)
                 history = gr.State([])
-            with gr_L2(scale=1):
-                with gr.Accordion("输入区", open=True) as area_input_primary:
+            with gr_L2(scale=1, elem_id="gpt-panel"):
+                with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
                     with gr.Row():
                         txt = gr.Textbox(show_label=False, placeholder="Input question here.").style(container=False)
                     with gr.Row():
@@ -70,17 +72,20 @@ def main():
                         resetBtn = gr.Button("重置", variant="secondary"); resetBtn.style(size="sm")
                         stopBtn = gr.Button("停止", variant="secondary"); stopBtn.style(size="sm")
                         clearBtn = gr.Button("清除", variant="secondary", visible=False); clearBtn.style(size="sm")
+                    if ENABLE_AUDIO: 
                         with gr.Row():
-                        status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}")
-                with gr.Accordion("基础功能区", open=True) as area_basic_fn:
+                            audio_mic = gr.Audio(source="microphone", type="numpy", streaming=True, show_label=False).style(container=False)
+                    with gr.Row():
+                        status = gr.Markdown(f"Tip: 按Enter提交, 按Shift+Enter换行。当前模型: {LLM_MODEL} \n {proxy_info}", elem_id="state-panel")
+                with gr.Accordion("基础功能区", open=True, elem_id="basic-panel") as area_basic_fn:
                     with gr.Row():
                         for k in functional:
                             if ("Visible" in functional[k]) and (not functional[k]["Visible"]): continue
                             variant = functional[k]["Color"] if "Color" in functional[k] else "secondary"
                             functional[k]["Button"] = gr.Button(k, variant=variant)
-                with gr.Accordion("函数插件区", open=True) as area_crazy_fn:
+                with gr.Accordion("函数插件区", open=True, elem_id="plugin-panel") as area_crazy_fn:
                     with gr.Row():
-                        gr.Markdown("注意：以下“红颜色”标识的函数插件需从输入区读取路径作为参数.")
+                        gr.Markdown("插件可读取“输入区”文本/路径作为参数（上传文件自动修正路径）")
                     with gr.Row():
                         for k in crazy_fns:
                             if not crazy_fns[k].get("AsButton", True): continue
@@ -91,16 +96,16 @@ def main():
                         with gr.Accordion("更多函数插件", open=True):
                             dropdown_fn_list = [k for k in crazy_fns.keys() if not crazy_fns[k].get("AsButton", True)]
                             with gr.Row():
-                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="").style(container=False)
+                                dropdown = gr.Dropdown(dropdown_fn_list, value=r"打开插件列表", label="", show_label=False).style(container=False)
                             with gr.Row():
                                 plugin_advanced_arg = gr.Textbox(show_label=True, label="高级参数输入区", visible=False, 
                                                                  placeholder="这里是特殊函数插件的高级参数输入区").style(container=False)
                             with gr.Row():
                                 switchy_bt = gr.Button(r"请先从插件列表中选择", variant="secondary")
                     with gr.Row():
-                        with gr.Accordion("点击展开“文件上传区”。上传本地文件可供红色函数插件调用。", open=False) as area_file_up:
+                        with gr.Accordion("点击展开“文件上传区”。上传本地文件/压缩包供函数插件调用。", open=False) as area_file_up:
                             file_upload = gr.Files(label="任何文件, 但推荐上传压缩文件(zip, tar)", file_count="multiple")
-                with gr.Accordion("更换模型 & SysPrompt & 交互界面布局", open=(LAYOUT == "TOP-DOWN")):
+                with gr.Accordion("更换模型 & SysPrompt & 交互界面布局", open=(LAYOUT == "TOP-DOWN"), elem_id="interact-panel"):
                     system_prompt = gr.Textbox(show_label=True, placeholder=f"System Prompt", label="System prompt", value=initial_prompt)
                     top_p = gr.Slider(minimum=-0, maximum=1.0, value=1.0, step=0.01,interactive=True, label="Top-p (nucleus sampling)",)
                     temperature = gr.Slider(minimum=-0, maximum=2.0, value=1.0, step=0.01, interactive=True, label="Temperature",)
@@ -109,7 +114,7 @@ def main():
                     md_dropdown = gr.Dropdown(AVAIL_LLM_MODELS, value=LLM_MODEL, label="更换LLM模型/请求源").style(container=False)
 
                     gr.Markdown(description)
-                with gr.Accordion("备选输入区", open=True, visible=False) as area_input_secondary:
+                with gr.Accordion("备选输入区", open=True, visible=False, elem_id="input-panel2") as area_input_secondary:
                     with gr.Row():
                         txt2 = gr.Textbox(show_label=False, placeholder="Input question here.", label="输入区2").style(container=False)
                     with gr.Row():
@@ -130,9 +135,9 @@ def main():
             ret.update({plugin_advanced_arg: gr.update(visible=("插件参数区" in a))})
             if "底部输入区" in a: ret.update({txt: gr.update(value="")})
             return ret
-        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, clearBtn, clearBtn2, plugin_advanced_arg] )
+        checkboxes.select(fn_area_visibility, [checkboxes], [area_basic_fn, area_crazy_fn, area_input_primary, area_input_secondary, txt, txt2, clearBtn, clearBtn2, plugin_advanced_arg] )
         # 整理反复出现的控件句柄组合
-        input_combo = [cookies, max_length_sl, md_dropdown, txt, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
+        input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
         output_combo = [cookies, chatbot, history, status]
         predict_args = dict(fn=ArgsGeneralWrapper(predict), inputs=input_combo, outputs=output_combo)
         # 提交按钮、重置按钮
@@ -155,7 +160,7 @@ def main():
             click_handle = functional[k]["Button"].click(fn=ArgsGeneralWrapper(predict), inputs=[*input_combo, gr.State(True), gr.State(k)], outputs=output_combo)
             cancel_handles.append(click_handle)
         # 文件上传区，接收文件后与chatbot的互动
-        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt ], [chatbot, txt])
+        file_upload.upload(on_file_uploaded, [file_upload, chatbot, txt, txt2, checkboxes], [chatbot, txt, txt2])
         # 函数插件-固定按钮区
         for k in crazy_fns:
             if not crazy_fns[k].get("AsButton", True): continue
@@ -176,15 +181,28 @@ def main():
             return {chatbot: gr.update(label="当前模型："+k)}
         md_dropdown.select(on_md_dropdown_changed, [md_dropdown], [chatbot] )
         # 随变按钮的回调函数注册
-        def route(k, *args, **kwargs):
+        def route(request: gr.Request, k, *args, **kwargs):
             if k in [r"打开插件列表", r"请先从插件列表中选择"]: return
-            yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(*args, **kwargs)
+            yield from ArgsGeneralWrapper(crazy_fns[k]["Function"])(request, *args, **kwargs)
         click_handle = switchy_bt.click(route,[switchy_bt, *input_combo, gr.State(PORT)], output_combo)
         click_handle.then(on_report_generated, [cookies, file_upload, chatbot], [cookies, file_upload, chatbot])
         cancel_handles.append(click_handle)
         # 终止按钮的回调函数注册
         stopBtn.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
         stopBtn2.click(fn=None, inputs=None, outputs=None, cancels=cancel_handles)
+        if ENABLE_AUDIO: 
+            from crazy_functions.live_audio.audio_io import RealtimeAudioDistribution
+            rad = RealtimeAudioDistribution()
+            def deal_audio(audio, cookies):
+                rad.feed(cookies['uuid'].hex, audio)
+            audio_mic.stream(deal_audio, inputs=[audio_mic, cookies])
+
+        def init_cookie(cookies, chatbot):
+            # 为每一位访问的用户赋予一个独一无二的uuid编码
+            cookies.update({'uuid': uuid.uuid4()})
+            return cookies
+        demo.load(init_cookie, inputs=[cookies, chatbot], outputs=[cookies])
+        demo.load(lambda: 0, inputs=None, outputs=None, _js='()=>{ChatBotHeight();}')
         
     # gradio的inbrowser触发不太稳定，回滚代码到原始的浏览器打开函数
     def auto_opentab_delay():

multi_language.py

@@ -33,7 +33,7 @@ import pickle
 import time
 
 CACHE_FOLDER = "gpt_log"
-blacklist = ['multi-language', 'gpt_log', '.git', 'private_upload', 'multi_language.py']
+blacklist = ['multi-language', 'gpt_log', '.git', 'private_upload', 'multi_language.py', 'build', '.github', '.vscode', '__pycache__', 'venv']
 
 # LANG = "TraditionalChinese"
 # TransPrompt = f"Replace each json value `#` with translated results in Traditional Chinese, e.g., \"原始文本\":\"翻譯後文字\". Keep Json format. Do not answer #."
@@ -301,6 +301,7 @@ def step_1_core_key_translate():
                 elif isinstance(node, ast.ImportFrom):
                     for n in node.names:
                         if contains_chinese(n.name): syntax.append(n.name)
+                        # if node.module is None: print(node.module)
                         for k in node.module.split('.'):
                             if contains_chinese(k): syntax.append(k)
             return syntax
@@ -310,6 +311,7 @@ def step_1_core_key_translate():
         for root, dirs, files in os.walk(directory_path):
             if any([b in root for b in blacklist]):
                 continue
+            print(files)
             for file in files:
                 if file.endswith('.py'):
                     file_path = os.path.join(root, file)
@@ -505,6 +507,6 @@ def step_2_core_key_translate():
                     with open(file_path_new, 'w', encoding='utf-8') as f:
                         f.write(content)
                     os.remove(file_path)
-
 step_1_core_key_translate()
 step_2_core_key_translate()
+print('Finished, checkout generated results at ./multi-language/')

prompt_generator.py

@@ -1,102 +0,0 @@
-#! .\venv\
-# encoding: utf-8
-# @Time   : 2023/4/19
-# @Author : Spike
-# @Descr   :
-import os.path
-import sqlite3
-import threading
-import functools
-import func_box
-# 连接到数据库
-base_path = os.path.dirname(__file__)
-prompt_path = os.path.join(base_path, 'users_data')
-
-
-def connect_db_close(cls_method):
-    @functools.wraps(cls_method)
-    def wrapper(cls=None, *args, **kwargs):
-        cls._connect_db()
-        result = cls_method(cls, *args, **kwargs)
-        cls._close_db()
-        return result
-    return wrapper
-
-
-class SqliteHandle:
-    def __init__(self, table='ai_common', database='ai_prompt.db'):
-        self.__database = database
-        self.__connect = sqlite3.connect(os.path.join(prompt_path, self.__database))
-        self.__cursor = self.__connect.cursor()
-        self.__table = table
-        if self.__table not in self.get_tables():
-            self.create_tab()
-
-    def new_connect_db(self):
-        """多线程操作时，每个线程新建独立的connect"""
-        self.__connect = sqlite3.connect(os.path.join(prompt_path, self.__database))
-        self.__cursor = self.__connect.cursor()
-
-    def new_close_db(self):
-        self.__cursor.close()
-        self.__connect.close()
-
-    def create_tab(self):
-        self.__cursor.execute(f"CREATE TABLE `{self.__table}` ('prompt' TEXT UNIQUE, 'result' TEXT)")
-
-    def get_tables(self):
-        all_tab = []
-        result = self.__cursor.execute("SELECT name FROM sqlite_master WHERE type = 'table';")
-        for tab in result:
-            all_tab.append(tab[0])
-        return all_tab
-
-    def get_prompt_value(self, find=None):
-        temp_all = {}
-        if find:
-            result = self.__cursor.execute(f"SELECT prompt, result FROM `{self.__table}` WHERE prompt LIKE '%{find}%'").fetchall()
-        else:
-            result = self.__cursor.execute(f"SELECT prompt, result FROM `{self.__table}`").fetchall()
-        for row in result:
-            temp_all[row[0]] = row[1]
-        return temp_all
-
-    def inset_prompt(self, prompt: dict):
-        for key in prompt:
-            self.__cursor.execute(f"REPLACE INTO `{self.__table}` (prompt, result) VALUES (?, ?);", (str(key), str(prompt[key])))
-        self.__connect.commit()
-
-    def delete_prompt(self, name):
-        self.__cursor.execute(f"DELETE from `{self.__table}` where prompt LIKE '{name}'")
-        self.__connect.commit()
-
-    def delete_tabls(self, tab):
-        self.__cursor.execute(f"DROP TABLE `{tab}`;")
-        self.__connect.commit()
-
-    def find_prompt_result(self, name):
-        query = self.__cursor.execute(f"SELECT result FROM `{self.__table}` WHERE prompt LIKE '{name}'").fetchall()
-        if query == []:
-            query = self.__cursor.execute(f"SELECT result FROM `prompt_127.0.0.1` WHERE prompt LIKE '{name}'").fetchall()
-            return query[0][0]
-        else:
-            return query[0][0]
-
-def cp_db_data(incloud_tab='prompt'):
-    sql_ll = sqlite_handle(database='ai_prompt_cp.db')
-    tabs = sql_ll.get_tables()
-    for i in tabs:
-        if str(i).startswith(incloud_tab):
-            old_data = sqlite_handle(table=i, database='ai_prompt_cp.db').get_prompt_value()
-            sqlite_handle(table=i).inset_prompt(old_data)
-
-def inset_127_prompt():
-    sql_handle = sqlite_handle(table='prompt_127.0.0.1')
-    prompt_json = os.path.join(prompt_path, 'prompts-PlexPt.json')
-    data_list = func_box.JsonHandle(prompt_json).load()
-    for i in data_list:
-        sql_handle.inset_prompt(prompt={i['act']: i['prompt']})
-
-sqlite_handle = SqliteHandle
-if __name__ == '__main__':
-    cp_db_data()

request_llm/bridge_all.py

@@ -13,21 +13,12 @@ from functools import lru_cache
 from concurrent.futures import ThreadPoolExecutor
 from toolbox import get_conf, trimmed_format_exc
 
-from request_llm.bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
-from request_llm.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_azure_test import predict_no_ui_long_connection as azure_noui
-from .bridge_azure_test import predict as azure_ui
+from .bridge_chatgpt import predict_no_ui_long_connection as chatgpt_noui
+from .bridge_chatgpt import predict as chatgpt_ui
 
 from .bridge_chatglm import predict_no_ui_long_connection as chatglm_noui
 from .bridge_chatglm import predict as chatglm_ui
 
-from .bridge_newbing import predict_no_ui_long_connection as newbing_noui
-from .bridge_newbing import predict as newbing_ui
-
 # from .bridge_tgui import predict_no_ui_long_connection as tgui_noui
 # from .bridge_tgui import predict as tgui_ui
 
@@ -54,11 +45,11 @@ class LazyloadTiktoken(object):
         return encoder.decode(*args, **kwargs)
 
 # Endpoint 重定向
-API_URL_REDIRECT, PROXY_API_URL = get_conf("API_URL_REDIRECT", 'PROXY_API_URL')
+API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "AZURE_ENDPOINT", "AZURE_ENGINE")
 openai_endpoint = "https://api.openai.com/v1/chat/completions"
 api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
 newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
-proxy_endpoint = PROXY_API_URL
+azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
 # 兼容旧版的配置
 try:
     API_URL, = get_conf("API_URL")
@@ -73,7 +64,6 @@ if api2d_endpoint in API_URL_REDIRECT: api2d_endpoint = API_URL_REDIRECT[api2d_e
 if newbing_endpoint in API_URL_REDIRECT: newbing_endpoint = API_URL_REDIRECT[newbing_endpoint]
 
 
-
 # 获取tokenizer
 tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
 tokenizer_gpt4 = LazyloadTiktoken("gpt-4")
@@ -127,21 +117,12 @@ model_info = {
         "tokenizer": tokenizer_gpt4,
         "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,
-    },
 
     # azure openai
-    "azure-gpt35":{
-        "fn_with_ui": azure_ui,
-        "fn_without_ui": azure_noui,
-        "endpoint": get_conf("AZURE_ENDPOINT"),
+    "azure-gpt-3.5":{
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": azure_endpoint,
         "max_token": 4096,
         "tokenizer": tokenizer_gpt35,
         "token_cnt": get_token_num_gpt35,
@@ -161,9 +142,9 @@ model_info = {
         "fn_with_ui": chatgpt_ui,
         "fn_without_ui": chatgpt_noui,
         "endpoint": api2d_endpoint,
-        "max_token": 4096,
-        "tokenizer": tokenizer_gpt35,
-        "token_cnt": get_token_num_gpt35,
+        "max_token": 8192,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
     },
 
