# ChatGPT Academic Wrapper
[gpt_academic](https://github.com/binary-husky/gpt_academic) 的一个分支，提供了一个 Python 库和 Windows 安装程序，以方便安装。
你可以到 [GitHub Release](https://github.com/haiiliin/chatgpt-academic/releases) 页面下载 ChatGPT Academic 的离线安装包，解压后安装即可使用。
或者也可以使用以下命令安装 ChatGPT Academic：
```sh
pip install chatgpt-academic
```
配置项目请使用 [环境变量](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明#4-环境变量格式说明)。
> **Caution**
>
> 2023.11.12: 某些依赖包尚不兼容python 3.12，推荐python 3.11。
>
> 2023.11.7: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目开源免费，近期发现有人蔑视开源协议并利用本项目违规圈钱，请提高警惕，谨防上当受骗。
<br>
<div align=center>
<h1 aligh="center">
<img src="docs/logo.png" width="40"> GPT 学术优化 (GPT Academic)
</h1>
[![Github][Github-image]][Github-url]
[![License][License-image]][License-url]
[![Releases][Releases-image]][Releases-url]
[![Installation][Installation-image]][Installation-url]
[![Wiki][Wiki-image]][Wiki-url]
[![PR][PRs-image]][PRs-url]
[License-image]: https://img.shields.io/badge/LICENSE-GPL3.0-orange?&style=flat-square
[Github-image]: https://img.shields.io/badge/github-12100E.svg?&style=flat-square
[Releases-image]: https://img.shields.io/badge/Releases-v3.6.0-blue?style=flat-square
[Installation-image]: https://img.shields.io/badge/Installation-v3.6.1-blue?style=flat-square
[Wiki-image]: https://img.shields.io/badge/wiki-项目文档-black?style=flat-square
[PRs-image]: https://img.shields.io/badge/PRs-welcome-pink?style=flat-square
[License-url]: https://github.com/binary-husky/gpt_academic/blob/master/LICENSE
[Github-url]: https://github.com/binary-husky/gpt_academic
[Releases-url]: https://github.com/binary-husky/gpt_academic/releases
[Installation-url]: https://github.com/binary-husky/gpt_academic#installation
[Wiki-url]: https://github.com/binary-husky/gpt_academic/wiki
[PRs-url]: https://github.com/binary-husky/gpt_academic/pulls
</div>
<br>
**如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或插件，欢迎发pull requests！**
If you like this project, please give it a Star. Read this in [English](docs/README.English.md) | [日本語](docs/README.Japanese.md) | [한국어](docs/README.Korean.md) | [Русский](docs/README.Russian.md) | [Français](docs/README.French.md). All translations have been provided by the project itself. To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).
<br>
> 1.请注意只有 **高亮** 标识的插件（按钮）才支持读取文件，部分插件位于插件区的**下拉菜单**中。另外我们以**最高优先级**欢迎和处理任何新插件的PR。
>
> 2.本项目中每个文件的功能都在[自译解报告](https://github.com/binary-husky/gpt_academic/wiki/GPT‐Academic项目自译解报告)`self_analysis.md`详细说明。随着版本的迭代，您也可以随时自行点击相关函数插件，调用GPT重新生成项目的自我解析报告。常见问题请查阅wiki。
> [](#installation) [](https://github.com/binary-husky/gpt_academic/releases) [](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明) []([https://github.com/binary-husky/gpt_academic/wiki/项目配置说明](https://github.com/binary-husky/gpt_academic/wiki))
>
> 3.本项目兼容并鼓励尝试国产大语言模型ChatGLM等。支持多个api-key共存，可在配置文件中填写如`API_KEY="openai-key1,openai-key2,azure-key3,api2d-key4"`。需要临时更换`API_KEY`时，在输入区输入临时的`API_KEY`然后回车键提交后即可生效。
<br><br>
<div align="center">
功能（⭐= 近期新增功能） | 描述
--- | ---
⭐[接入新模型](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B) | 百度[千帆](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu)与文心一言, 通义千问[Qwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)，上海AI-Lab[书生](https://github.com/InternLM/InternLM)，讯飞[星火](https://xinghuo.xfyun.cn/)，[LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)，[智谱API](https://open.bigmodel.cn/)，DALLE3, [DeepseekCoder](https://coder.deepseek.com/)
润色、翻译、代码解释 | 一键润色、翻译、查找论文语法错误、解释代码