     # 将 chatglm 直接对齐到 chatglm2
@@ -184,20 +165,34 @@ model_info = {
         "token_cnt": get_token_num_gpt35,
     },
 
-    # newbing
-    "newbing": {
-        "fn_with_ui": newbing_ui,
-        "fn_without_ui": newbing_noui,
-        "endpoint": newbing_endpoint,
-        "max_token": 4096,
-        "tokenizer": tokenizer_gpt35,
-        "token_cnt": get_token_num_gpt35,
-    },
-
 }
 
 
-AVAIL_LLM_MODELS, = get_conf("AVAIL_LLM_MODELS")
+AVAIL_LLM_MODELS, LLM_MODEL = get_conf("AVAIL_LLM_MODELS", "LLM_MODEL")
+AVAIL_LLM_MODELS = AVAIL_LLM_MODELS + [LLM_MODEL]
+if "claude-1-100k" in AVAIL_LLM_MODELS or "claude-2" in AVAIL_LLM_MODELS:
+    from .bridge_claude import predict_no_ui_long_connection as claude_noui
+    from .bridge_claude import predict as claude_ui
+    model_info.update({
+        "claude-1-100k": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": None,
+            "max_token": 8196,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
+    model_info.update({
+        "claude-2": {
+            "fn_with_ui": claude_ui,
+            "fn_without_ui": claude_noui,
+            "endpoint": None,
+            "max_token": 8196,
+            "tokenizer": tokenizer_gpt35,
+            "token_cnt": get_token_num_gpt35,
+        },
+    })
 if "jittorllms_rwkv" in AVAIL_LLM_MODELS:
     from .bridge_jittorllms_rwkv import predict_no_ui_long_connection as rwkv_noui
     from .bridge_jittorllms_rwkv import predict as rwkv_ui
@@ -253,7 +248,6 @@ if "moss" in AVAIL_LLM_MODELS:
 if "stack-claude" in AVAIL_LLM_MODELS:
     from .bridge_stackclaude import predict_no_ui_long_connection as claude_noui
     from .bridge_stackclaude import predict as claude_ui
-    # claude
     model_info.update({
         "stack-claude": {
             "fn_with_ui": claude_ui,
@@ -268,7 +262,6 @@ if "newbing-free" in AVAIL_LLM_MODELS:
     try:
         from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
         from .bridge_newbingfree import predict as newbingfree_ui
-        # claude
         model_info.update({
             "newbing-free": {
                 "fn_with_ui": newbingfree_ui,
@@ -281,6 +274,54 @@ if "newbing-free" in AVAIL_LLM_MODELS:
         })
     except:
         print(trimmed_format_exc())
+if "newbing" in AVAIL_LLM_MODELS:   # same with newbing-free
+    try:
+        from .bridge_newbingfree import predict_no_ui_long_connection as newbingfree_noui
+        from .bridge_newbingfree import predict as newbingfree_ui
+        model_info.update({
+            "newbing": {
+                "fn_with_ui": newbingfree_ui,
+                "fn_without_ui": newbingfree_noui,
+                "endpoint": newbing_endpoint,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            }
+        })
+    except:
+        print(trimmed_format_exc())
+if "chatglmft" in AVAIL_LLM_MODELS:   # same with newbing-free
+    try:
+        from .bridge_chatglmft import predict_no_ui_long_connection as chatglmft_noui
+        from .bridge_chatglmft import predict as chatglmft_ui
+        model_info.update({
+            "chatglmft": {
+                "fn_with_ui": chatglmft_ui,
+                "fn_without_ui": chatglmft_noui,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            }
+        })
+    except:
+        print(trimmed_format_exc())
+if "internlm" in AVAIL_LLM_MODELS:
+    try:
+        from .bridge_internlm import predict_no_ui_long_connection as internlm_noui
+        from .bridge_internlm import predict as internlm_ui
+        model_info.update({
+            "internlm": {
+                "fn_with_ui": internlm_ui,
+                "fn_without_ui": internlm_noui,
+                "endpoint": None,
+                "max_token": 4096,
+                "tokenizer": tokenizer_gpt35,
+                "token_cnt": get_token_num_gpt35,
+            }
+        })
+    except:
+        print(trimmed_format_exc())
 
 def LLM_CATCH_EXCEPTION(f):
     """
@@ -384,6 +425,6 @@ def predict(inputs, llm_kwargs, *args, **kwargs):
     additional_fn代表点击的哪个按钮，按钮见functional.py
     """
 
-    method = model_info[llm_kwargs['llm_model']]["fn_with_ui"]
+    method = model_info[llm_kwargs['llm_model']]["fn_with_ui"]  # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
     yield from method(inputs, llm_kwargs, *args, **kwargs)
 

request_llm/bridge_azure_test.py

@@ -1,241 +0,0 @@
-"""
-    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
-
-

request_llm/bridge_chatglm.py

@@ -37,15 +37,23 @@ class GetGLMHandle(Process):
         # 子进程执行
         # 第一次运行，加载参数
         retry = 0
+        LOCAL_MODEL_QUANT, device = get_conf('LOCAL_MODEL_QUANT', 'LOCAL_MODEL_DEVICE')
+
+        if LOCAL_MODEL_QUANT == "INT4":         # INT4
+            _model_name_ = "THUDM/chatglm2-6b-int4"
+        elif LOCAL_MODEL_QUANT == "INT8":       # INT8
+            _model_name_ = "THUDM/chatglm2-6b-int8"
+        else:
+            _model_name_ = "THUDM/chatglm2-6b"  # FP16
+
         while True:
             try:
                 if self.chatglm_model is None:
-                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
-                    device, = get_conf('LOCAL_MODEL_DEVICE')
+                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
                     if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).float()
+                        self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).float()
                     else:
-                        self.chatglm_model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+                        self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).half().cuda()
                     self.chatglm_model = self.chatglm_model.eval()
                     break
                 else:

request_llm/bridge_chatglmft.py

@@ -0,0 +1,210 @@
+
+from transformers import AutoModel, AutoTokenizer
+import time
+import os
+import json
+import threading
+import importlib
+from toolbox import update_ui, get_conf
+from multiprocessing import Process, Pipe
+
+load_message = "ChatGLMFT尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，ChatGLMFT消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
+
+def string_to_options(arguments):
+    import argparse
+    import shlex
+    # Create an argparse.ArgumentParser instance
+    parser = argparse.ArgumentParser()
+    # Add command-line arguments
+    parser.add_argument("--llm_to_learn", type=str, help="LLM model to learn", default="gpt-3.5-turbo")
+    parser.add_argument("--prompt_prefix", type=str, help="Prompt prefix", default='')
+    parser.add_argument("--system_prompt", type=str, help="System prompt", default='')
+    parser.add_argument("--batch", type=int, help="System prompt", default=50)
+    # Parse the arguments
+    args = parser.parse_args(shlex.split(arguments))
+    return args
+
+
+#################################################################################
+class GetGLMFTHandle(Process):
+    def __init__(self):
+        super().__init__(daemon=True)
+        self.parent, self.child = Pipe()
+        self.chatglmft_model = None
+        self.chatglmft_tokenizer = None
+        self.info = ""
+        self.success = True
+        self.check_dependency()
+        self.start()
+        self.threadLock = threading.Lock()
+        
+    def check_dependency(self):
+        try:
+            import sentencepiece
+            self.info = "依赖检测通过"
+            self.success = True
+        except:
+            self.info = "缺少ChatGLMFT的依赖，如果要使用ChatGLMFT，除了基础的pip依赖以外，您还需要运行`pip install -r request_llm/requirements_chatglm.txt`安装ChatGLM的依赖。"
+            self.success = False
+
+    def ready(self):
+        return self.chatglmft_model is not None
+
+    def run(self):
+        # 子进程执行
+        # 第一次运行，加载参数
+        retry = 0
+        while True:
+            try:
+                if self.chatglmft_model is None:
+                    from transformers import AutoConfig
+                    import torch
+                    # conf = 'request_llm/current_ptune_model.json'
+                    # if not os.path.exists(conf): raise RuntimeError('找不到微调模型信息')
+                    # with open(conf, 'r', encoding='utf8') as f:
+                    #     model_args = json.loads(f.read())
+                    ChatGLM_PTUNING_CHECKPOINT, = get_conf('ChatGLM_PTUNING_CHECKPOINT')
+                    assert os.path.exists(ChatGLM_PTUNING_CHECKPOINT), "找不到微调模型检查点"
+                    conf = os.path.join(ChatGLM_PTUNING_CHECKPOINT, "config.json")
+                    with open(conf, 'r', encoding='utf8') as f:
+                        model_args = json.loads(f.read())
+                    if 'model_name_or_path' not in model_args:
+                        model_args['model_name_or_path'] = model_args['_name_or_path']
+                    self.chatglmft_tokenizer = AutoTokenizer.from_pretrained(
+                        model_args['model_name_or_path'], trust_remote_code=True)
+                    config = AutoConfig.from_pretrained(
+                        model_args['model_name_or_path'], trust_remote_code=True)
+
+                    config.pre_seq_len = model_args['pre_seq_len']
+                    config.prefix_projection = model_args['prefix_projection']
+
+                    print(f"Loading prefix_encoder weight from {ChatGLM_PTUNING_CHECKPOINT}")
+                    model = AutoModel.from_pretrained(model_args['model_name_or_path'], config=config, trust_remote_code=True)
+                    prefix_state_dict = torch.load(os.path.join(ChatGLM_PTUNING_CHECKPOINT, "pytorch_model.bin"))
+                    new_prefix_state_dict = {}
+                    for k, v in prefix_state_dict.items():
+                        if k.startswith("transformer.prefix_encoder."):
+                            new_prefix_state_dict[k[len("transformer.prefix_encoder."):]] = v
+                    model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
+
+                    if model_args['quantization_bit'] is not None:
+                        print(f"Quantized to {model_args['quantization_bit']} bit")
+                        model = model.quantize(model_args['quantization_bit'])
+                    model = model.cuda()
+                    if model_args['pre_seq_len'] is not None:
+                        # P-tuning v2
+                        model.transformer.prefix_encoder.float()
+                    self.chatglmft_model = model.eval()
+
+                    break
+                else:
+                    break
+            except Exception as e:
+                retry += 1
+                if retry > 3: 
+                    self.child.send('[Local Message] Call ChatGLMFT fail 不能正常加载ChatGLMFT的参数。')
+                    raise RuntimeError("不能正常加载ChatGLMFT的参数！")
+
+        while True:
+            # 进入任务等待状态
+            kwargs = self.child.recv()
+            # 收到消息，开始请求
+            try:
+                for response, history in self.chatglmft_model.stream_chat(self.chatglmft_tokenizer, **kwargs):
+                    self.child.send(response)
+                    # # 中途接收可能的终止指令（如果有的话）
+                    # if self.child.poll(): 
+                    #     command = self.child.recv()
+                    #     if command == '[Terminate]': break
+            except:
+                from toolbox import trimmed_format_exc
+                self.child.send('[Local Message] Call ChatGLMFT fail.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
+            # 请求处理结束，开始下一个循环
+            self.child.send('[Finish]')
+
+    def stream_chat(self, **kwargs):
+        # 主进程执行
+        self.threadLock.acquire()
+        self.parent.send(kwargs)
+        while True:
+            res = self.parent.recv()
+            if res != '[Finish]':
+                yield res
+            else:
+                break
+        self.threadLock.release()
+    
+global glmft_handle
+glmft_handle = None
+#################################################################################
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+    """
+        多线程方法
+        函数的说明请见 request_llm/bridge_all.py
+    """
+    global glmft_handle
+    if glmft_handle is None:
+        glmft_handle = GetGLMFTHandle()
+        if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + glmft_handle.info
+        if not glmft_handle.success: 
+            error = glmft_handle.info
+            glmft_handle = None
+            raise RuntimeError(error)
+
+    # chatglmft 没有 sys_prompt 接口，因此把prompt加入 history
+    history_feedin = []
+    history_feedin.append(["What can I do?", sys_prompt])
+    for i in range(len(history)//2):
+        history_feedin.append([history[2*i], history[2*i+1]] )
+
+    watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
+    response = ""
+    for response in glmft_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
+        if len(observe_window) >= 1:  observe_window[0] = response
+        if len(observe_window) >= 2:  
+            if (time.time()-observe_window[1]) > watch_dog_patience:
+                raise RuntimeError("程序终止。")
+    return response
+
+
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+    """
+        单线程方法
+        函数的说明请见 request_llm/bridge_all.py
+    """
+    chatbot.append((inputs, ""))
+
+    global glmft_handle
+    if glmft_handle is None:
+        glmft_handle = GetGLMFTHandle()
+        chatbot[-1] = (inputs, load_message + "\n\n" + glmft_handle.info)
+        yield from update_ui(chatbot=chatbot, history=[])
+        if not glmft_handle.success: 
+            glmft_handle = None
+            return
+
+    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"]
+
+    # 处理历史信息
+    history_feedin = []
+    history_feedin.append(["What can I do?", system_prompt] )
+    for i in range(len(history)//2):
+        history_feedin.append([history[2*i], history[2*i+1]] )
+
+    # 开始接收chatglmft的回复
+    response = "[Local Message]: 等待ChatGLMFT响应中 ..."
+    for response in glmft_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
+        chatbot[-1] = (inputs, response)
+        yield from update_ui(chatbot=chatbot, history=history)
+
+    # 总结输出
+    if response == "[Local Message]: 等待ChatGLMFT响应中 ...":
+        response = "[Local Message]: ChatGLMFT响应异常 ..."
+    history.extend([inputs, response])
+    yield from update_ui(chatbot=chatbot, history=history)

request_llm/bridge_chatgpt.py

@@ -12,20 +12,18 @@
 """
 
 import json
-import random
 import time
 import gradio as gr
 import logging
 import traceback
 import requests
 import importlib
-import func_box
 
 # config_private.py放自己的秘密如API和代理网址
 # 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
 from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc
-proxies, API_KEY, TIMEOUT_SECONDS, MAX_RETRY = \
-    get_conf('proxies', 'API_KEY', 'TIMEOUT_SECONDS', 'MAX_RETRY')
+proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG = \
+    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG')
 
 timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
                   '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
@@ -62,7 +60,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
     while True:
         try:
             # make a POST request to the API endpoint, stream=False
-            from request_llm.bridge_all import model_info
+            from .bridge_all import model_info
             endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
             response = requests.post(endpoint, headers=headers, proxies=proxies,
                                     json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
@@ -103,6 +101,8 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
                     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 json_data['finish_reason'] == 'content_filter':
+        raise RuntimeError("由于提问含不合规内容被Azure过滤。")
     if json_data['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
@@ -136,22 +136,24 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         inputs = core_functional[additional_fn]["Prefix"] + inputs + core_functional[additional_fn]["Suffix"]
 
     raw_input = inputs
-    logging.info(f'[raw_input]_{llm_kwargs["ipaddr"]} {raw_input}')
+    logging.info(f'[raw_input] {raw_input}')
     chatbot.append((inputs, ""))
-    loading_msg = func_box.spinner_chatbot_loading(chatbot)
-    yield from update_ui(chatbot=loading_msg, history=history, msg="等待响应") # 刷新界面
+    yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+
     try:
         headers, payload = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
     except RuntimeError as e:
         chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
         yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
         return
+        
     history.append(inputs); history.append("")
+
     retry = 0
     while True:
         try:
             # make a POST request to the API endpoint, stream=True
-            from request_llm.bridge_all import model_info
+            from .bridge_all import model_info
             endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
             response = requests.post(endpoint, headers=headers, proxies=proxies,
                                     json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
@@ -163,6 +165,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             if retry > MAX_RETRY: raise TimeoutError
 
     gpt_replying_buffer = ""
+    
     is_head_of_the_stream = True
     if stream:
         stream_response =  response.iter_lines()
@@ -171,9 +174,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
                 chunk = next(stream_response)
             except StopIteration:
                 # 非OpenAI官方接口的出现这样的报错，OpenAI和API2D不会走这里
-                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.decode())}")
-                yield from update_ui(chatbot=chatbot, history=history, msg="远程返回错误:" + chunk.decode()) # 刷新界面
+                chunk_decoded = chunk.decode()
+                error_msg = chunk_decoded
+                chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                yield from update_ui(chatbot=chatbot, history=history, msg="非Openai官方接口返回了错误:" + chunk.decode()) # 刷新界面
                 return
             
             # print(chunk.decode()[6:])
@@ -184,28 +188,32 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
             if chunk:
                 try:
                     chunk_decoded = chunk.decode()
-                    # 前者API2D的
+                    # 前者是API2D的结束条件，后者是OPENAI的结束条件
                     if ('data: [DONE]' in chunk_decoded) or (len(json.loads(chunk_decoded[6:])['choices'][0]["delta"]) == 0):
                         # 判定为数据流的结束，gpt_replying_buffer也写完了
-                        logging.info(f'[response]_{llm_kwargs["ipaddr"]} {gpt_replying_buffer}')
+                        logging.info(f'[response] {gpt_replying_buffer}')
                         break
                     # 处理数据流的主体
                     chunkjson = json.loads(chunk_decoded[6:])
-
+                    status_text = f"finish_reason: {chunkjson['choices'][0]['finish_reason']}"
                     # 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
                     gpt_replying_buffer = gpt_replying_buffer + json.loads(chunk_decoded[6:])['choices'][0]["delta"]["content"]
                     history[-1] = gpt_replying_buffer
                     chatbot[-1] = (history[-2], history[-1])
-                    count_time = round(time.time() - llm_kwargs['start_time'], 3)
-                    status_text = f"finish_reason: {chunkjson['choices'][0]['finish_reason']}\t" \
-                                  f"本次对话耗时: {func_box.html_tag_color(tag=f'{count_time}s')}"
                     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)
                     chunk_decoded = chunk.decode()
                     error_msg = chunk_decoded
+                    chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
+                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
+                    print(error_msg)
+                    return
+
+def handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg):
+    from .bridge_all import model_info
+    openai_website = ' 请登录OpenAI查看详情 https://platform.openai.com/signup'
     if "reduce the length" in error_msg:
         if len(history) >= 2: history[-1] = ""; history[-2] = "" # 清除当前溢出的输入：history[-2] 是本次输入, history[-1] 是本次输出
         history = clip_history(inputs=inputs, history=history, tokenizer=model_info[llm_kwargs['llm_model']]['tokenizer'], 
@@ -215,9 +223,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
     elif "does not exist" in error_msg:
         chatbot[-1] = (chatbot[-1][0], f"[Local Message] Model {llm_kwargs['llm_model']} does not exist. 模型不存在, 或者您没有获得体验资格.")
     elif "Incorrect API key" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务.")
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Incorrect API key. OpenAI以提供了不正确的API_KEY为由, 拒绝服务. " + openai_website)
     elif "exceeded your current quota" in error_msg:
-                        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务.")
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You exceeded your current quota. OpenAI以账户额度不足为由, 拒绝服务." + openai_website)
+    elif "account is not active" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] Your account is not active. OpenAI以账户失效为由, 拒绝服务." + openai_website)
+    elif "associated with a deactivated account" in error_msg:
+        chatbot[-1] = (chatbot[-1][0], "[Local Message] You are associated with a deactivated account. OpenAI以账户失效为由, 拒绝服务." + openai_website)
     elif "bad forward key" in error_msg:
         chatbot[-1] = (chatbot[-1][0], "[Local Message] Bad forward key. API2D账户额度不足.")
     elif "Not enough point" in error_msg:
@@ -226,11 +238,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
         from toolbox import regular_txt_to_markdown
         tb_str = '```\n' + trimmed_format_exc() + '```'
         chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str} \n\n{regular_txt_to_markdown(chunk_decoded)}")
-                    yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + error_msg) # 刷新界面
-                    return
-    count_tokens = func_box.num_tokens_from_string(listing=history)
-    status_text += f'\t 本次对话使用tokens: {func_box.html_tag_color(count_tokens)}'
-    yield from update_ui(chatbot=chatbot, history=history, msg=status_text)  # 刷新界面
+    return chatbot, history
 
 def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     """
@@ -238,18 +246,15 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
     """
     if not is_any_api_key(llm_kwargs['api_key']):
         raise AssertionError("你提供了错误的API_KEY。\n\n1. 临时解决方案：直接在输入区键入api_key，然后回车提交。\n\n2. 长效解决方案：在config.py中配置。")
-    if llm_kwargs['llm_model'].startswith('proxy-'):
-        api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
-        headers = {
-            "Content-Type": "application/json",
-            "api-key": f"{api_key}"
-        }
-    else:
+
     api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
+
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {api_key}"
     }
+    if API_ORG.startswith('org-'): headers.update({"OpenAI-Organization": API_ORG})
+    if llm_kwargs['llm_model'].startswith('azure-'): headers.update({"api-key": api_key})
 
     conversation_cnt = len(history) // 2
 
@@ -286,20 +291,9 @@ def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
         "frequency_penalty": 0,
     }
     try:
-        print("\033[1;35m", f"{llm_kwargs['llm_model']}_{llm_kwargs['ipaddr']} :", "\033[0m", f"{conversation_cnt} : {inputs[:100]} ..........")
+        print(f" {llm_kwargs['llm_model']} : {conversation_cnt} : {inputs[:100]} ..........")
     except:
         print('输入中可能存在乱码。')
     return headers,payload
 
-if __name__ == '__main__':
-    llm_kwargs = {
-        'api_key': 'sk-',
-        'llm_model': 'gpt-3.5-turbo',
-        'top_p': 1,
-        'max_length': 512,
-        'temperature': 1,
-        # 'ipaddr': ipaddr.client.host
-    }
-    chat = []
-    predict('你好', llm_kwargs=llm_kwargs, chatbot=chat, plugin_kwargs={})
-    print(chat)
+

request_llm/bridge_claude.py

@@ -0,0 +1,231 @@
+# 借鉴了 https://github.com/GaiZhenbiao/ChuanhuChatGPT 项目
+
+"""
+    该文件中主要包含2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_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 os
+import json
+import time
+import gradio as gr
+import logging
+import traceback
+import requests
+import importlib
+
+# config_private.py放自己的秘密如API和代理网址
+# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
+from toolbox import get_conf, update_ui, trimmed_format_exc, ProxyNetworkActivate
+proxies, TIMEOUT_SECONDS, MAX_RETRY, ANTHROPIC_API_KEY = \
+    get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'ANTHROPIC_API_KEY')
+
+timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
+                  '网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
+
+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_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
+    """
+    发送至chatGPT，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
+    """
+    from anthropic import Anthropic
+    watch_dog_patience = 5 # 看门狗的耐心, 设置5秒即可
+    prompt = generate_payload(inputs, llm_kwargs, history, system_prompt=sys_prompt, stream=True)
+    retry = 0
+    if len(ANTHROPIC_API_KEY) == 0:
+        raise RuntimeError("没有设置ANTHROPIC_API_KEY选项")
+
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=False
+            from .bridge_all import model_info
+            anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
+            # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            # with ProxyNetworkActivate()
+            stream = anthropic.completions.create(
+                prompt=prompt,
+                max_tokens_to_sample=4096,       # The maximum number of tokens to generate before stopping.
+                model=llm_kwargs['llm_model'],
+                stream=True,
+                temperature = llm_kwargs['temperature']
+            )
+            break
+        except Exception as e:
+            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}) ……')
+    result = ''
+    try: 
+        for completion in stream:
+            result += completion.completion
+            if not console_slience: print(completion.completion, 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] += completion.completion
+                # 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。")
+    except Exception as e:
+        traceback.print_exc()
+
+    return result
+
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+    """
+    发送至chatGPT，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
+    """
+    from anthropic import Anthropic
+    if len(ANTHROPIC_API_KEY) == 0:
+        chatbot.append((inputs, "没有设置ANTHROPIC_API_KEY"))
+        yield from update_ui(chatbot=chatbot, history=history, msg="等待响应") # 刷新界面
+        return
+    
+    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
+
+    try:
+        prompt = generate_payload(inputs, llm_kwargs, history, system_prompt, stream)
+    except RuntimeError as e:
+        chatbot[-1] = (inputs, f"您提供的api-key不满足要求，不包含任何可用于{llm_kwargs['llm_model']}的api-key。您可能选择了错误的模型或请求源。")
+        yield from update_ui(chatbot=chatbot, history=history, msg="api-key不满足要求") # 刷新界面
+        return
+
+    history.append(inputs); history.append("")
+
+    retry = 0
+    while True:
+        try:
+            # make a POST request to the API endpoint, stream=True
+            from .bridge_all import model_info
+            anthropic = Anthropic(api_key=ANTHROPIC_API_KEY)
+            # endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
+            # with ProxyNetworkActivate()
+            stream = anthropic.completions.create(
+                prompt=prompt,
+                max_tokens_to_sample=4096,       # The maximum number of tokens to generate before stopping.
+                model=llm_kwargs['llm_model'],
+                stream=True,
+                temperature = llm_kwargs['temperature']
+            )
+            
+            break
+        except:
+            retry += 1
+            chatbot[-1] = ((chatbot[-1][0], timeout_bot_msg))
+            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 = ""
+    
+    for completion in stream:
+        try:
+            gpt_replying_buffer = gpt_replying_buffer + completion.completion
+            history[-1] = gpt_replying_buffer
+            chatbot[-1] = (history[-2], history[-1])
+            yield from update_ui(chatbot=chatbot, history=history, msg='正常') # 刷新界面
+
+        except Exception as e:
+            from toolbox import regular_txt_to_markdown
+            tb_str = '```\n' + trimmed_format_exc() + '```'
+            chatbot[-1] = (chatbot[-1][0], f"[Local Message] 异常 \n\n{tb_str}")
+            yield from update_ui(chatbot=chatbot, history=history, msg="Json异常" + tb_str) # 刷新界面
+            return
+        
+
+
+
+# https://github.com/jtsang4/claude-to-chatgpt/blob/main/claude_to_chatgpt/adapter.py
+def convert_messages_to_prompt(messages):
+    prompt = ""
+    role_map = {
+        "system": "Human",
+        "user": "Human",
+        "assistant": "Assistant",
+    }
+    for message in messages:
+        role = message["role"]
+        content = message["content"]
+        transformed_role = role_map[role]
+        prompt += f"\n\n{transformed_role.capitalize()}: {content}"
+    prompt += "\n\nAssistant: "
+    return prompt
+
+def generate_payload(inputs, llm_kwargs, history, system_prompt, stream):
+    """
+    整合所有信息，选择LLM模型，生成http请求，为发送请求做准备
+    """
+    from anthropic import Anthropic, HUMAN_PROMPT, AI_PROMPT
+
+    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
+                if what_gpt_answer["content"] == timeout_bot_msg: 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)
+    prompt = convert_messages_to_prompt(messages)
+
+    return prompt
+
+