[自定义快捷键](https://www.bilibili.com/video/BV14s4y1E7jN) | 支持自定义快捷键
模块化设计 | 支持自定义强大的[插件](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)，插件支持[热更新](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)
[程序剖析](https://www.bilibili.com/video/BV1cj411A7VW) | [插件] 一键剖析Python/C/C++/Java/Lua/...项目树 或 [自我剖析](https://www.bilibili.com/video/BV1cj411A7VW)
读论文、[翻译](https://www.bilibili.com/video/BV1KT411x7Wn)论文 | [插件] 一键解读latex/pdf论文全文并生成摘要
Latex全文[翻译](https://www.bilibili.com/video/BV1nk4y1Y7Js/)、[润色](https://www.bilibili.com/video/BV1FT411H7c5/) | [插件] 一键翻译或润色latex论文
批量注释生成 | [插件] 一键批量生成函数注释
Markdown[中英互译](https://www.bilibili.com/video/BV1yo4y157jV/) | [插件] 看到上面5种语言的[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)了吗？就是出自他的手笔
chat分析报告生成 | [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) | [插件] PDF论文提取题目&摘要+翻译全文（多线程）
[Arxiv小助手](https://www.bilibili.com/video/BV1LM4y1279X) | [插件] 输入arxiv文章url即可一键翻译摘要+下载PDF
Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼写纠错+输出对照PDF
[谷歌学术统合小助手](https://www.bilibili.com/video/BV19L411U7ia) | [插件] 给定任意谷歌学术搜索页面URL，让gpt帮你[写relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)
互联网信息聚合+GPT | [插件] 一键[让GPT从互联网获取信息](https://www.bilibili.com/video/BV1om4y127ck)回答问题，让信息永不过时
⭐Arxiv论文精细翻译 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [插件] 一键[以超高质量翻译arxiv论文](https://www.bilibili.com/video/BV1dz4y1v77A/)，目前最好的论文翻译工具
⭐[实时语音对话输入](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [插件] 异步[监听音频](https://www.bilibili.com/video/BV1AV4y187Uy/)，自动断句，自动寻找回答时机
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
⭐AutoGen多智能体插件 | [插件] 借助微软AutoGen，探索多Agent的智能涌现可能！
启动暗色[主题](https://github.com/binary-husky/gpt_academic/issues/173) | 在浏览器url后面添加```/?__theme=dark```可以切换dark主题
[多LLM模型](https://www.bilibili.com/video/BV1wT411p7yf)支持 | 同时被GPT3.5、GPT4、[清华ChatGLM2](https://github.com/THUDM/ChatGLM2-6B)、[复旦MOSS](https://github.com/OpenLMLab/MOSS)伺候的感觉一定会很不错吧？
⭐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/)
⭐[void-terminal](https://github.com/binary-husky/void-terminal) pip包 | 脱离GUI，在Python中直接调用本项目的所有函数插件（开发中）
⭐虚空终端插件 | [插件] 能够使用自然语言直接调度本项目其他插件
更多新功能展示 (图像生成等) …… | 见本文档结尾处 ……
</div>
- 新界面（修改`config.py`中的LAYOUT选项即可实现“左右布局”和“上下布局”的切换）
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/279702205-d81137c3-affd-4cd1-bb5e-b15610389762.gif" width="700" >
</div>
- 所有按钮都通过读取functional.py动态生成，可随意加自定义功能，解放剪贴板
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif" width="700" >
</div>
- 润色/纠错
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif" width="700" >
</div>
- 如果输出包含公式，会以tex形式和渲染形式同时显示，方便复制和阅读
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png" width="700" >
</div>
- 懒得看项目代码？直接把整个工程炫ChatGPT嘴里
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" width="700" >
</div>
- 多种大语言模型混合调用（ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4）
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png" width="700" >
</div>
<br><br>
# Installation
### 安装方法I：直接运行 (Windows, Linux or MacOS)
1. 下载项目
```sh
git clone --depth=1 https://github.com/binary-husky/gpt_academic.git
cd gpt_academic
```
2. 配置API_KEY等变量
在`config.py`中，配置API KEY等变量。[特殊网络环境设置方法](https://github.com/binary-husky/gpt_academic/issues/1)、[Wiki-项目配置说明](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。
「 程序会优先检查是否存在名为`config_private.py`的私密配置文件，并用其中的配置覆盖`config.py`的同名配置。如您能理解以上读取逻辑，我们强烈建议您在`config.py`同路径下创建一个名为`config_private.py`的新配置文件，并使用`config_private.py`配置项目，以确保更新或其他用户无法轻易查看您的私有配置 」。
「 支持通过`环境变量`配置项目，环境变量的书写格式参考`docker-compose.yml`文件或者我们的[Wiki页面](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)。配置读取优先级: `环境变量` > `config_private.py` > `config.py` 」。
3. 安装依赖
```sh
# （选择I: 如熟悉python, python推荐版本 3.9 ~ 3.11）备注：使用官方pip源或者阿里pip源, 临时换源方法：python -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/
python -m pip install -r requirements.txt
# （选择II: 使用Anaconda）步骤也是类似的 (https://www.bilibili.com/video/BV1rc411W7Dr)：
conda create -n gptac_venv python=3.11 # 创建anaconda环境
conda activate gptac_venv # 激活anaconda环境
python -m pip install -r requirements.txt # 这个步骤和pip安装一样的步骤
```
<details><summary>如果需要支持清华ChatGLM2/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
<p>
【可选步骤】如果需要支持清华ChatGLM2/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
```sh
# 【可选步骤I】支持清华ChatGLM2。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
python -m pip install -r request_llms/requirements_chatglm.txt
# 【可选步骤II】支持复旦MOSS
python -m pip install -r request_llms/requirements_moss.txt
git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss # 注意执行此行代码时，必须处于项目根路径
# 【可选步骤III】支持RWKV Runner
参考wiki：https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
# 【可选步骤IV】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
```
</p>
</details>
4. 运行
```sh
python main.py
```
### 安装方法II：使用Docker
0. 部署项目的全部能力（这个是包含cuda和latex的大型镜像。但如果您网速慢、硬盘小，则不推荐该方法部署完整项目）
[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)
``` sh
# 修改docker-compose.yml，保留方案0并删除其他方案。然后运行：
docker-compose up
```
1. 仅ChatGPT+文心一言+spark等在线模型（推荐大多数人选择）
[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)
[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)
[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)
``` sh
# 修改docker-compose.yml，保留方案1并删除其他方案。然后运行：
docker-compose up
```
P.S. 如果需要依赖Latex的插件功能，请见Wiki。另外，您也可以直接使用方案4或者方案0获取Latex功能。
2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + 通义千问（需要熟悉[Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian)运行时）
[](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。然后运行：
docker-compose up
```
### 安装方法III：其他部署方法
1. **Windows一键运行脚本**。
完全不熟悉python环境的Windows用户可以下载[Release](https://github.com/binary-husky/gpt_academic/releases)中发布的一键运行脚本安装无本地模型的版本。脚本贡献来源：[oobabooga](https://github.com/oobabooga/one-click-installers)。
2. 使用第三方API、Azure等、文心一言、星火等，见[Wiki页面](https://github.com/binary-husky/gpt_academic/wiki/项目配置说明)
3. 云服务器远程部署避坑指南。
请访问[云服务器远程部署wiki](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)
4. 在其他平台部署&二级网址部署
- 使用Sealos[一键部署](https://github.com/binary-husky/gpt_academic/issues/993)。
- 使用WSL2（Windows Subsystem for Linux 子系统）。请访问[部署wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)
- 如何在二级网址（如`http://localhost/subpath`）下运行。请访问[FastAPI运行说明](docs/WithFastapi.md)
<br><br>
# Advanced Usage
### I：自定义新的便捷按钮（学术快捷键）
任意文本编辑器打开`core_functional.py`，添加如下条目，然后重启程序。（如果按钮已存在，那么可以直接修改（前缀、后缀都已支持热修改），无需重启程序即可生效。）
例如
```python
"超级英译中": {
# 前缀，会被加在你的输入之前。例如，用来描述你的要求，例如翻译、解释代码、润色等等
"Prefix": "请翻译把下面一段内容成中文，然后用一个markdown表格逐一解释文中出现的专有名词：\n\n",
# 后缀，会被加在你的输入之后。例如，配合前缀可以把你的输入内容用引号圈起来。
"Suffix": "",
},
```
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png" width="500" >
</div>
### II：自定义函数插件
编写强大的函数插件来执行任何你想得到的和想不到的任务。
本项目的插件编写、调试难度很低，只要您具备一定的python基础知识，就可以仿照我们提供的模板实现自己的插件功能。
详情请参考[函数插件指南](https://github.com/binary-husky/gpt_academic/wiki/%E5%87%BD%E6%95%B0%E6%8F%92%E4%BB%B6%E6%8C%87%E5%8D%97)。
<br><br>
# Updates
### I：动态
1. 对话保存功能。在函数插件区调用 `保存当前的对话` 即可将当前对话保存为可读+可复原的html文件，
另外在函数插件区（下拉菜单）调用 `载入对话历史存档` ，即可还原之前的会话。
Tip：不指定文件直接点击 `载入对话历史存档` 可以查看历史html存档缓存。