request_llm/bridge_internlm.py

@@ -0,0 +1,315 @@
+
+from transformers import AutoModel, AutoTokenizer
+import time
+import threading
+import importlib
+from toolbox import update_ui, get_conf, Singleton
+from multiprocessing import Process, Pipe
+
+model_name = "InternLM"
+cmd_to_install = "`pip install ???`"
+load_message = f"{model_name}尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，{model_name}消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
+def try_to_import_special_deps():
+    import sentencepiece
+
+user_prompt = "<|User|>:{user}<eoh>\n"
+robot_prompt = "<|Bot|>:{robot}<eoa>\n"
+cur_query_prompt = "<|User|>:{user}<eoh>\n<|Bot|>:"
+
+
+def combine_history(prompt, hist):
+    messages = hist
+    total_prompt = ""
+    for message in messages:
+        cur_content = message
+        cur_prompt = user_prompt.replace("{user}", cur_content[0])
+        total_prompt += cur_prompt
+        cur_prompt = robot_prompt.replace("{robot}", cur_content[1])
+        total_prompt += cur_prompt
+    total_prompt = total_prompt + cur_query_prompt.replace("{user}", prompt)
+    return total_prompt
+
+
+@Singleton
+class GetInternlmHandle(Process):
+    def __init__(self):
+        # ⭐主进程执行
+        super().__init__(daemon=True)
+        self.parent, self.child = Pipe()
+        self._model = None
+        self._tokenizer = None
+        self.info = ""
+        self.success = True
+        self.check_dependency()
+        self.start()
+        self.threadLock = threading.Lock()
+
+    def ready(self):
+        # ⭐主进程执行
+        return self._model is not None
+
+    def load_model_and_tokenizer(self):
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        import torch
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+        device, = get_conf('LOCAL_MODEL_DEVICE')
+        if self._model is None:
+            tokenizer = AutoTokenizer.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True)
+            if device=='cpu':
+                model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).to(torch.bfloat16)
+            else:
+                model = AutoModelForCausalLM.from_pretrained("internlm/internlm-chat-7b", trust_remote_code=True).to(torch.bfloat16).cuda()
+
+            model = model.eval()
+        return model, tokenizer
+
+    def llm_stream_generator(self, **kwargs):
+        import torch
+        import logging
+        import copy
+        import warnings
+        import torch.nn as nn
+        from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList, GenerationConfig
+
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        def adaptor():
+            model = self._model
+            tokenizer = self._tokenizer
+            prompt = kwargs['query']
+            max_length = kwargs['max_length']
+            top_p = kwargs['top_p']
+            temperature = kwargs['temperature']
+            history = kwargs['history']
+            real_prompt = combine_history(prompt, history)
+            return model, tokenizer, real_prompt, max_length, top_p, temperature
+        
+        model, tokenizer, prompt, max_length, top_p, temperature = adaptor()
+        prefix_allowed_tokens_fn = None
+        logits_processor = None
+        stopping_criteria = None
+        additional_eos_token_id = 103028
+        generation_config = None
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ https://github.com/InternLM/InternLM/blob/efbf5335709a8c8faeac6eaf07193973ff1d56a1/web_demo.py#L25
+
+        inputs = tokenizer([prompt], padding=True, return_tensors="pt")
+        input_length = len(inputs["input_ids"][0])
+        for k, v in inputs.items():
+            inputs[k] = v.cuda()
+        input_ids = inputs["input_ids"]
+        batch_size, input_ids_seq_length = input_ids.shape[0], input_ids.shape[-1]
+        if generation_config is None:
+            generation_config = model.generation_config
+        generation_config = copy.deepcopy(generation_config)
+        model_kwargs = generation_config.update(**kwargs)
+        bos_token_id, eos_token_id = generation_config.bos_token_id, generation_config.eos_token_id
+        if isinstance(eos_token_id, int):
+            eos_token_id = [eos_token_id]
+        if additional_eos_token_id is not None:
+            eos_token_id.append(additional_eos_token_id)
+        has_default_max_length = kwargs.get("max_length") is None and generation_config.max_length is not None
+        if has_default_max_length and generation_config.max_new_tokens is None:
+            warnings.warn(
+                f"Using `max_length`'s default ({generation_config.max_length}) to control the generation length. "
+                "This behaviour is deprecated and will be removed from the config in v5 of Transformers -- we"
+                " recommend using `max_new_tokens` to control the maximum length of the generation.",
+                UserWarning,
+            )
+        elif generation_config.max_new_tokens is not None:
+            generation_config.max_length = generation_config.max_new_tokens + input_ids_seq_length
+            if not has_default_max_length:
+                logging.warn(
+                    f"Both `max_new_tokens` (={generation_config.max_new_tokens}) and `max_length`(="
+                    f"{generation_config.max_length}) seem to have been set. `max_new_tokens` will take precedence. "
+                    "Please refer to the documentation for more information. "
+                    "(https://huggingface.co/docs/transformers/main/en/main_classes/text_generation)",
+                    UserWarning,
+                )
+
+        if input_ids_seq_length >= generation_config.max_length:
+            input_ids_string = "input_ids"
+            logging.warning(
+                f"Input length of {input_ids_string} is {input_ids_seq_length}, but `max_length` is set to"
+                f" {generation_config.max_length}. This can lead to unexpected behavior. You should consider"
+                " increasing `max_new_tokens`."
+            )
+
+        # 2. Set generation parameters if not already defined
+        logits_processor = logits_processor if logits_processor is not None else LogitsProcessorList()
+        stopping_criteria = stopping_criteria if stopping_criteria is not None else StoppingCriteriaList()
+
+        logits_processor = model._get_logits_processor(
+            generation_config=generation_config,
+            input_ids_seq_length=input_ids_seq_length,
+            encoder_input_ids=input_ids,
+            prefix_allowed_tokens_fn=prefix_allowed_tokens_fn,
+            logits_processor=logits_processor,
+        )
+
+        stopping_criteria = model._get_stopping_criteria(
+            generation_config=generation_config, stopping_criteria=stopping_criteria
+        )
+        logits_warper = model._get_logits_warper(generation_config)
+
+        unfinished_sequences = input_ids.new(input_ids.shape[0]).fill_(1)
+        scores = None
+        while True:
+            model_inputs = model.prepare_inputs_for_generation(input_ids, **model_kwargs)
+            # forward pass to get next token
+            outputs = model(
+                **model_inputs,
+                return_dict=True,
+                output_attentions=False,
+                output_hidden_states=False,
+            )
+
+            next_token_logits = outputs.logits[:, -1, :]
+
+            # pre-process distribution
+            next_token_scores = logits_processor(input_ids, next_token_logits)
+            next_token_scores = logits_warper(input_ids, next_token_scores)
+
+            # sample
+            probs = nn.functional.softmax(next_token_scores, dim=-1)
+            if generation_config.do_sample:
+                next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
+            else:
+                next_tokens = torch.argmax(probs, dim=-1)
+
+            # update generated ids, model inputs, and length for next step
+            input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
+            model_kwargs = model._update_model_kwargs_for_generation(
+                outputs, model_kwargs, is_encoder_decoder=False
+            )
+            unfinished_sequences = unfinished_sequences.mul((min(next_tokens != i for i in eos_token_id)).long())
+            
+            output_token_ids = input_ids[0].cpu().tolist()
+            output_token_ids = output_token_ids[input_length:]
+            for each_eos_token_id in eos_token_id:
+                if output_token_ids[-1] == each_eos_token_id:
+                    output_token_ids = output_token_ids[:-1]
+            response = tokenizer.decode(output_token_ids)
+
+            yield response
+            # stop when each sentence is finished, or if we exceed the maximum length
+            if unfinished_sequences.max() == 0 or stopping_criteria(input_ids, scores):
+                return
+
+
+
+    def check_dependency(self):
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        try:
+            try_to_import_special_deps()
+            self.info = "依赖检测通过"
+            self.success = True
+        except:
+            self.info = f"缺少{model_name}的依赖，如果要使用{model_name}，除了基础的pip依赖以外，您还需要运行{cmd_to_install}安装{model_name}的依赖。"
+            self.success = False
+
+    def run(self):
+        # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
+        # 第一次运行，加载参数
+        try:
+            self._model, self._tokenizer = self.load_model_and_tokenizer()
+        except:
+            from toolbox import trimmed_format_exc
+            self.child.send(f'[Local Message] 不能正常加载{model_name}的参数.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
+            raise RuntimeError(f"不能正常加载{model_name}的参数！")
+
+        while True:
+            # 进入任务等待状态
+            kwargs = self.child.recv()
+            # 收到消息，开始请求
+            try:
+                for response_full in self.llm_stream_generator(**kwargs):
+                    self.child.send(response_full)
+            except:
+                from toolbox import trimmed_format_exc
+                self.child.send(f'[Local Message] 调用{model_name}失败.' + '\n```\n' + trimmed_format_exc() + '\n```\n')
+            # 请求处理结束，开始下一个循环
+            self.child.send('[Finish]')
+
+    def stream_chat(self, **kwargs):
+        # ⭐主进程执行
+        self.threadLock.acquire()
+        self.parent.send(kwargs)
+        while True:
+            res = self.parent.recv()
+            if res != '[Finish]':
+                yield res
+            else:
+                break
+        self.threadLock.release()
+    
+    
+# ------------------------------------------------------------------------------------------------------------------------
+# 🔌💻 GPT-Academic
+# ------------------------------------------------------------------------------------------------------------------------
+def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=[], console_slience=False):
+    """
+        ⭐多线程方法
+        函数的说明请见 request_llm/bridge_all.py
+    """
+    _llm_handle = GetInternlmHandle()
+    if len(observe_window) >= 1: observe_window[0] = load_message + "\n\n" + _llm_handle.info
+    if not _llm_handle.success: 
+        error = _llm_handle.info
+        _llm_handle = None
+        raise RuntimeError(error)
+
+    # chatglm 没有 sys_prompt 接口，因此把prompt加入 history
+    history_feedin = []
+    history_feedin.append(["What can I do?", sys_prompt])
+    for i in range(len(history)//2):
+        history_feedin.append([history[2*i], history[2*i+1]] )
+
+    watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
+    response = ""
+    for response in _llm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
+        if len(observe_window) >= 1:  observe_window[0] = response
+        if len(observe_window) >= 2:  
+            if (time.time()-observe_window[1]) > watch_dog_patience:
+                raise RuntimeError("程序终止。")
+    return response
+
+
+
+def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
+    """
+        ⭐单线程方法
+        函数的说明请见 request_llm/bridge_all.py
+    """
+    chatbot.append((inputs, ""))
+
+    _llm_handle = GetInternlmHandle()
+    chatbot[-1] = (inputs, load_message + "\n\n" + _llm_handle.info)
+    yield from update_ui(chatbot=chatbot, history=[])
+    if not _llm_handle.success: 
+        _llm_handle = None
+        return
+
+    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"]
+
+    # 处理历史信息
+    history_feedin = []
+    history_feedin.append(["What can I do?", system_prompt] )
+    for i in range(len(history)//2):
+        history_feedin.append([history[2*i], history[2*i+1]] )
+
+    # 开始接收chatglm的回复
+    response = f"[Local Message]: 等待{model_name}响应中 ..."
+    for response in _llm_handle.stream_chat(query=inputs, history=history_feedin, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
+        chatbot[-1] = (inputs, response)
+        yield from update_ui(chatbot=chatbot, history=history)
+
+    # 总结输出
+    if response == f"[Local Message]: 等待{model_name}响应中 ...":
+        response = f"[Local Message]: {model_name}响应异常 ..."
+    history.extend([inputs, response])
+    yield from update_ui(chatbot=chatbot, history=history)

request_llm/bridge_newbing.py

@@ -1,254 +0,0 @@
-"""
-========================================================================
-第一部分：来自EdgeGPT.py
-https://github.com/acheong08/EdgeGPT
-========================================================================
-"""
-from .edge_gpt import NewbingChatbot
-load_message = "等待NewBing响应。"
-
-"""
-========================================================================
-第二部分：子进程Worker（调用主体）
-========================================================================
-"""
-import time
-import json
-import re
-import logging
-import asyncio
-import importlib
-import threading
-from toolbox import update_ui, get_conf, trimmed_format_exc
-from multiprocessing import Process, Pipe
-
-def preprocess_newbing_out(s):
-    pattern = r'\^(\d+)\^' # 匹配^数字^
-    sub = lambda m: '('+m.group(1)+')' # 将匹配到的数字作为替换值
-    result = re.sub(pattern, sub, s) # 替换操作
-    if '[1]' in result:
-        result += '\n\n```reference\n' + "\n".join([r for r in result.split('\n') if r.startswith('[')]) + '\n```\n'
-    return result
-
-def preprocess_newbing_out_simple(result):
-    if '[1]' in result:
-        result += '\n\n```reference\n' + "\n".join([r for r in result.split('\n') if r.startswith('[')]) + '\n```\n'
-    return result
-
-class NewBingHandle(Process):
-    def __init__(self):
-        super().__init__(daemon=True)
-        self.parent, self.child = Pipe()
-        self.newbing_model = None
-        self.info = ""
-        self.success = True
-        self.local_history = []
-        self.check_dependency()
-        self.start()
-        self.threadLock = threading.Lock()
-        
-    def check_dependency(self):
-        try:
-            self.success = False
-            import certifi, httpx, rich
-            self.info = "依赖检测通过，等待NewBing响应。注意目前不能多人同时调用NewBing接口（有线程锁），否则将导致每个人的NewBing问询历史互相渗透。调用NewBing时，会自动使用已配置的代理。"
-            self.success = True
-        except:
-            self.info = "缺少的依赖，如果要使用Newbing，除了基础的pip依赖以外，您还需要运行`pip install -r request_llm/requirements_newbing.txt`安装Newbing的依赖。"
-            self.success = False
-
-    def ready(self):
-        return self.newbing_model is not None
-
-    async def async_run(self):
-        # 读取配置
-        NEWBING_STYLE, = get_conf('NEWBING_STYLE')
-        from request_llm.bridge_all import model_info
-        endpoint = model_info['newbing']['endpoint']
-        while True:
-            # 等待
-            kwargs = self.child.recv()
-            question=kwargs['query']
-            history=kwargs['history']
-            system_prompt=kwargs['system_prompt']
-
-            # 是否重置
-            if len(self.local_history) > 0 and len(history)==0:
-                await self.newbing_model.reset()
-                self.local_history = []
-
-            # 开始问问题
-            prompt = ""
-            if system_prompt not in self.local_history:
-                self.local_history.append(system_prompt)
-                prompt += system_prompt + '\n'
-
-            # 追加历史
-            for ab in history:
-                a, b = ab
-                if a not in self.local_history:
-                    self.local_history.append(a)
-                    prompt += a + '\n'
-                # if b not in self.local_history:
-                #     self.local_history.append(b)
-                #     prompt += b + '\n'
-
-            # 问题
-            prompt += question
-            self.local_history.append(question)
-            print('question:', prompt)
-            # 提交
-            async for final, response in self.newbing_model.ask_stream(
-                prompt=question,
-                conversation_style=NEWBING_STYLE,     # ["creative", "balanced", "precise"]
-                wss_link=endpoint,                      # "wss://sydney.bing.com/sydney/ChatHub"
-            ):
-                if not final:
-                    print(response)
-                    self.child.send(str(response))
-                else:
-                    print('-------- receive final ---------')
-                    self.child.send('[Finish]')
-                    # self.local_history.append(response)
-
-    
-    def run(self):
-        """
-        这个函数运行在子进程
-        """
-        # 第一次运行，加载参数
-        self.success = False
-        self.local_history = []
-        if (self.newbing_model is None) or (not self.success):
-            # 代理设置
-            proxies, = get_conf('proxies')
-            if proxies is None: 
-                self.proxies_https = None
-            else: 
-                self.proxies_https = proxies['https']
-            # cookie
-            NEWBING_COOKIES, = get_conf('NEWBING_COOKIES')
-            try:
-                cookies = json.loads(NEWBING_COOKIES)
-            except:
-                self.success = False
-                tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
-                self.child.send(f'[Local Message] 不能加载Newbing组件。NEWBING_COOKIES未填写或有格式错误。')
-                self.child.send('[Fail]')
-                self.child.send('[Finish]')
-                raise RuntimeError(f"不能加载Newbing组件。NEWBING_COOKIES未填写或有格式错误。")
-
-            try:
-                self.newbing_model = NewbingChatbot(proxy=self.proxies_https, cookies=cookies)
-            except:
-                self.success = False
-                tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
-                self.child.send(f'[Local Message] 不能加载Newbing组件。{tb_str}')
-                self.child.send('[Fail]')
-                self.child.send('[Finish]')
-                raise RuntimeError(f"不能加载Newbing组件。")
-
-        self.success = True
-        try:
-            # 进入任务等待状态
-            asyncio.run(self.async_run())
-        except Exception:
-            tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
-            self.child.send(f'[Local Message] Newbing失败 {tb_str}.')
-            self.child.send('[Fail]')
-            self.child.send('[Finish]')
-        
-    def stream_chat(self, **kwargs):
-        """
-        这个函数运行在主进程
-        """
-        self.threadLock.acquire()
-        self.parent.send(kwargs)    # 发送请求到子进程
-        while True:
-            res = self.parent.recv()    # 等待newbing回复的片段
-            if res == '[Finish]':
-                break       # 结束
-            elif res == '[Fail]':
-                self.success = False
-                break
-            else:
-                yield res   # newbing回复的片段
-        self.threadLock.release()
-
-
-"""
-========================================================================
-第三部分：主进程统一调用函数接口
-========================================================================
-"""
-global newbing_handle
-newbing_handle = None
-
-def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
-    """
-        多线程方法
-        函数的说明请见 request_llm/bridge_all.py
-    """
-    global newbing_handle
-    if (newbing_handle is None) or (not newbing_handle.success):
-        newbing_handle = NewBingHandle()
-        observe_window[0] = load_message + "\n\n" + newbing_handle.info
-        if not newbing_handle.success: 
-            error = newbing_handle.info
-            newbing_handle = None
-            raise RuntimeError(error)
-
-    # 没有 sys_prompt 接口，因此把prompt加入 history
-    history_feedin = []
-    for i in range(len(history)//2):
-        history_feedin.append([history[2*i], history[2*i+1]] )
-
-    watch_dog_patience = 5 # 看门狗 (watchdog) 的耐心, 设置5秒即可
-    response = ""
-    observe_window[0] = "[Local Message]: 等待NewBing响应中 ..."
-    for response in newbing_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=sys_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
-        observe_window[0] = preprocess_newbing_out_simple(response)
-        if len(observe_window) >= 2:  
-            if (time.time()-observe_window[1]) > watch_dog_patience:
-                raise RuntimeError("程序终止。")
-    return preprocess_newbing_out_simple(response)
-
-def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_prompt='', stream = True, additional_fn=None):
-    """
-        单线程方法
-        函数的说明请见 request_llm/bridge_all.py
-    """
-    chatbot.append((inputs, "[Local Message]: 等待NewBing响应中 ..."))
-
-    global newbing_handle
-    if (newbing_handle is None) or (not newbing_handle.success):
-        newbing_handle = NewBingHandle()
-        chatbot[-1] = (inputs, load_message + "\n\n" + newbing_handle.info)
-        yield from update_ui(chatbot=chatbot, history=[])
-        if not newbing_handle.success: 
-            newbing_handle = None
-            return
-
-    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"]
-
-    history_feedin = []
-    for i in range(len(history)//2):
-        history_feedin.append([history[2*i], history[2*i+1]] )
-
-    chatbot[-1] = (inputs, "[Local Message]: 等待NewBing响应中 ...")
-    response = "[Local Message]: 等待NewBing响应中 ..."
-    yield from update_ui(chatbot=chatbot, history=history, msg="NewBing响应缓慢，尚未完成全部响应，请耐心完成后再提交新问题。")
-    for response in newbing_handle.stream_chat(query=inputs, history=history_feedin, system_prompt=system_prompt, max_length=llm_kwargs['max_length'], top_p=llm_kwargs['top_p'], temperature=llm_kwargs['temperature']):
-        chatbot[-1] = (inputs, preprocess_newbing_out(response))
-        yield from update_ui(chatbot=chatbot, history=history, msg="NewBing响应缓慢，尚未完成全部响应，请耐心完成后再提交新问题。")
-    if response == "[Local Message]: 等待NewBing响应中 ...": response = "[Local Message]: NewBing响应异常，请刷新界面重试 ..."
-    history.extend([inputs, response])
-    logging.info(f'[raw_input] {inputs}')
-    logging.info(f'[response] {response}')
-    yield from update_ui(chatbot=chatbot, history=history, msg="完成全部响应，请提交新问题。")
-

request_llm/bridge_newbingfree.py

@@ -89,9 +89,6 @@ class NewBingHandle(Process):
                 if a not in self.local_history:
                     self.local_history.append(a)
                     prompt += a + '\n'
-                # if b not in self.local_history:
-                #     self.local_history.append(b)
-                #     prompt += b + '\n'
 
             # 问题
             prompt += question
@@ -121,14 +118,26 @@ class NewBingHandle(Process):
         self.local_history = []
         if (self.newbing_model is None) or (not self.success):
             # 代理设置
-            proxies, = get_conf('proxies')
+            proxies, NEWBING_COOKIES = get_conf('proxies', 'NEWBING_COOKIES')
             if proxies is None: 
                 self.proxies_https = None
             else: 
                 self.proxies_https = proxies['https']
 
+            if (NEWBING_COOKIES is not None) and len(NEWBING_COOKIES) > 100:
                 try:
-                self.newbing_model = NewbingChatbot(proxy=self.proxies_https)
+                    cookies = json.loads(NEWBING_COOKIES)
+                except:
+                    self.success = False
+                    tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
+                    self.child.send(f'[Local Message] NEWBING_COOKIES未填写或有格式错误。')
+                    self.child.send('[Fail]'); self.child.send('[Finish]')
+                    raise RuntimeError(f"NEWBING_COOKIES未填写或有格式错误。")
+            else:
+                cookies = None
+
+            try:
+                self.newbing_model = NewbingChatbot(proxy=self.proxies_https, cookies=cookies)
             except:
                 self.success = False
                 tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
@@ -143,7 +152,7 @@ class NewBingHandle(Process):
             asyncio.run(self.async_run())
         except Exception:
             tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
-            self.child.send(f'[Local Message] Newbing失败 {tb_str}.')
+            self.child.send(f'[Local Message] Newbing 请求失败，报错信息如下. 如果是与网络相关的问题，建议更换代理协议（推荐http）或代理节点 {tb_str}.')
             self.child.send('[Fail]')
             self.child.send('[Finish]')
         
@@ -151,18 +160,14 @@ class NewBingHandle(Process):
         """
         这个函数运行在主进程
         """
-        self.threadLock.acquire()
-        self.parent.send(kwargs)    # 发送请求到子进程
+        self.threadLock.acquire()   # 获取线程锁
+        self.parent.send(kwargs)    # 请求子进程
         while True:
             res = self.parent.recv()                            # 等待newbing回复的片段
-            if res == '[Finish]':
-                break       # 结束
-            elif res == '[Fail]':
-                self.success = False
-                break
-            else:
-                yield res   # newbing回复的片段
-        self.threadLock.release()
+            if res == '[Finish]': break                         # 结束
+            elif res == '[Fail]': self.success = False; break   # 失败
+            else: yield res                                     # newbing回复的片段
+        self.threadLock.release()   # 释放线程锁
 
 
 """

request_llm/bridge_stackclaude.py

@@ -1,4 +1,4 @@
-from .bridge_newbing import preprocess_newbing_out, preprocess_newbing_out_simple
+from .bridge_newbingfree import preprocess_newbing_out, preprocess_newbing_out_simple
 from multiprocessing import Process, Pipe
 from toolbox import update_ui, get_conf, trimmed_format_exc
 import threading

request_llm/edge_gpt.py

@@ -1,409 +0,0 @@
-"""
-========================================================================
-第一部分：来自EdgeGPT.py
-https://github.com/acheong08/EdgeGPT
-========================================================================
-"""
-
-import argparse
-import asyncio
-import json
-import os
-import random
-import re
-import ssl
-import sys
-import uuid
-from enum import Enum
-from typing import Generator
-from typing import Literal
-from typing import Optional
-from typing import Union
-import websockets.client as websockets
-
-DELIMITER = "\x1e"
-
-
-# Generate random IP between range 13.104.0.0/14
-FORWARDED_IP = (
-    f"13.{random.randint(104, 107)}.{random.randint(0, 255)}.{random.randint(0, 255)}"
-)
-
-HEADERS = {
-    "accept": "application/json",
-    "accept-language": "en-US,en;q=0.9",
-    "content-type": "application/json",
-    "sec-ch-ua": '"Not_A Brand";v="99", "Microsoft Edge";v="110", "Chromium";v="110"',
-    "sec-ch-ua-arch": '"x86"',
-    "sec-ch-ua-bitness": '"64"',
-    "sec-ch-ua-full-version": '"109.0.1518.78"',
-    "sec-ch-ua-full-version-list": '"Chromium";v="110.0.5481.192", "Not A(Brand";v="24.0.0.0", "Microsoft Edge";v="110.0.1587.69"',
-    "sec-ch-ua-mobile": "?0",
-    "sec-ch-ua-model": "",
-    "sec-ch-ua-platform": '"Windows"',
-    "sec-ch-ua-platform-version": '"15.0.0"',
-    "sec-fetch-dest": "empty",
-    "sec-fetch-mode": "cors",
-    "sec-fetch-site": "same-origin",
-    "x-ms-client-request-id": str(uuid.uuid4()),
-    "x-ms-useragent": "azsdk-js-api-client-factory/1.0.0-beta.1 core-rest-pipeline/1.10.0 OS/Win32",
-    "Referer": "https://www.bing.com/search?q=Bing+AI&showconv=1&FORM=hpcodx",
-    "Referrer-Policy": "origin-when-cross-origin",
-    "x-forwarded-for": FORWARDED_IP,
-}
-
-HEADERS_INIT_CONVER = {
-    "authority": "edgeservices.bing.com",
-    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
-    "accept-language": "en-US,en;q=0.9",
-    "cache-control": "max-age=0",
-    "sec-ch-ua": '"Chromium";v="110", "Not A(Brand";v="24", "Microsoft Edge";v="110"',
-    "sec-ch-ua-arch": '"x86"',
-    "sec-ch-ua-bitness": '"64"',
-    "sec-ch-ua-full-version": '"110.0.1587.69"',
-    "sec-ch-ua-full-version-list": '"Chromium";v="110.0.5481.192", "Not A(Brand";v="24.0.0.0", "Microsoft Edge";v="110.0.1587.69"',
-    "sec-ch-ua-mobile": "?0",
-    "sec-ch-ua-model": '""',
-    "sec-ch-ua-platform": '"Windows"',
-    "sec-ch-ua-platform-version": '"15.0.0"',
-    "sec-fetch-dest": "document",
-    "sec-fetch-mode": "navigate",
-    "sec-fetch-site": "none",
-    "sec-fetch-user": "?1",
-    "upgrade-insecure-requests": "1",
-    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.69",
-    "x-edge-shopping-flag": "1",
-    "x-forwarded-for": FORWARDED_IP,
-}
-
-def get_ssl_context():
-    import certifi
-    ssl_context = ssl.create_default_context()
-    ssl_context.load_verify_locations(certifi.where())
-    return ssl_context
-
-
-
-class NotAllowedToAccess(Exception):
-    pass
-
-
-class ConversationStyle(Enum):
-    creative = "h3imaginative,clgalileo,gencontentv3"
-    balanced = "galileo"
-    precise = "h3precise,clgalileo"
-
-
-CONVERSATION_STYLE_TYPE = Optional[
-    Union[ConversationStyle, Literal["creative", "balanced", "precise"]]
-]
-
-
-def _append_identifier(msg: dict) -> str:
-    """
-    Appends special character to end of message to identify end of message
-    """
-    # Convert dict to json string
-    return json.dumps(msg) + DELIMITER
-
-
-def _get_ran_hex(length: int = 32) -> str:
-    """
-    Returns random hex string
-    """
-    return "".join(random.choice("0123456789abcdef") for _ in range(length))
-
-
-class _ChatHubRequest:
-    """
-    Request object for ChatHub
-    """
-
-    def __init__(
-        self,
-        conversation_signature: str,
-        client_id: str,
-        conversation_id: str,
-        invocation_id: int = 0,
-    ) -> None:
-        self.struct: dict = {}
-
-        self.client_id: str = client_id
-        self.conversation_id: str = conversation_id
-        self.conversation_signature: str = conversation_signature
-        self.invocation_id: int = invocation_id
-
-    def update(
-        self,
-        prompt,
-        conversation_style,
-        options,
-    ) -> None:
-        """
-        Updates request object
-        """
-        if options is None:
-            options = [
-                "deepleo",
-                "enable_debug_commands",
-                "disable_emoji_spoken_text",
-                "enablemm",
-            ]
-        if conversation_style:
-            if not isinstance(conversation_style, ConversationStyle):
-                conversation_style = getattr(ConversationStyle, conversation_style)
-            options = [
-                "nlu_direct_response_filter",
-                "deepleo",
-                "disable_emoji_spoken_text",
-                "responsible_ai_policy_235",
-                "enablemm",
-                conversation_style.value,
-                "dtappid",
-                "cricinfo",
-                "cricinfov2",
-                "dv3sugg",
-            ]
-        self.struct = {
-            "arguments": [
-                {
-                    "source": "cib",
-                    "optionsSets": options,
-                    "sliceIds": [
-                        "222dtappid",
-                        "225cricinfo",
-                        "224locals0",
-                    ],
-                    "traceId": _get_ran_hex(32),
-                    "isStartOfSession": self.invocation_id == 0,
-                    "message": {
-                        "author": "user",
-                        "inputMethod": "Keyboard",
-                        "text": prompt,
-                        "messageType": "Chat",
-                    },
-                    "conversationSignature": self.conversation_signature,
-                    "participant": {
-                        "id": self.client_id,
-                    },
-                    "conversationId": self.conversation_id,
-                },
-            ],
-            "invocationId": str(self.invocation_id),
-            "target": "chat",
-            "type": 4,
-        }
-        self.invocation_id += 1
-
-
-class _Conversation:
-    """
-    Conversation API
-    """
-
-    def __init__(
-        self,
-        cookies,
-        proxy,
-    ) -> None:
-        self.struct: dict = {
-            "conversationId": None,
-            "clientId": None,
-            "conversationSignature": None,
-            "result": {"value": "Success", "message": None},
-        }
-        import httpx
-        self.proxy = proxy
-        proxy = (
-            proxy
-            or os.environ.get("all_proxy")
-            or os.environ.get("ALL_PROXY")
-            or os.environ.get("https_proxy")
-            or os.environ.get("HTTPS_PROXY")
-            or None
-        )
-        if proxy is not None and proxy.startswith("socks5h://"):
-            proxy = "socks5://" + proxy[len("socks5h://") :]
-        self.session = httpx.Client(
-            proxies=proxy,
-            timeout=30,
-            headers=HEADERS_INIT_CONVER,
-        )
-        for cookie in cookies:
-            self.session.cookies.set(cookie["name"], cookie["value"])
-
-        # Send GET request
-        response = self.session.get(
-            url=os.environ.get("BING_PROXY_URL")
-            or "https://edgeservices.bing.com/edgesvc/turing/conversation/create",
-        )
-        if response.status_code != 200:
-            response = self.session.get(
-                "https://edge.churchless.tech/edgesvc/turing/conversation/create",
-            )
-        if response.status_code != 200:
-            print(f"Status code: {response.status_code}")
-            print(response.text)
-            print(response.url)
-            raise Exception("Authentication failed")
-        try:
-            self.struct = response.json()
-        except (json.decoder.JSONDecodeError, NotAllowedToAccess) as exc:
-            raise Exception(
-                "Authentication failed. You have not been accepted into the beta.",
-            ) from exc
-        if self.struct["result"]["value"] == "UnauthorizedRequest":
-            raise NotAllowedToAccess(self.struct["result"]["message"])
-
-
-class _ChatHub:
-    """
-    Chat API
-    """
-
-    def __init__(self, conversation) -> None:
-        self.wss = None
-        self.request: _ChatHubRequest
-        self.loop: bool
-        self.task: asyncio.Task
-        print(conversation.struct)
-        self.request = _ChatHubRequest(
-            conversation_signature=conversation.struct["conversationSignature"],
-            client_id=conversation.struct["clientId"],
-            conversation_id=conversation.struct["conversationId"],
-        )
-
-    async def ask_stream(
-        self,
-        prompt: str,
-        wss_link: str,
-        conversation_style: CONVERSATION_STYLE_TYPE = None,
-        raw: bool = False,
-        options: dict = None,
-    ) -> Generator[str, None, None]:
-        """
-        Ask a question to the bot
-        """
-        if self.wss and not self.wss.closed:
-            await self.wss.close()
-        # Check if websocket is closed
-        self.wss = await websockets.connect(
-            wss_link,
-            extra_headers=HEADERS,
-            max_size=None,
-            ssl=get_ssl_context()
-        )
-        await self._initial_handshake()
-        # Construct a ChatHub request
-        self.request.update(
-            prompt=prompt,
-            conversation_style=conversation_style,
-            options=options,
-        )
-        # Send request
-        await self.wss.send(_append_identifier(self.request.struct))
-        final = False
-        while not final:
-            objects = str(await self.wss.recv()).split(DELIMITER)
-            for obj in objects:
-                if obj is None or not obj:
-                    continue
-                response = json.loads(obj)
-                if response.get("type") != 2 and raw:
-                    yield False, response
-                elif response.get("type") == 1 and response["arguments"][0].get(
-                    "messages",
-                ):
-                    resp_txt = response["arguments"][0]["messages"][0]["adaptiveCards"][
-                        0
-                    ]["body"][0].get("text")
-                    yield False, resp_txt
-                elif response.get("type") == 2:
-                    final = True
-                    yield True, response
-
-    async def _initial_handshake(self) -> None:
-        await self.wss.send(_append_identifier({"protocol": "json", "version": 1}))
-        await self.wss.recv()
-
-    async def close(self) -> None:
-        """
-        Close the connection
-        """
-        if self.wss and not self.wss.closed:
-            await self.wss.close()
-
-
-class NewbingChatbot:
-    """
-    Combines everything to make it seamless
-    """
-
-    def __init__(
-        self,
-        cookies,
-        proxy
-    ) -> None:
-        if cookies is None:
-            cookies = {}
-        self.cookies = cookies
-        self.proxy = proxy
-        self.chat_hub: _ChatHub = _ChatHub(
-            _Conversation(self.cookies, self.proxy),
-        )
-
-    async def ask(
-        self,
-        prompt: str,
-        wss_link: str,
-        conversation_style: CONVERSATION_STYLE_TYPE = None,
-        options: dict = None,
-    ) -> dict:
-        """
-        Ask a question to the bot
-        """
-        async for final, response in self.chat_hub.ask_stream(
-            prompt=prompt,
-            conversation_style=conversation_style,
-            wss_link=wss_link,
-            options=options,
-        ):
-            if final:
-                return response
-        await self.chat_hub.wss.close()
-        return None
-
-    async def ask_stream(
-        self,
-        prompt: str,
-        wss_link: str,
-        conversation_style: CONVERSATION_STYLE_TYPE = None,
-        raw: bool = False,
-        options: dict = None,
-    ) -> Generator[str, None, None]:
-        """
-        Ask a question to the bot
-        """
-        async for response in self.chat_hub.ask_stream(
-            prompt=prompt,
-            conversation_style=conversation_style,
-            wss_link=wss_link,
-            raw=raw,
-            options=options,
-        ):
-            yield response
-
-    async def close(self) -> None:
-        """
-        Close the connection
-        """
-        await self.chat_hub.close()
-
-    async def reset(self) -> None:
-        """
-        Reset the conversation
-        """
-        await self.close()
-        self.chat_hub = _ChatHub(_Conversation(self.cookies, self.proxy))
-
-

request_llm/edge_gpt_free.py

@@ -447,6 +447,15 @@ class _ChatHub:
         """
         Ask a question to the bot
         """
+        req_header = HEADERS
+        if self.cookies is not None:
+            ws_cookies = []
+            for cookie in self.cookies:
+                ws_cookies.append(f"{cookie['name']}={cookie['value']}")
+            req_header.update({
+                'Cookie': ';'.join(ws_cookies),
+            })
+            
         timeout = aiohttp.ClientTimeout(total=30)
         self.session = aiohttp.ClientSession(timeout=timeout)
 
@@ -455,7 +464,7 @@ class _ChatHub:
         # Check if websocket is closed
         self.wss = await self.session.ws_connect(
             wss_link,
-            headers=HEADERS,
+            headers=req_header,
             ssl=ssl_context,
             proxy=self.proxy,
             autoping=False,
@@ -510,7 +519,11 @@ class _ChatHub:
         resp_txt_no_link = ""
         while not final:
             msg = await self.wss.receive()
+            try:
                 objects = msg.data.split(DELIMITER)
+            except :
+                continue
+            
             for obj in objects:
                 if obj is None or not obj:
                     continue

request_llm/test_llms.py

@@ -10,10 +10,12 @@ def validate_path():
     
 validate_path() # validate path so you can run from base directory
 if __name__ == "__main__":
-    from request_llm.bridge_newbingfree import predict_no_ui_long_connection
+    # from request_llm.bridge_newbingfree import predict_no_ui_long_connection
     # from request_llm.bridge_moss import predict_no_ui_long_connection
     # from request_llm.bridge_jittorllms_pangualpha import predict_no_ui_long_connection
     # from request_llm.bridge_jittorllms_llama import predict_no_ui_long_connection
+    # from request_llm.bridge_claude import predict_no_ui_long_connection
+    from request_llm.bridge_internlm import predict_no_ui_long_connection
 
     llm_kwargs = {
         'max_length': 512,
@@ -21,58 +23,8 @@ if __name__ == "__main__":
         'temperature': 1,
     }
 