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png" width="500" >
</div>
2. ⭐Latex/Arxiv论文翻译功能⭐
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1" height="250" > ===>
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b" height="250" >
</div>
3. 虚空终端（从自然语言输入中，理解用户意图+自动调用其他插件）
- 步骤一：输入 “ 请调用插件翻译PDF论文，地址为https://openreview.net/pdf?id=rJl0r3R9KX ”
- 步骤二：点击“虚空终端”
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed" width="500" >
</div>
4. 模块化功能设计，简单的接口却能支持强大的功能
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png" height="400" >
<img src="https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png" height="400" >
</div>
5. 译解其他开源项目
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png" height="250" >
<img src="https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png" height="250" >
</div>
6. 装饰[live2d](https://github.com/fghrsh/live2d_demo)的小功能（默认关闭，需要修改`config.py`）
<div align="center">
<img src="https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png" width="500" >
</div>
7. OpenAI图像生成
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665" width="500" >
</div>
8. OpenAI音频解析与总结
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b" width="500" >
</div>
9. Latex全文校对纠错
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033" height="200" > ===>
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb" height="200">
</div>
10. 语言、主题切换
<div align="center">
<img src="https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8" width="500" >
</div>
### II：版本:
- version 3.70（todo）: 优化AutoGen插件主题并设计一系列衍生插件
- version 3.60: 引入AutoGen作为新一代插件的基石
- version 3.57: 支持GLM3，星火v3，文心一言v4，修复本地模型的并发BUG
- version 3.56: 支持动态追加基础功能按钮，新汇报PDF汇总页面
- version 3.55: 重构前端界面，引入悬浮窗口与菜单栏
- version 3.54: 新增动态代码解释器（Code Interpreter）（待完善）
- version 3.53: 支持动态选择不同界面主题，提高稳定性&解决多用户冲突问题
- version 3.50: 使用自然语言调用本项目的所有函数插件（虚空终端），支持插件分类，改进UI，设计新主题
- version 3.49: 支持百度千帆平台和文心一言
- version 3.48: 支持阿里达摩院通义千问，上海AI-Lab书生，讯飞星火
- version 3.46: 支持完全脱手操作的实时语音对话
- version 3.45: 支持自定义ChatGLM2微调模型
- version 3.44: 正式支持Azure，优化界面易用性
- version 3.4: +arxiv论文翻译、latex论文批改功能
- version 3.3: +互联网信息综合功能
- version 3.2: 函数插件支持更多参数接口 (保存对话功能, 解读任意语言代码+同时询问任意的LLM组合)
- version 3.1: 支持同时问询多个gpt模型！支持api2d，支持多个apikey负载均衡
- version 3.0: 对chatglm和其他小型llm的支持
- version 2.6: 重构了插件结构，提高了交互性，加入更多插件
- version 2.5: 自更新，解决总结大工程源代码时文本过长、token溢出的问题
- version 2.4: 新增PDF全文翻译功能; 新增输入区切换位置的功能
- version 2.3: 增强多线程交互性
- version 2.2: 函数插件支持热重载
- version 2.1: 可折叠式布局
- version 2.0: 引入模块化函数插件
- version 1.0: 基础功能
GPT Academic开发者QQ群：`610599535`
- 已知问题
- 某些浏览器翻译插件干扰此软件前端的运行
- 官方Gradio目前有很多兼容性问题，请**务必使用`requirement.txt`安装Gradio**
### III：主题
可以通过修改`THEME`选项（config.py）变更主题
1. `Chuanhu-Small-and-Beautiful` [网址](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)
### IV：本项目的开发分支
1. `master` 分支: 主分支，稳定版
2. `frontier` 分支: 开发分支，测试版
3. 如何接入其他大模型：[接入其他大模型](request_llms/README.md)
### V：参考与学习
```
代码中参考了很多其他优秀项目中的设计，顺序不分先后：
# 清华ChatGLM2-6B:
https://github.com/THUDM/ChatGLM2-6B
# 清华JittorLLMs:
https://github.com/Jittor/JittorLLMs
# ChatPaper:
https://github.com/kaixindelele/ChatPaper
# Edge-GPT:
https://github.com/acheong08/EdgeGPT
# ChuanhuChatGPT:
https://github.com/GaiZhenbiao/ChuanhuChatGPT
# Oobabooga one-click installer:
https://github.com/oobabooga/one-click-installers
# More：
https://github.com/gradio-app/gradio
https://github.com/fghrsh/live2d_demo
```
Raw data
{
"_id": null,
"home_page": "",
"name": "chatgpt-academic",
"maintainer": "",
"docs_url": null,