-    result = predict_no_ui_long_connection(inputs="你好", 
+    result = predict_no_ui_long_connection( inputs="请问什么是质子？", 
                                             llm_kwargs=llm_kwargs,
-                                        history=[],
+                                            history=["你好", "我好！"],
                                             sys_prompt="")
     print('final result:', result)
-
-
-    result = predict_no_ui_long_connection(inputs="what is a hero?", 
-                                        llm_kwargs=llm_kwargs,
-                                        history=["hello world"],
-                                        sys_prompt="")
-    print('final result:', result)
-
-    result = predict_no_ui_long_connection(inputs="如何理解传奇?", 
-                                        llm_kwargs=llm_kwargs,
-                                        history=[],
-                                        sys_prompt="")
-    print('final result:', result)
-
-    # # print(result)
-    # from multiprocessing import Process, Pipe
-    # class GetGLMHandle(Process):
-    #     def __init__(self):
-    #         super().__init__(daemon=True)
-    #         pass
-    #     def run(self):
-    #         # 子进程执行
-    #         # 第一次运行，加载参数
-    #         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 + '/request_llm/jittorllms')
-    #             sys.path.append(root_dir_assume + '/request_llm/jittorllms')
-    #         validate_path() # validate path so you can run from base directory
-
-    #         jittorllms_model = None
-    #         import types
-    #         try:
-    #             if jittorllms_model is None:
-    #                 from models import get_model
-    #                 # availabel_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
-    #                 args_dict = {'model': 'chatrwkv'}
-    #                 print('self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))')
-    #                 jittorllms_model = get_model(types.SimpleNamespace(**args_dict))
-    #                 print('done get model')
-    #         except:
-    #             # self.child.send('[Local Message] Call jittorllms fail 不能正常加载jittorllms的参数。')
-    #             raise RuntimeError("不能正常加载jittorllms的参数！")
-            
-    # x = GetGLMHandle()
-    # x.start()
-
-
-    # input()

requirements.txt

@@ -1,4 +1,5 @@
 ./docs/gradio-3.32.2-py3-none-any.whl
+pydantic==1.10.11
 tiktoken>=0.3.3
 requests[socks]
 transformers
@@ -8,6 +9,7 @@ prompt_toolkit
 latex2mathml
 python-docx
 mdtex2html
+anthropic
 colorama
 Markdown
 pygments
@@ -15,11 +17,5 @@ pymupdf
 openai
 numpy
 arxiv
-pymupdf
-pyperclip
-scikit-learn
-psutil
-distro
-python-dotenv
 rich
-Levenshtein
+pypdf2==2.12.1

themes/common.js

@@ -0,0 +1,47 @@
+function ChatBotHeight() {
+    function update_height(){
+        var { panel_height_target, chatbot_height, chatbot } = get_elements();
+        if (panel_height_target!=chatbot_height)
+        {
+            var pixelString = panel_height_target.toString() + 'px';
+            chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString; 
+        }
+    }
+
+    function update_height_slow(){
+        var { panel_height_target, chatbot_height, chatbot } = get_elements();
+        if (panel_height_target!=chatbot_height)
+        {
+            new_panel_height = (panel_height_target - chatbot_height)*0.5 + chatbot_height;
+            if (Math.abs(new_panel_height - panel_height_target) < 10){
+                new_panel_height = panel_height_target;
+            }
+            // console.log(chatbot_height, panel_height_target, new_panel_height);
+            var pixelString = new_panel_height.toString() + 'px';
+            chatbot.style.maxHeight = pixelString; chatbot.style.height = pixelString; 
+        }
+    }
+
+    update_height();
+    setInterval(function() {
+        update_height_slow()
+    }, 50); // 每100毫秒执行一次
+}
+
+function get_elements() {
+    var chatbot = document.querySelector('#gpt-chatbot > div.wrap.svelte-18telvq');
+    if (!chatbot) {
+        chatbot = document.querySelector('#gpt-chatbot');
+    }
+    const panel1 = document.querySelector('#input-panel');
+    const panel2 = document.querySelector('#basic-panel');
+    const panel3 = document.querySelector('#plugin-panel');
+    const panel4 = document.querySelector('#interact-panel');
+    const panel5 = document.querySelector('#input-panel2');
+    const panel_active = document.querySelector('#state-panel');
+    var panel_height_target = (20-panel_active.offsetHeight) + panel1.offsetHeight + panel2.offsetHeight + panel3.offsetHeight + panel4.offsetHeight + panel5.offsetHeight + 21;
+    var panel_height_target = parseInt(panel_height_target);
+    var chatbot_height = chatbot.style.height;
+    var chatbot_height = parseInt(chatbot_height);
+    return { panel_height_target, chatbot_height, chatbot };
+}

themes/default.css

@@ -1,213 +1,28 @@
-import gradio as gr
-from toolbox import get_conf
-CODE_HIGHLIGHT, ADD_WAIFU, ADD_CHUANHU = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'ADD_CHUANHU')
-# gradio可用颜色列表
-# gr.themes.utils.colors.slate (石板色)
-# gr.themes.utils.colors.gray (灰色)
-# gr.themes.utils.colors.zinc (锌色)
-# gr.themes.utils.colors.neutral (中性色)
-# gr.themes.utils.colors.stone (石头色)
-# gr.themes.utils.colors.red (红色)
-# gr.themes.utils.colors.orange (橙色)
-# gr.themes.utils.colors.amber (琥珀色)
-# gr.themes.utils.colors.yellow (黄色)
-# gr.themes.utils.colors.lime (酸橙色)
-# gr.themes.utils.colors.green (绿色)
-# gr.themes.utils.colors.emerald (祖母绿)
-# gr.themes.utils.colors.teal (青蓝色)
-# gr.themes.utils.colors.cyan (青色)
-# gr.themes.utils.colors.sky (天蓝色)
-# gr.themes.utils.colors.blue (蓝色)
-# gr.themes.utils.colors.indigo (靛蓝色)
-# gr.themes.utils.colors.violet (紫罗兰色)
-# gr.themes.utils.colors.purple (紫色)
-# gr.themes.utils.colors.fuchsia (洋红色)
-# gr.themes.utils.colors.pink (粉红色)
-# gr.themes.utils.colors.rose (玫瑰色)
-
-
-def adjust_theme():
-
-    try:
-        set_theme = gr.themes.Soft(
-            primary_hue=gr.themes.Color(
-                c50="#EBFAF2",
-                c100="#CFF3E1",
-                c200="#A8EAC8",
-                c300="#77DEA9",
-                c400="#3FD086",
-                c500="#02C160",
-                c600="#06AE56",
-                c700="#05974E",
-                c800="#057F45",
-                c900="#04673D",
-                c950="#2E5541",
-                name="small_and_beautiful",
-            ),
-            secondary_hue=gr.themes.Color(
-                c50="#576b95",
-                c100="#576b95",
-                c200="#576b95",
-                c300="#576b95",
-                c400="#576b95",
-                c500="#576b95",
-                c600="#576b95",
-                c700="#576b95",
-                c800="#576b95",
-                c900="#576b95",
-                c950="#576b95",
-            ),
-            neutral_hue=gr.themes.Color(
-                name="gray",
-                c50="#f6f7f8",
-                # c100="#f3f4f6",
-                c100="#F2F2F2",
-                c200="#e5e7eb",
-                c300="#d1d5db",
-                c400="#B2B2B2",
-                c500="#808080",
-                c600="#636363",
-                c700="#515151",
-                c800="#393939",
-                # c900="#272727",
-                c900="#2B2B2B",
-                c950="#171717",
-            ),
-
-            radius_size=gr.themes.sizes.radius_sm,
-        ).set(
-            button_primary_background_fill="*primary_500",
-            button_primary_background_fill_dark="*primary_600",
-            button_primary_background_fill_hover="*primary_400",
-            button_primary_border_color="*primary_500",
-            button_primary_border_color_dark="*primary_600",
-            button_primary_text_color="wihte",
-            button_primary_text_color_dark="white",
-            button_secondary_background_fill="*neutral_100",
-            button_secondary_background_fill_hover="*neutral_50",
-            button_secondary_background_fill_dark="*neutral_900",
-            button_secondary_text_color="*neutral_800",
-            button_secondary_text_color_dark="white",
-            background_fill_primary="#F7F7F7",
-            background_fill_primary_dark="#1F1F1F",
-            block_title_text_color="*primary_500",
-            block_title_background_fill_dark="*primary_900",
-            block_label_background_fill_dark="*primary_900",
-            input_background_fill="#F6F6F6",
-            chatbot_code_background_color="*neutral_950",
-            chatbot_code_background_color_dark="*neutral_950",
-        )
-        js = ''
-        if ADD_CHUANHU:
-            with open("./docs/assets/custom.js", "r", encoding="utf-8") as f, \
-                    open("./docs/assets/external-scripts.js", "r", encoding="utf-8") as f1:
-                customJS = f.read()
-                externalScripts = f1.read()
-            js += f'<script>{customJS}</script><script async>{externalScripts}</script>'
-        # 添加一个萌萌的看板娘
-        if ADD_WAIFU:
-            js += """
-                <script src="file=docs/waifu_plugin/jquery.min.js"></script>
-                <script src="file=docs/waifu_plugin/jquery-ui.min.js"></script>
-                <script src="file=docs/waifu_plugin/autoload.js"></script>
-            """
-        gradio_original_template_fn = gr.routes.templates.TemplateResponse
-        def gradio_new_template_fn(*args, **kwargs):
-            res = gradio_original_template_fn(*args, **kwargs)
-            res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
-            res.init_headers()
-            return res
-        gr.routes.templates.TemplateResponse = gradio_new_template_fn   # override gradio template
-    except:
-        set_theme = None
-        print('gradio版本较旧, 不能自定义字体和颜色')
-    return set_theme
-
-
-with open("docs/assets/custom.css", "r", encoding="utf-8") as f:
-    customCSS = f.read()
-custom_css = customCSS
-advanced_css = """
-#debug_mes {
-    position: absolute;
-    bottom: 0;
-    left: 0;
-    width: 100%;
-    z-index: 1; /* 设置更高的 z-index 值 */
-    margin-bottom: 10px !important;
-}
-#chat_txt {
-    display: flex;
-    flex-direction: column-reverse;
-    overflow-y: auto !important;
-    z-index: 3;
-    flex-grow: 1; /* 自动填充剩余空间 */
-    position: absolute;
-    bottom: 0;
-    left: 0;
-    width: 100%;
-    margin-bottom: 35px !important;
-}
-#sm_btn {
-    display: flex;
-    flex-wrap: unset !important; 
-    gap: 5px !important;
-    width: var(--size-full);
-}
-textarea {
-    resize: none;
-    height: 100%; /* 填充父元素的高度 */
-}
-#main_chatbot {
-    height: 75vh !important;
-    max-height: 75vh !important;
-    /* overflow: auto !important; */
-    z-index: 2;
-}
-#prompt_result{
-    height: 60vh !important;
-    max-height: 60vh !important;
-}
-.wrap.svelte-18telvq.svelte-18telvq {
-    padding: var(--block-padding) !important;
-    height: 100% !important;
-    max-height: 95% !important;
-    overflow-y: auto !important;
-}
-.app.svelte-1mya07g.svelte-1mya07g {
-    max-width: 100%;
-    position: relative;
-    /* margin: auto; */
-    padding: var(--size-4);
-    width: 100%;
-    height: 100%;
-}
-.md-message table {
+.markdown-body table {
     margin: 1em 0;
     border-collapse: collapse;
     empty-cells: show;
 }
 
-.md-message th, .md-message td {
+.markdown-body th, .markdown-body td {
     border: 1.2px solid var(--border-color-primary);
     padding: 5px;
 }
 
-.md-message thead {
+.markdown-body thead {
     background-color: rgba(175,184,193,0.2);
 }
 
-.md-message thead th {
+.markdown-body thead th {
     padding: .5em .2em;
 }
 
-.md-message ol, .md-message ul {
+.markdown-body ol, .markdown-body ul {
     padding-inline-start: 2em !important;
 }
 
 /* chat box. */
 [class *= "message"] {
-    gap: 7px !important;
     border-radius: var(--radius-xl) !important;
     /* padding: var(--spacing-xl) !important; */
     /* font-size: var(--text-md) !important; */
@@ -217,40 +32,27 @@ textarea {
 }
 [data-testid = "bot"] {
     max-width: 95%;
-    letter-spacing: 0.5px;
-    font-weight: normal;
     /* width: auto !important; */
     border-bottom-left-radius: 0 !important;
 }
-
-.dark [data-testid = "bot"] {
-    max-width: 95%;
-    color: #ccd2db !important;
-    letter-spacing: 0.5px;
-    font-weight: normal;
-    /* width: auto !important; */
-    border-bottom-left-radius: 0 !important;
-}
-
 [data-testid = "user"] {
     max-width: 100%;
-    letter-spacing: 0.5px;
     /* width: auto !important; */
     border-bottom-right-radius: 0 !important;
 }
 
 /* linein code block. */
-.md-message code {
+.markdown-body code {
     display: inline;
     white-space: break-spaces;
     border-radius: 6px;
     margin: 0 2px 0 2px;
     padding: .2em .4em .1em .4em;
     background-color: rgba(13, 17, 23, 0.95);
-    color: #eff0f2;
+    color: #c9d1d9;
 }
 
-.dark .md-message code {
+.dark .markdown-body code {
     display: inline;
     white-space: break-spaces;
     border-radius: 6px;
@@ -260,7 +62,7 @@ textarea {
 }
 
 /* code block css */
-.md-message pre code {
+.markdown-body pre code {
     display: block;
     overflow: auto;
     white-space: pre;
@@ -270,7 +72,7 @@ textarea {
     margin: 1em 2em 1em 0.5em;
 }
 
-.dark .md-message pre code {
+.dark .markdown-body pre code {
     display: block;
     overflow: auto;
     white-space: pre;
@@ -280,10 +82,15 @@ textarea {
     margin: 1em 2em 1em 0.5em;
 }
 
-"""
+/* .mic-wrap.svelte-1thnwz {
 
-if CODE_HIGHLIGHT:
-    advanced_css += """
+} */
+.block.svelte-mppz8v > .mic-wrap.svelte-1thnwz{
+    justify-content: center;
+    display: flex;
+    padding: 0;
+
+}
 
 .codehilite .hll { background-color: #6e7681 }
 .codehilite .c { color: #8b949e; font-style: italic } /* Comment */
@@ -443,4 +250,3 @@ if CODE_HIGHLIGHT:
 .dark .codehilite .vm { color: #82AAFF } /* Name.Variable.Magic */
 .dark .codehilite .il { color: #F78C6C } /* Literal.Number.Integer.Long */
 
-"""

themes/default.py

@@ -0,0 +1,86 @@
+import gradio as gr
+from toolbox import get_conf
+CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'LAYOUT')
+
+def adjust_theme():
+
+    try:
+        color_er = gr.themes.utils.colors.fuchsia
+        set_theme = gr.themes.Default(
+            primary_hue=gr.themes.utils.colors.orange,
+            neutral_hue=gr.themes.utils.colors.gray,
+            font=["sans-serif", "Microsoft YaHei", "ui-sans-serif", "system-ui"],
+            font_mono=["ui-monospace", "Consolas", "monospace"])
+        set_theme.set(
+            # Colors
+            input_background_fill_dark="*neutral_800",
+            # Transition
+            button_transition="none",
+            # Shadows
+            button_shadow="*shadow_drop",
+            button_shadow_hover="*shadow_drop_lg",
+            button_shadow_active="*shadow_inset",
+            input_shadow="0 0 0 *shadow_spread transparent, *shadow_inset",
+            input_shadow_focus="0 0 0 *shadow_spread *secondary_50, *shadow_inset",
+            input_shadow_focus_dark="0 0 0 *shadow_spread *neutral_700, *shadow_inset",
+            checkbox_label_shadow="*shadow_drop",
+            block_shadow="*shadow_drop",
+            form_gap_width="1px",
+            # Button borders
+            input_border_width="1px",
+            input_background_fill="white",
+            # Gradients
+            stat_background_fill="linear-gradient(to right, *primary_400, *primary_200)",
+            stat_background_fill_dark="linear-gradient(to right, *primary_400, *primary_600)",
+            error_background_fill=f"linear-gradient(to right, {color_er.c100}, *background_fill_secondary)",
+            error_background_fill_dark="*background_fill_primary",
+            checkbox_label_background_fill="linear-gradient(to top, *neutral_50, white)",
+            checkbox_label_background_fill_dark="linear-gradient(to top, *neutral_900, *neutral_800)",
+            checkbox_label_background_fill_hover="linear-gradient(to top, *neutral_100, white)",
+            checkbox_label_background_fill_hover_dark="linear-gradient(to top, *neutral_900, *neutral_800)",
+            button_primary_background_fill="linear-gradient(to bottom right, *primary_100, *primary_300)",
+            button_primary_background_fill_dark="linear-gradient(to bottom right, *primary_500, *primary_600)",
+            button_primary_background_fill_hover="linear-gradient(to bottom right, *primary_100, *primary_200)",
+            button_primary_background_fill_hover_dark="linear-gradient(to bottom right, *primary_500, *primary_500)",
+            button_primary_border_color_dark="*primary_500",
+            button_secondary_background_fill="linear-gradient(to bottom right, *neutral_100, *neutral_200)",
+            button_secondary_background_fill_dark="linear-gradient(to bottom right, *neutral_600, *neutral_700)",
+            button_secondary_background_fill_hover="linear-gradient(to bottom right, *neutral_100, *neutral_100)",
+            button_secondary_background_fill_hover_dark="linear-gradient(to bottom right, *neutral_600, *neutral_600)",
+            button_cancel_background_fill=f"linear-gradient(to bottom right, {color_er.c100}, {color_er.c200})",
+            button_cancel_background_fill_dark=f"linear-gradient(to bottom right, {color_er.c600}, {color_er.c700})",
+            button_cancel_background_fill_hover=f"linear-gradient(to bottom right, {color_er.c100}, {color_er.c100})",
+            button_cancel_background_fill_hover_dark=f"linear-gradient(to bottom right, {color_er.c600}, {color_er.c600})",
+            button_cancel_border_color=color_er.c200,
+            button_cancel_border_color_dark=color_er.c600,
+            button_cancel_text_color=color_er.c600,
+            button_cancel_text_color_dark="white",
+        )
+
+        if LAYOUT=="TOP-DOWN": 
+            js = ""
+        else:
+            with open('themes/common.js', 'r', encoding='utf8') as f: 
+                js = f"<script>{f.read()}</script>"
+            
+        # 添加一个萌萌的看板娘
+        if ADD_WAIFU:
+            js += """
+                <script src="file=docs/waifu_plugin/jquery.min.js"></script>
+                <script src="file=docs/waifu_plugin/jquery-ui.min.js"></script>
+                <script src="file=docs/waifu_plugin/autoload.js"></script>
+            """
+        gradio_original_template_fn = gr.routes.templates.TemplateResponse
+        def gradio_new_template_fn(*args, **kwargs):
+            res = gradio_original_template_fn(*args, **kwargs)
+            res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
+            res.init_headers()
+            return res
+        gr.routes.templates.TemplateResponse = gradio_new_template_fn   # override gradio template
+    except:
+        set_theme = None
+        print('gradio版本较旧, 不能自定义字体和颜色')
+    return set_theme
+
+with open("themes/default.css", "r", encoding="utf-8") as f:
+    advanced_css = f.read()

themes/green.css

@@ -167,6 +167,7 @@ footer {
     font-size: 85%;
     opacity: 0.60;
 }
+/* user_info */
 
 #float_display {
     position: absolute;
@@ -241,16 +242,15 @@ textarea.svelte-1pie7s6 {
     transition: height 0.3s ease;
 }
 
-.wrap.svelte-18telvq.svelte-18telvq {
+/* .wrap.svelte-18telvq.svelte-18telvq {
     padding: var(--block-padding) !important;
     height: 100% !important;
     max-height: 95% !important;
     overflow-y: auto !important;
-}
+}*/
 .app.svelte-1mya07g.svelte-1mya07g {
     max-width: 100%;
     position: relative;
-    /* margin: auto; */
     padding: var(--size-4);
     width: 100%;
     height: 100%;

themes/green.py

@@ -0,0 +1,104 @@
+import gradio as gr
+from toolbox import get_conf
+CODE_HIGHLIGHT, ADD_WAIFU, LAYOUT = get_conf('CODE_HIGHLIGHT', 'ADD_WAIFU', 'LAYOUT')
+
+def adjust_theme():
+    try:
+        set_theme = gr.themes.Soft(
+            primary_hue=gr.themes.Color(
+                c50="#EBFAF2",
+                c100="#CFF3E1",
+                c200="#A8EAC8",
+                c300="#77DEA9",
+                c400="#3FD086",
+                c500="#02C160",
+                c600="#06AE56",
+                c700="#05974E",
+                c800="#057F45",
+                c900="#04673D",
+                c950="#2E5541",
+                name="small_and_beautiful",
+            ),
+            secondary_hue=gr.themes.Color(
+                c50="#576b95",
+                c100="#576b95",
+                c200="#576b95",
+                c300="#576b95",
+                c400="#576b95",
+                c500="#576b95",
+                c600="#576b95",
+                c700="#576b95",
+                c800="#576b95",
+                c900="#576b95",
+                c950="#576b95",
+            ),
+            neutral_hue=gr.themes.Color(
+                name="gray",
+                c50="#f6f7f8",
+                # c100="#f3f4f6",
+                c100="#F2F2F2",
+                c200="#e5e7eb",
+                c300="#d1d5db",
+                c400="#B2B2B2",
+                c500="#808080",
+                c600="#636363",
+                c700="#515151",
+                c800="#393939",
+                # c900="#272727",
+                c900="#2B2B2B",
+                c950="#171717",
+            ),
+
+            radius_size=gr.themes.sizes.radius_sm,
+        ).set(
+            button_primary_background_fill="*primary_500",
+            button_primary_background_fill_dark="*primary_600",
+            button_primary_background_fill_hover="*primary_400",
+            button_primary_border_color="*primary_500",
+            button_primary_border_color_dark="*primary_600",
+            button_primary_text_color="wihte",
+            button_primary_text_color_dark="white",
+            button_secondary_background_fill="*neutral_100",
+            button_secondary_background_fill_hover="*neutral_50",
+            button_secondary_background_fill_dark="*neutral_900",
+            button_secondary_text_color="*neutral_800",
+            button_secondary_text_color_dark="white",
+            background_fill_primary="#F7F7F7",
+            background_fill_primary_dark="#1F1F1F",
+            block_title_text_color="*primary_500",
+            block_title_background_fill_dark="*primary_900",
+            block_label_background_fill_dark="*primary_900",
+            input_background_fill="#F6F6F6",
+            chatbot_code_background_color="*neutral_950",
+            chatbot_code_background_color_dark="*neutral_950",
+        )
+
+        js = ''
+        if LAYOUT=="TOP-DOWN":
+            js = ""
+        else:
+            with open('themes/common.js', 'r', encoding='utf8') as f:
+                js = f"<script>{f.read()}</script>"
+
+        # 添加一个萌萌的看板娘
+        if ADD_WAIFU:
+            js += """
+                <script src="file=docs/waifu_plugin/jquery.min.js"></script>
+                <script src="file=docs/waifu_plugin/jquery-ui.min.js"></script>
+                <script src="file=docs/waifu_plugin/autoload.js"></script>
+            """
+        gradio_original_template_fn = gr.routes.templates.TemplateResponse
+        def gradio_new_template_fn(*args, **kwargs):
+            res = gradio_original_template_fn(*args, **kwargs)
+            res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
+            res.init_headers()
+            return res
+        gr.routes.templates.TemplateResponse = gradio_new_template_fn   # override gradio template
+    except:
+        set_theme = None
+        print('gradio版本较旧, 不能自定义字体和颜色')
+    return set_theme
+
+
+with open("themes/green.css", "r", encoding="utf-8") as f:
+    advanced_css = f.read()

themes/theme.py

@@ -0,0 +1,12 @@
+import gradio as gr
+from toolbox import get_conf
+THEME, = get_conf('THEME')
+
+if THEME == 'Chuanhu-Small-and-Beautiful':
+    from .green import adjust_theme, advanced_css
+    theme_declaration = "<h2 align=\"center\"  class=\"small\">[Chuanhu-Small-and-Beautiful主题]</h2>"
+else:
+    from .default import adjust_theme, advanced_css
+    theme_declaration = ""
+
+

toolbox.py

@@ -1,18 +1,12 @@
-import html
 import markdown
 import importlib
+import time
 import inspect
-import gradio as gr
-import func_box
+import re
+import os
+import gradio
 from latex2mathml.converter import convert as tex2mathml
 from functools import wraps, lru_cache
-import shutil
-import os
-import time
-import glob
-import sys
-import threading
-############################### 插件输入输出接驳区 #######################################
 pj = os.path.join
 
 """
@@ -47,62 +41,57 @@ def ArgsGeneralWrapper(f):
     """
     装饰器函数，用于重组输入参数，改变输入参数的顺序与结构。
     """
-    def decorated(cookies, max_length, llm_model, txt, top_p, temperature,
-                  chatbot, history, system_prompt, models, plugin_advanced_arg, ipaddr: gr.Request, *args):
-        """"""
+    def decorated(request: gradio.Request, cookies, max_length, llm_model, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg, *args):
+        txt_passon = txt
+        if txt == "" and txt2 != "": txt_passon = txt2
         # 引入一个有cookie的chatbot
-        start_time = time.time()
-        encrypt, private = get_conf('switch_model')[0]['key']
-        private_key, = get_conf('private_key')
         cookies.update({
             'top_p':top_p,
             'temperature':temperature,
         })
-
         llm_kwargs = {
             'api_key': cookies['api_key'],
             'llm_model': llm_model,
             'top_p':top_p,
             'max_length': max_length,
             'temperature':temperature,
-            'ipaddr': ipaddr.client.host,
-            'start_time': start_time
+            'client_ip': request.client.host,
         }
         plugin_kwargs = {
             "advanced_arg": plugin_advanced_arg,
-            "parameters_def": ''
         }
-        if len(args) > 1:
-            plugin_kwargs.update({'parameters_def': args[1]})
-        transparent_address_private = f'<p style="display:none;">\n{private_key}\n{ipaddr.client.host}\n</p>'
-        transparent_address = f'<p style="display:none;">\n{ipaddr.client.host}\n</p>'
-        if private in models:
-            if chatbot == []:
-                chatbot.append([None, f'隐私模式, 你的对话记录无法被他人检索 {transparent_address_private}'])
-            else:
-                chatbot[0] = [None, f'隐私模式, 你的对话记录无法被他人检索 {transparent_address_private}']
-        else:
-            if chatbot == []:
-                chatbot.append([None, f'正常对话模式, 你接来下的对话将会被记录并且可以被所有人检索，你可以到Settings中选择隐私模式 {transparent_address}'])
-            else:
-                chatbot[0] = [None, f'正常对话模式, 你接来下的对话将会被记录并且可以被所有人检索，你可以到Settings中选择隐私模式 {transparent_address}']
         chatbot_with_cookie = ChatBotWithCookies(cookies)
         chatbot_with_cookie.write_list(chatbot)
-        txt_passon = txt
-        if encrypt in models: txt_passon = func_box.encryption_str(txt)
+        if cookies.get('lock_plugin', None) is None:
+            # 正常状态
             yield from f(txt_passon, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, system_prompt, *args)
+        else:
+            # 处理个别特殊插件的锁定状态
+            module, fn_name = cookies['lock_plugin'].split('->')
+            f_hot_reload = getattr(importlib.import_module(module, fn_name), fn_name)
+            yield from f_hot_reload(txt_passon, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, system_prompt, *args)
     return decorated
 
 
-
-def update_ui(chatbot, history, msg='正常', *args):  # 刷新界面
+def update_ui(chatbot, history, msg='正常', **kwargs):  # 刷新界面
     """
     刷新用户界面
     """
-    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
-    threading.Thread(target=func_box.thread_write_chat, args=(chatbot, history)).start()
-    # func_box.thread_write_chat(chatbot, history)
+    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。"
+    cookies = chatbot.get_cookies()
+
+    # 解决插件锁定时的界面显示问题
+    if cookies.get('lock_plugin', None):
+        label = cookies.get('llm_model', "") + " | " + "正在锁定插件" + cookies.get('lock_plugin', None)
+        chatbot_gr = gradio.update(value=chatbot, label=label)
+        if cookies.get('label', "") != label: cookies['label'] = label   # 记住当前的label
+    elif cookies.get('label', None):
+        chatbot_gr = gradio.update(value=chatbot, label=cookies.get('llm_model', ""))
+        cookies['label'] = None    # 清空label
+    else:
+        chatbot_gr = chatbot
+
+    yield cookies, chatbot_gr, history, msg
 
 def update_ui_lastest_msg(lastmsg, chatbot, history, delay=1):  # 刷新界面
     """
@@ -159,14 +148,9 @@ def HotReload(f):
     def decorated(*args, **kwargs):
         fn_name = f.__name__
         f_hot_reload = getattr(importlib.reload(inspect.getmodule(f)), fn_name)
-        try:
-            yield from f_hot_reload(*args, **kwargs)
-        except TypeError:
-            args = tuple(args[element] for element in range(len(args)) if element != 6)
         yield from f_hot_reload(*args, **kwargs)
     return decorated
 
-####################################### 其他小工具 #####################################
 
 """
 ========================================================================
@@ -230,7 +214,8 @@ def write_results_to_file(history, file_name=None):
                 # remove everything that cannot be handled by utf8
                 f.write(content.encode('utf-8', 'ignore').decode())
             f.write('\n\n')
-    res = '以上材料已经被写入' + f'./gpt_log/{file_name}'
+    res = '以上材料已经被写入:\t' + os.path.abspath(f'./gpt_log/{file_name}')
+    print(res)
     return res
 
 
@@ -255,51 +240,37 @@ def report_execption(chatbot, history, a, b):
     history.append(b)
 
 
-import re
-def text_divide_paragraph(input_str):
-    if input_str:
-        code_blocks = re.findall(r'```[\s\S]*?```', input_str)
+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
     
-        for i, block in enumerate(code_blocks):
-            input_str = input_str.replace(block, f'{{{{CODE_BLOCK_{i}}}}}')
-
-        if code_blocks:
-            sections = re.split(r'({{{{\w+}}}})', input_str)
-            for idx, section in enumerate(sections):
-                if 'CODE_BLOCK' in section or section.startswith('    '):
-                    continue
-                sections[idx] = re.sub(r'(?!```)(?<!\n)\n(?!(\n|^)( {0,3}[\*\+\-]|[0-9]+\.))', '\n\n', section)
-            input_str = ''.join(sections)
-
-            for i, block in enumerate(code_blocks):
-                input_str = input_str.replace(f'{{{{CODE_BLOCK_{i}}}}}', block.replace('\n', '\n'))
+    if '```' in text:
+        # careful input
+        return pre + text + suf
     else:
-            lines = input_str.split('\n')
-            for idx, line in enumerate(lines[:-1]):
-                if not line.strip():
-                    continue
-                if not (lines[idx + 1].startswith('    ') or lines[idx + 1].startswith('\t')):
-                    lines[idx] += '\n'  # 将一个换行符替换为两个换行符
-            input_str = '\n'.join(lines)
-
-    return input_str
-
+        # wtf input
+        lines = text.split("\n")
+        for i, line in enumerate(lines):
+            lines[i] = lines[i].replace(" ", "&nbsp;")
+        text = "</br>".join(lines)
+        return pre + text + suf
 
 @lru_cache(maxsize=128) # 使用 lru缓存 加快转换速度
 def markdown_convertion(txt):
     """
     将Markdown格式的文本转换为HTML格式。如果包含数学公式，则先将公式转换为HTML格式。
     """
-    pre = '<div class="md-message">'
+    pre = '<div class="markdown-body">'
     suf = '</div>'
-    raw_pre = '<div class="raw-message hideM">'
-    raw_suf = '</div>'
     if txt.startswith(pre) and txt.endswith(suf):
         # print('警告，输入了已经经过转化的字符串，二次转化可能出问题')
         return txt # 已经被转化过，不需要再次转化
-    if txt.startswith(raw_pre) and txt.endswith(raw_suf):
-        return txt  # 已经被转化过，不需要再次转化
-    raw_hide = raw_pre + txt + raw_suf
+    
     markdown_extension_configs = {
         'mdx_math': {
             'enable_dollar_delimiter': True,
@@ -308,6 +279,13 @@ def markdown_convertion(txt):
     }
     find_equation_pattern = r'<script type="math/tex(?:.*?)>(.*?)</script>'
 