"requires_python": "<3.13,>=3.8",
"maintainer_email": "",
"keywords": "",
"author": "",
"author_email": "Wang Hailin <wanghailin@tongji.edu.cn>",
"download_url": "https://files.pythonhosted.org/packages/df/f5/e762d5a88e762ad99aae2de45a63fa9e3f21bf4001d05f9330403271de96/chatgpt-academic-3.60.3.tar.gz",
"platform": null,
"description": "# ChatGPT Academic Wrapper\n\n[gpt_academic](https://github.com/binary-husky/gpt_academic) \u7684\u4e00\u4e2a\u5206\u652f\uff0c\u63d0\u4f9b\u4e86\u4e00\u4e2a Python \u5e93\u548c Windows \u5b89\u88c5\u7a0b\u5e8f\uff0c\u4ee5\u65b9\u4fbf\u5b89\u88c5\u3002\n\n\u4f60\u53ef\u4ee5\u5230 [GitHub Release](https://github.com/haiiliin/chatgpt-academic/releases) \u9875\u9762\u4e0b\u8f7d ChatGPT Academic \u7684\u79bb\u7ebf\u5b89\u88c5\u5305\uff0c\u89e3\u538b\u540e\u5b89\u88c5\u5373\u53ef\u4f7f\u7528\u3002\n\u6216\u8005\u4e5f\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u547d\u4ee4\u5b89\u88c5 ChatGPT Academic\uff1a\n```sh\npip install chatgpt-academic\n```\n\u914d\u7f6e\u9879\u76ee\u8bf7\u4f7f\u7528 [\u73af\u5883\u53d8\u91cf](https://github.com/binary-husky/gpt_academic/wiki/\u9879\u76ee\u914d\u7f6e\u8bf4\u660e#4-\u73af\u5883\u53d8\u91cf\u683c\u5f0f\u8bf4\u660e)\u3002\n\n> **Caution**\n> \n> 2023.11.12: \u67d0\u4e9b\u4f9d\u8d56\u5305\u5c1a\u4e0d\u517c\u5bb9python 3.12\uff0c\u63a8\u8350python 3.11\u3002\n> \n> 2023.11.7: \u5b89\u88c5\u4f9d\u8d56\u65f6\uff0c\u8bf7\u9009\u62e9`requirements.txt`\u4e2d**\u6307\u5b9a\u7684\u7248\u672c**\u3002 \u5b89\u88c5\u547d\u4ee4\uff1a`pip install -r requirements.txt`\u3002\u672c\u9879\u76ee\u5f00\u6e90\u514d\u8d39\uff0c\u8fd1\u671f\u53d1\u73b0\u6709\u4eba\u8511\u89c6\u5f00\u6e90\u534f\u8bae\u5e76\u5229\u7528\u672c\u9879\u76ee\u8fdd\u89c4\u5708\u94b1\uff0c\u8bf7\u63d0\u9ad8\u8b66\u60d5\uff0c\u8c28\u9632\u4e0a\u5f53\u53d7\u9a97\u3002\n\n<br>\n\n<div align=center>\n<h1 aligh=\"center\">\n<img src=\"docs/logo.png\" width=\"40\"> GPT \u5b66\u672f\u4f18\u5316 (GPT Academic)\n</h1>\n\n[![Github][Github-image]][Github-url]\n[![License][License-image]][License-url]\n[![Releases][Releases-image]][Releases-url]\n[![Installation][Installation-image]][Installation-url]\n[![Wiki][Wiki-image]][Wiki-url]\n[![PR][PRs-image]][PRs-url]\n\n[License-image]: https://img.shields.io/badge/LICENSE-GPL3.0-orange?&style=flat-square\n[Github-image]: https://img.shields.io/badge/github-12100E.svg?&style=flat-square\n[Releases-image]: https://img.shields.io/badge/Releases-v3.6.0-blue?style=flat-square\n[Installation-image]: https://img.shields.io/badge/Installation-v3.6.1-blue?style=flat-square\n[Wiki-image]: https://img.shields.io/badge/wiki-\u9879\u76ee\u6587\u6863-black?style=flat-square\n[PRs-image]: https://img.shields.io/badge/PRs-welcome-pink?style=flat-square\n\n[License-url]: https://github.com/binary-husky/gpt_academic/blob/master/LICENSE\n[Github-url]: https://github.com/binary-husky/gpt_academic\n[Releases-url]: https://github.com/binary-husky/gpt_academic/releases\n[Installation-url]: https://github.com/binary-husky/gpt_academic#installation\n[Wiki-url]: https://github.com/binary-husky/gpt_academic/wiki\n[PRs-url]: https://github.com/binary-husky/gpt_academic/pulls\n\n\n</div>\n<br>\n\n**\u5982\u679c\u559c\u6b22\u8fd9\u4e2a\u9879\u76ee\uff0c\u8bf7\u7ed9\u5b83\u4e00\u4e2aStar\uff1b\u5982\u679c\u60a8\u53d1\u660e\u4e86\u597d\u7528\u7684\u5feb\u6377\u952e\u6216\u63d2\u4ef6\uff0c\u6b22\u8fce\u53d1pull requests\uff01**\n\nIf you like this project, please give it a Star. Read this in [English](docs/README.English.md) | [\u65e5\u672c\u8a9e](docs/README.Japanese.md) | [\ud55c\uad6d\uc5b4](docs/README.Korean.md) | [\u0420\u0443\u0441\u0441\u043a\u0438\u0439](docs/README.Russian.md) | [Fran\u00e7ais](docs/README.French.md). All translations have been provided by the project itself. To translate this project to arbitrary language with GPT, read and run [`multi_language.py`](multi_language.py) (experimental).