+    def tex2mathml_catch_exception(content, *args, **kwargs):
+        try:
+            content = tex2mathml(content, *args, **kwargs)
+        except:
+            content = content
+        return content
+
     def replace_math_no_render(match):
         content = match.group(1)
         if 'mode=display' in match.group(0):
@@ -323,17 +301,16 @@ def markdown_convertion(txt):
                 content = content.replace('\\begin{aligned}', '\\begin{array}')
                 content = content.replace('\\end{aligned}', '\\end{array}')
                 content = content.replace('&', ' ')
-            content = tex2mathml(content, display="block")
+            content = tex2mathml_catch_exception(content, display="block")
             return content
         else:
-            return tex2mathml(content)
+            return tex2mathml_catch_exception(content)
 
     def markdown_bug_hunt(content):
         """
         解决一个mdx_math的bug（单$包裹begin命令时多余<script>）
         """
-        content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">',
-                                  '<script type="math/tex; mode=display">')
+        content = content.replace('<script type="math/tex">\n<script type="math/tex; mode=display">', '<script type="math/tex; mode=display">')
         content = content.replace('</script>\n</script>', '</script>')
         return content
 
@@ -341,29 +318,23 @@ def markdown_convertion(txt):
         if '```' not in txt: 
             return True
         else:
-            if '```reference' in txt:
-                return True  # newbing
-            else:
-                return False
+            if '```reference' in txt: return True    # newbing
+            else: return False
 
-    if ('$$' in txt) and no_code(txt):  # 有$标识的公式符号，且没有代码段```的标识
+    if ('$' in txt) and no_code(txt):  # 有$标识的公式符号，且没有代码段```的标识
         # convert everything to html format
         split = markdown.markdown(text='---')
-        txt = re.sub(r'\$\$((?:.|\n)*?)\$\$', lambda match: '$$' + re.sub(r'\n+', '</br>', match.group(1)) + '$$', txt)
         convert_stage_1 = markdown.markdown(text=txt, extensions=['mdx_math', 'fenced_code', 'tables', 'sane_lists'], extension_configs=markdown_extension_configs)
         convert_stage_1 = markdown_bug_hunt(convert_stage_1)
         # re.DOTALL: Make the '.' special character match any character at all, including a newline; without this flag, '.' will match anything except a newline. Corresponds to the inline flag (?s).
         # 1. convert to easy-to-copy tex (do not render math)
         convert_stage_2_1, n = re.subn(find_equation_pattern, replace_math_no_render, convert_stage_1, flags=re.DOTALL)
         # 2. convert to rendered equation
-        convert_stage_1_resp = convert_stage_1.replace('</br>', '')
-        convert_stage_2_2, n = re.subn(find_equation_pattern, replace_math_render, convert_stage_1_resp, flags=re.DOTALL)
+        convert_stage_2_2, n = re.subn(find_equation_pattern, replace_math_render, convert_stage_1, flags=re.DOTALL)
         # cat them together
-        context = pre + convert_stage_2_1 + f'{split}' + convert_stage_2_2 + suf
-        return raw_hide + context   # 破坏html 结构，并显示源码
+        return pre + convert_stage_2_1 + f'{split}' + convert_stage_2_2 + suf
     else:
-        context = pre + markdown.markdown(txt, extensions=['fenced_code', 'codehilite', 'tables', 'sane_lists']) + suf
-        return raw_hide + context  # 破坏html 结构，并显示源码
+        return pre + markdown.markdown(txt, extensions=['fenced_code', 'codehilite', 'tables', 'sane_lists']) + suf
 
 
 def close_up_code_segment_during_stream(gpt_reply):
@@ -377,9 +348,9 @@ def close_up_code_segment_during_stream(gpt_reply):
         str: 返回一个新的字符串，将输出代码片段的“后面的```”补上。
 
     """
-    if '```' not in str(gpt_reply):
+    if '```' not in gpt_reply:
         return gpt_reply
-    if str(gpt_reply).endswith('```'):
+    if gpt_reply.endswith('```'):
         return gpt_reply
 
     # 排除了以上两个情况，我们
@@ -405,8 +376,7 @@ def format_io(self, y):
     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 i_ask is None else markdown_convertion(i_ask),
+        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)
     )
     return y
@@ -497,58 +467,52 @@ def promote_file_to_downloadzone(file, rename_file=None, chatbot=None):
     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)
+    # 如果已经存在，先删除
     if os.path.exists(new_path) and not os.path.samefile(new_path, file): os.remove(new_path)
+    # 把文件复制过去
     if not os.path.exists(new_path): shutil.copyfile(file, new_path)
+    # 将文件添加到chatbot cookie中，避免多用户干扰
     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 get_user_upload(chatbot, ipaddr: gr.Request):
-    """
-    获取用户上传过的文件
-    """
-    private_upload = './private_upload'
-    user_history = os.path.join(private_upload, ipaddr.client.host)
-    history = """| 编号 | 目录 | 目录内文件 |\n| --- | --- | --- |\n"""
-    count_num = 1
-    for root, d, file in os.walk(user_history):
-        file_link = "<br>".join([f'{func_box.html_view_blank(f"{root}/{i}")}' for i in file])
-        history += f'| {count_num} | {root} | {file_link} |\n'
-        count_num += 1
-    chatbot.append(['Load Submission History....',
-                    f'[Local Message] 请自行复制以下目录 or 目录+文件, 填入输入框以供函数区高亮按钮使用\n\n'
-                    f'{func_box.html_tag_color("提交前记得请检查头尾空格哦～")}\n\n'
-                    f'{history}'
-                    ])
-    return chatbot
-
-
-def on_file_uploaded(files, chatbot, txt, ipaddr: gr.Request):
+def on_file_uploaded(files, chatbot, txt, txt2, checkboxes):
     """
     当文件被上传时的回调函数
     """
     if len(files) == 0:
         return chatbot, txt
-    private_upload = './private_upload'
-    #     shutil.rmtree('./private_upload/')  不需要删除文件
-    time_tag_path = os.path.join(private_upload, ipaddr.client.host, time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()))
-    os.makedirs(f'{time_tag_path}', exist_ok=True)
+    import shutil
+    import os
+    import time
+    import glob
+    from toolbox import extract_archive
+    try:
+        shutil.rmtree('./private_upload/')
+    except:
+        pass
+    time_tag = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
+    os.makedirs(f'private_upload/{time_tag}', exist_ok=True)
     err_msg = ''
     for file in files:
         file_origin_name = os.path.basename(file.orig_name)
-        shutil.copy(file.name, f'{time_tag_path}/{file_origin_name}')
-        err_msg += extract_archive(f'{time_tag_path}/{file_origin_name}',
-                                   dest_dir=f'{time_tag_path}/{file_origin_name}.extract')
-    moved_files = [fp for fp in glob.glob(f'{time_tag_path}/**/*', recursive=True)]
-    txt = f'{time_tag_path}'
+        shutil.copy(file.name, f'private_upload/{time_tag}/{file_origin_name}')
+        err_msg += extract_archive(f'private_upload/{time_tag}/{file_origin_name}',
+                                   dest_dir=f'private_upload/{time_tag}/{file_origin_name}.extract')
+    moved_files = [fp for fp in glob.glob('private_upload/**/*', recursive=True)]
+    if "底部输入区" in checkboxes:
+        txt = ""
+        txt2 = f'private_upload/{time_tag}'
+    else:
+        txt = f'private_upload/{time_tag}'
+        txt2 = ""
     moved_files_str = '\t\n\n'.join(moved_files)
-    chatbot.append([None,
+    chatbot.append(['我上传了文件，请查收',
                     f'[Local Message] 收到以下文件: \n\n{moved_files_str}' +
                     f'\n\n调用路径参数已自动修正到: \n\n{txt}' +
-                    f'\n\n现在您点击任意“高亮”标识的函数插件时，以上文件将被作为输入参数'+err_msg])
-    return chatbot, txt
+                    f'\n\n现在您点击任意“红颜色”标识的函数插件时，以上文件将被作为输入参数'+err_msg])
+    return chatbot, txt, txt2
 
 
 def on_report_generated(cookies, files, chatbot):
@@ -566,23 +530,28 @@ def on_report_generated(cookies, files, chatbot):
     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 load_chat_cookies():
+    API_KEY, LLM_MODEL, AZURE_API_KEY = get_conf('API_KEY', 'LLM_MODEL', 'AZURE_API_KEY')
+    if is_any_api_key(AZURE_API_KEY):
+        if is_any_api_key(API_KEY): API_KEY = API_KEY + ',' + AZURE_API_KEY
+        else: API_KEY = AZURE_API_KEY
+    return {'api_key': API_KEY, 'llm_model': LLM_MODEL}
+
 def is_openai_api_key(key):
+    CUSTOM_API_KEY_PATTERN, = get_conf('CUSTOM_API_KEY_PATTERN')
+    if len(CUSTOM_API_KEY_PATTERN) != 0:
+        API_MATCH_ORIGINAL = re.match(CUSTOM_API_KEY_PATTERN, key)
+    else:
         API_MATCH_ORIGINAL = re.match(r"sk-[a-zA-Z0-9]{48}$", key)
+    return bool(API_MATCH_ORIGINAL)
+
+def is_azure_api_key(key):
     API_MATCH_AZURE = re.match(r"[a-zA-Z0-9]{32}$", key)
-    return bool(API_MATCH_ORIGINAL) or bool(API_MATCH_AZURE)
+    return bool(API_MATCH_AZURE)
 
 def is_api2d_key(key):
-    if key.startswith('fk') and len(key) == 41:
-        return True
-    else:
-        return False
-
-def is_proxy_key(key):
-    if key.startswith('proxy-') and len(key) == 38:
-        return True
-    else:
-        return False
-
+    API_MATCH_API2D = re.match(r"fk[a-zA-Z0-9]{6}-[a-zA-Z0-9]{32}$", key)
+    return bool(API_MATCH_API2D)
 
 def is_any_api_key(key):
     if ',' in key:
@@ -591,10 +560,10 @@ def is_any_api_key(key):
             if is_any_api_key(k): return True
         return False
     else:
-        return is_openai_api_key(key) or is_api2d_key(key) or is_proxy_key(key)
+        return is_openai_api_key(key) or is_api2d_key(key) or is_azure_api_key(key)
 
 def what_keys(keys):
-    avail_key_list = {'OpenAI Key':0, "API2D Key":0}
+    avail_key_list = {'OpenAI Key':0, "Azure Key":0, "API2D Key":0}
     key_list = keys.split(',')
 
     for k in key_list:
@@ -606,13 +575,10 @@ def what_keys(keys):
             avail_key_list['API2D Key'] += 1
 
     for k in key_list:
-        if is_proxy_key(k):
-            avail_key_list['Proxy Key'] += 1
+        if is_azure_api_key(k): 
+            avail_key_list['Azure Key'] += 1
 
-    return f"检测到： \n" \
-           f"OpenAI Key {avail_key_list['OpenAI Key']} 个\n" \
-           f"API2D Key {avail_key_list['API2D Key']} 个\n" \
-           f"Proxy Key {avail_key_list['API2D Key']} 个\n"
+    return f"检测到： OpenAI Key {avail_key_list['OpenAI Key']} 个, Azure Key {avail_key_list['Azure Key']} 个, API2D Key {avail_key_list['API2D Key']} 个"
 
 def select_api_key(keys, llm_model):
     import random
@@ -627,12 +593,12 @@ def select_api_key(keys, llm_model):
         for k in key_list:
             if is_api2d_key(k): avail_key_list.append(k)
 
-    if llm_model.startswith('proxy-'):
+    if llm_model.startswith('azure-'):
         for k in key_list:
-            if is_proxy_key(k): avail_key_list.append(k.replace('proxy-', ''))
+            if is_azure_api_key(k): avail_key_list.append(k)
 
     if len(avail_key_list) == 0:
-        raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源。")
+        raise RuntimeError(f"您提供的api-key不满足要求，不包含任何可用于{llm_model}的api-key。您可能选择了错误的模型或请求源（右下角更换模型菜单中可切换openai,azure,claude,api2d等请求源）。")
 
     api_key = random.choice(avail_key_list) # 随机负载均衡
     return api_key
@@ -701,12 +667,6 @@ def read_single_conf_with_lru_cache(arg):
     except:
         try:
             # 优先级2. 获取config_private中的配置
-            # 获取当前文件所在目录的路径
-            current_dir = os.path.dirname(os.path.abspath(__file__))
-            # 获取上一层目录的路径
-            parent_dir = os.path.dirname(current_dir)
-            # 将上一层目录添加到Python的搜索路径中
-            sys.path.append(parent_dir)
             r = getattr(importlib.import_module('config_private'), arg)
         except:
             # 优先级3. 获取config中的配置
@@ -714,13 +674,14 @@ def read_single_conf_with_lru_cache(arg):
 
     # 在读取API_KEY时，检查一下是不是忘了改config
     if arg == 'API_KEY':
-        print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和API2D的api-key。也支持同时填写多个api-key，如API_KEY=\"openai-key1,openai-key2,api2d-key3\"")
+        print亮蓝(f"[API_KEY] 本项目现已支持OpenAI和Azure的api-key。也支持同时填写多个api-key，如API_KEY=\"openai-key1,openai-key2,azure-key3\"")
         print亮蓝(f"[API_KEY] 您既可以在config.py中修改api-key(s)，也可以在问题输入区输入临时的api-key(s)，然后回车键提交后即可生效。")
         if is_any_api_key(r):
             print亮绿(f"[API_KEY] 您的 API_KEY 是: {r[:15]}*** API_KEY 导入成功")
         else:
-            print亮红( "[API_KEY] 正确的 API_KEY 是'sk'开头的51位密钥（OpenAI），或者 'fk'开头的41位密钥，请在config文件中修改API密钥之后再运行。")
+            print亮红( "[API_KEY] 您的 API_KEY 不满足任何一种已知的密钥格式，请在config文件中修改API密钥之后再运行。")
     if arg == 'proxies':
+        if not read_single_conf_with_lru_cache('USE_PROXY'): r = None   # 检查USE_PROXY，防止proxies单独起作用
         if r is None:
             print亮红('[PROXY] 网络代理状态：未配置。无代理状态下很可能无法访问OpenAI家族的模型。建议：检查USE_PROXY选项是否修改。')
         else:
@@ -729,6 +690,7 @@ def read_single_conf_with_lru_cache(arg):
     return r
 
 
+@lru_cache(maxsize=128)
 def get_conf(*args):
     # 建议您复制一个config_private.py放自己的秘密, 如API和代理网址, 避免不小心传github被别人看到
     res = []
@@ -761,7 +723,6 @@ class DummyWith():
     def __exit__(self, exc_type, exc_value, traceback):
         return
 
-
 def run_gradio_in_subpath(demo, auth, port, custom_path):
     """
     把gradio的运行地址更改到指定的二次路径上
@@ -928,3 +889,16 @@ def objload(file='objdump.tmp'):
         return
     with open(file, 'rb') as f:
         return pickle.load(f)
+    
+def Singleton(cls):
+    """
+    一个单实例装饰器
+    """
+    _instance = {}
+ 
+    def _singleton(*args, **kargs):
+        if cls not in _instance:
+            _instance[cls] = cls(*args, **kargs)
+        return _instance[cls]
+ 
+    return _singleton

version

@@ -1,5 +1,5 @@
 {
-  "version": 3.42,
+  "version": 3.47,
   "show_feature": true,
-  "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"
+  "new_feature": "优化一键升级 <-> 提高arxiv翻译速度和成功率 <-> 支持自定义APIKEY格式 <-> 临时修复theme的文件丢失问题 <-> 新增实时语音对话插件（自动断句，脱手对话） <-> 支持加载自定义的ChatGLM2微调模型 <-> 动态ChatBot窗口高度 <-> 修复Azure接口的BUG <-> 完善多语言模块 <-> 完善本地Latex矫错和翻译功能 <-> 增加gpt-3.5-16k的支持"
 }