\n<br>\n\n\n> 1.\u8bf7\u6ce8\u610f\u53ea\u6709 **\u9ad8\u4eae** \u6807\u8bc6\u7684\u63d2\u4ef6\uff08\u6309\u94ae\uff09\u624d\u652f\u6301\u8bfb\u53d6\u6587\u4ef6\uff0c\u90e8\u5206\u63d2\u4ef6\u4f4d\u4e8e\u63d2\u4ef6\u533a\u7684**\u4e0b\u62c9\u83dc\u5355**\u4e2d\u3002\u53e6\u5916\u6211\u4eec\u4ee5**\u6700\u9ad8\u4f18\u5148\u7ea7**\u6b22\u8fce\u548c\u5904\u7406\u4efb\u4f55\u65b0\u63d2\u4ef6\u7684PR\u3002\n>\n> 2.\u672c\u9879\u76ee\u4e2d\u6bcf\u4e2a\u6587\u4ef6\u7684\u529f\u80fd\u90fd\u5728[\u81ea\u8bd1\u89e3\u62a5\u544a](https://github.com/binary-husky/gpt_academic/wiki/GPT\u2010Academic\u9879\u76ee\u81ea\u8bd1\u89e3\u62a5\u544a)`self_analysis.md`\u8be6\u7ec6\u8bf4\u660e\u3002\u968f\u7740\u7248\u672c\u7684\u8fed\u4ee3\uff0c\u60a8\u4e5f\u53ef\u4ee5\u968f\u65f6\u81ea\u884c\u70b9\u51fb\u76f8\u5173\u51fd\u6570\u63d2\u4ef6\uff0c\u8c03\u7528GPT\u91cd\u65b0\u751f\u6210\u9879\u76ee\u7684\u81ea\u6211\u89e3\u6790\u62a5\u544a\u3002\u5e38\u89c1\u95ee\u9898\u8bf7\u67e5\u9605wiki\u3002\n> [](#installation) [](https://github.com/binary-husky/gpt_academic/releases) [](https://github.com/binary-husky/gpt_academic/wiki/\u9879\u76ee\u914d\u7f6e\u8bf4\u660e) []([https://github.com/binary-husky/gpt_academic/wiki/\u9879\u76ee\u914d\u7f6e\u8bf4\u660e](https://github.com/binary-husky/gpt_academic/wiki))\n> \n> 3.\u672c\u9879\u76ee\u517c\u5bb9\u5e76\u9f13\u52b1\u5c1d\u8bd5\u56fd\u4ea7\u5927\u8bed\u8a00\u6a21\u578bChatGLM\u7b49\u3002\u652f\u6301\u591a\u4e2aapi-key\u5171\u5b58\uff0c\u53ef\u5728\u914d\u7f6e\u6587\u4ef6\u4e2d\u586b\u5199\u5982`API_KEY=\"openai-key1,openai-key2,azure-key3,api2d-key4\"`\u3002\u9700\u8981\u4e34\u65f6\u66f4\u6362`API_KEY`\u65f6\uff0c\u5728\u8f93\u5165\u533a\u8f93\u5165\u4e34\u65f6\u7684`API_KEY`\u7136\u540e\u56de\u8f66\u952e\u63d0\u4ea4\u540e\u5373\u53ef\u751f\u6548\u3002\n\n<br><br>\n\n<div align=\"center\">\n\n\u529f\u80fd\uff08\u2b50= \u8fd1\u671f\u65b0\u589e\u529f\u80fd\uff09 | \u63cf\u8ff0\n--- | ---\n\u2b50[\u63a5\u5165\u65b0\u6a21\u578b](https://github.com/binary-husky/gpt_academic/wiki/%E5%A6%82%E4%BD%95%E5%88%87%E6%8D%A2%E6%A8%A1%E5%9E%8B) | \u767e\u5ea6[\u5343\u5e06](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu)\u4e0e\u6587\u5fc3\u4e00\u8a00, \u901a\u4e49\u5343\u95ee[Qwen](https://modelscope.cn/models/qwen/Qwen-7B-Chat/summary)\uff0c\u4e0a\u6d77AI-Lab[\u4e66\u751f](https://github.com/InternLM/InternLM)\uff0c\u8baf\u98de[\u661f\u706b](https://xinghuo.xfyun.cn/)\uff0c[LLaMa2](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)\uff0c[\u667a\u8c31API](https://open.bigmodel.cn/)\uff0cDALLE3, [DeepseekCoder](https://coder.deepseek.com/)\n\u6da6\u8272\u3001\u7ffb\u8bd1\u3001\u4ee3\u7801\u89e3\u91ca | \u4e00\u952e\u6da6\u8272\u3001\u7ffb\u8bd1\u3001\u67e5\u627e\u8bba\u6587\u8bed\u6cd5\u9519\u8bef\u3001\u89e3\u91ca\u4ee3\u7801\n[\u81ea\u5b9a\u4e49\u5feb\u6377\u952e](https://www.bilibili.com/video/BV14s4y1E7jN) | \u652f\u6301\u81ea\u5b9a\u4e49\u5feb\u6377\u952e\n\u6a21\u5757\u5316\u8bbe\u8ba1 | \u652f\u6301\u81ea\u5b9a\u4e49\u5f3a\u5927\u7684[\u63d2\u4ef6](https://github.com/binary-husky/gpt_academic/tree/master/crazy_functions)\uff0c\u63d2\u4ef6\u652f\u6301[\u70ed\u66f4\u65b0](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)\n[\u7a0b\u5e8f\u5256\u6790](https://www.bilibili.com/video/BV1cj411A7VW) | [\u63d2\u4ef6] \u4e00\u952e\u5256\u6790Python/C/C++/Java/Lua/...\u9879\u76ee\u6811 \u6216 [\u81ea\u6211\u5256\u6790](https://www.bilibili.com/video/BV1cj411A7VW)\n\u8bfb\u8bba\u6587\u3001[\u7ffb\u8bd1](https://www.bilibili.com/video/BV1KT411x7Wn)\u8bba\u6587 | [\u63d2\u4ef6] \u4e00\u952e\u89e3\u8bfblatex/pdf\u8bba\u6587\u5168\u6587\u5e76\u751f\u6210\u6458\u8981\nLatex\u5168\u6587[\u7ffb\u8bd1](https://www.bilibili.com/video/BV1nk4y1Y7Js/)\u3001[\u6da6\u8272](https://www.bilibili.com/video/BV1FT411H7c5/) | [\u63d2\u4ef6] \u4e00\u952e\u7ffb\u8bd1\u6216\u6da6\u8272latex\u8bba\u6587\n\u6279\u91cf\u6ce8\u91ca\u751f\u6210 | [\u63d2\u4ef6] \u4e00\u952e\u6279\u91cf\u751f\u6210\u51fd\u6570\u6ce8\u91ca\nMarkdown[\u4e2d\u82f1\u4e92\u8bd1](https://www.bilibili.com/video/BV1yo4y157jV/) | [\u63d2\u4ef6] \u770b\u5230\u4e0a\u97625\u79cd\u8bed\u8a00\u7684[README](https://github.com/binary-husky/gpt_academic/blob/master/docs/README_EN.md)\u4e86\u5417\uff1f\u5c31\u662f\u51fa\u81ea\u4ed6\u7684\u624b\u7b14\nchat\u5206\u6790\u62a5\u544a\u751f\u6210 | [\u63d2\u4ef6] \u8fd0\u884c\u540e\u81ea\u52a8\u751f\u6210\u603b\u7ed3\u6c47\u62a5\n[PDF\u8bba\u6587\u5168\u6587\u7ffb\u8bd1\u529f\u80fd](https://www.bilibili.com/video/BV1KT411x7Wn) | [\u63d2\u4ef6] PDF\u8bba\u6587\u63d0\u53d6\u9898\u76ee&\u6458\u8981+\u7ffb\u8bd1\u5168\u6587\uff08\u591a\u7ebf\u7a0b\uff09\n[Arxiv\u5c0f\u52a9\u624b](https://www.bilibili.com/video/BV1LM4y1279X) | [\u63d2\u4ef6] \u8f93\u5165arxiv\u6587\u7ae0url\u5373\u53ef\u4e00\u952e\u7ffb\u8bd1\u6458\u8981+\u4e0b\u8f7dPDF\nLatex\u8bba\u6587\u4e00\u952e\u6821\u5bf9 | [\u63d2\u4ef6] \u4effGrammarly\u5bf9Latex\u6587\u7ae0\u8fdb\u884c\u8bed\u6cd5\u3001\u62fc\u5199\u7ea0\u9519+\u8f93\u51fa\u5bf9\u7167PDF\n[\u8c37\u6b4c\u5b66\u672f\u7edf\u5408\u5c0f\u52a9\u624b](https://www.bilibili.com/video/BV19L411U7ia) | [\u63d2\u4ef6] \u7ed9\u5b9a\u4efb\u610f\u8c37\u6b4c\u5b66\u672f\u641c\u7d22\u9875\u9762URL\uff0c\u8ba9gpt\u5e2e\u4f60[\u5199relatedworks](https://www.bilibili.com/video/BV1GP411U7Az/)\n\u4e92\u8054\u7f51\u4fe1\u606f\u805a\u5408+GPT | [\u63d2\u4ef6] \u4e00\u952e[\u8ba9GPT\u4ece\u4e92\u8054\u7f51\u83b7\u53d6\u4fe1\u606f](https://www.bilibili.com/video/BV1om4y127ck)\u56de\u7b54\u95ee\u9898\uff0c\u8ba9\u4fe1\u606f\u6c38\u4e0d\u8fc7\u65f6\n\u2b50Arxiv\u8bba\u6587\u7cbe\u7ec6\u7ffb\u8bd1 ([Docker](https://github.com/binary-husky/gpt_academic/pkgs/container/gpt_academic_with_latex)) | [\u63d2\u4ef6] \u4e00\u952e[\u4ee5\u8d85\u9ad8\u8d28\u91cf\u7ffb\u8bd1arxiv\u8bba\u6587](https://www.bilibili.com/video/BV1dz4y1v77A/)\uff0c\u76ee\u524d\u6700\u597d\u7684\u8bba\u6587\u7ffb\u8bd1\u5de5\u5177\n\u2b50[\u5b9e\u65f6\u8bed\u97f3\u5bf9\u8bdd\u8f93\u5165](https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md) | [\u63d2\u4ef6] \u5f02\u6b65[\u76d1\u542c\u97f3\u9891](https://www.bilibili.com/video/BV1AV4y187Uy/)\uff0c\u81ea\u52a8\u65ad\u53e5\uff0c\u81ea\u52a8\u5bfb\u627e\u56de\u7b54\u65f6\u673a\n\u516c\u5f0f/\u56fe\u7247/\u8868\u683c\u663e\u793a | \u53ef\u4ee5\u540c\u65f6\u663e\u793a\u516c\u5f0f\u7684[tex\u5f62\u5f0f\u548c\u6e32\u67d3\u5f62\u5f0f](https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png)\uff0c\u652f\u6301\u516c\u5f0f\u3001\u4ee3\u7801\u9ad8\u4eae\n\u2b50AutoGen\u591a\u667a\u80fd\u4f53\u63d2\u4ef6 | [\u63d2\u4ef6] \u501f\u52a9\u5fae\u8f6fAutoGen\uff0c\u63a2\u7d22\u591aAgent\u7684\u667a\u80fd\u6d8c\u73b0\u53ef\u80fd\uff01\n\u542f\u52a8\u6697\u8272[\u4e3b\u9898](https://github.com/binary-husky/gpt_academic/issues/173) | \u5728\u6d4f\u89c8\u5668url\u540e\u9762\u6dfb\u52a0```/?__theme=dark```\u53ef\u4ee5\u5207\u6362dark\u4e3b\u9898\n[\u591aLLM\u6a21\u578b](https://www.bilibili.com/video/BV1wT411p7yf)\u652f\u6301 | \u540c\u65f6\u88abGPT3.5\u3001GPT4\u3001[\u6e05\u534eChatGLM2](https://github.com/THUDM/ChatGLM2-6B)\u3001[\u590d\u65e6MOSS](https://github.com/OpenLMLab/MOSS)\u4f3a\u5019\u7684\u611f\u89c9\u4e00\u5b9a\u4f1a\u5f88\u4e0d\u9519\u5427\uff1f\n\u2b50ChatGLM2\u5fae\u8c03\u6a21\u578b | \u652f\u6301\u52a0\u8f7dChatGLM2\u5fae\u8c03\u6a21\u578b\uff0c\u63d0\u4f9bChatGLM2\u5fae\u8c03\u8f85\u52a9\u63d2\u4ef6\n\u66f4\u591aLLM\u6a21\u578b\u63a5\u5165\uff0c\u652f\u6301[huggingface\u90e8\u7f72](https://huggingface.co/spaces/qingxu98/gpt-academic) | \u52a0\u5165Newbing\u63a5\u53e3(\u65b0\u5fc5\u5e94)\uff0c\u5f15\u5165\u6e05\u534e[Jittorllms](https://github.com/Jittor/JittorLLMs)\u652f\u6301[LLaMA](https://github.com/facebookresearch/llama)\u548c[\u76d8\u53e4\u03b1](https://openi.org.cn/pangu/)\n\u2b50[void-terminal](https://github.com/binary-husky/void-terminal) pip\u5305 | \u8131\u79bbGUI\uff0c\u5728Python\u4e2d\u76f4\u63a5\u8c03\u7528\u672c\u9879\u76ee\u7684\u6240\u6709\u51fd\u6570\u63d2\u4ef6\uff08\u5f00\u53d1\u4e2d\uff09\n\u2b50\u865a\u7a7a\u7ec8\u7aef\u63d2\u4ef6 | [\u63d2\u4ef6] \u80fd\u591f\u4f7f\u7528\u81ea\u7136\u8bed\u8a00\u76f4\u63a5\u8c03\u5ea6\u672c\u9879\u76ee\u5176\u4ed6\u63d2\u4ef6\n\u66f4\u591a\u65b0\u529f\u80fd\u5c55\u793a (\u56fe\u50cf\u751f\u6210\u7b49) \u2026\u2026 | \u89c1\u672c\u6587\u6863\u7ed3\u5c3e\u5904 \u2026\u2026\n</div>\n\n\n- \u65b0\u754c\u9762\uff08\u4fee\u6539`config.py`\u4e2d\u7684LAYOUT\u9009\u9879\u5373\u53ef\u5b9e\u73b0\u201c\u5de6\u53f3\u5e03\u5c40\u201d\u548c\u201c\u4e0a\u4e0b\u5e03\u5c40\u201d\u7684\u5207\u6362\uff09\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/279702205-d81137c3-affd-4cd1-bb5e-b15610389762.gif\" width=\"700\" >\n</div>\n\n\n- \u6240\u6709\u6309\u94ae\u90fd\u901a\u8fc7\u8bfb\u53d6functional.py\u52a8\u6001\u751f\u6210\uff0c\u53ef\u968f\u610f\u52a0\u81ea\u5b9a\u4e49\u529f\u80fd\uff0c\u89e3\u653e\u526a\u8d34\u677f\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/231975334-b4788e91-4887-412f-8b43-2b9c5f41d248.gif\" width=\"700\" >\n</div>\n\n- \u6da6\u8272/\u7ea0\u9519\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/231980294-f374bdcb-3309-4560-b424-38ef39f04ebd.gif\" width=\"700\" >\n</div>\n\n- \u5982\u679c\u8f93\u51fa\u5305\u542b\u516c\u5f0f\uff0c\u4f1a\u4ee5tex\u5f62\u5f0f\u548c\u6e32\u67d3\u5f62\u5f0f\u540c\u65f6\u663e\u793a\uff0c\u65b9\u4fbf\u590d\u5236\u548c\u9605\u8bfb\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/230598842-1d7fcddd-815d-40ee-af60-baf488a199df.png\" width=\"700\" >\n</div>\n\n- \u61d2\u5f97\u770b\u9879\u76ee\u4ee3\u7801\uff1f\u76f4\u63a5\u628a\u6574\u4e2a\u5de5\u7a0b\u70abChatGPT\u5634\u91cc\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png\" width=\"700\" >\n</div>\n\n- \u591a\u79cd\u5927\u8bed\u8a00\u6a21\u578b\u6df7\u5408\u8c03\u7528\uff08ChatGLM + OpenAI-GPT3.5 + [API2D](https://api2d.com/)-GPT4\uff09\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/232537274-deca0563-7aa6-4b5d-94a2-b7c453c47794.png\" width=\"700\" >\n</div>\n\n<br><br>\n\n# Installation\n### \u5b89\u88c5\u65b9\u6cd5I\uff1a\u76f4\u63a5\u8fd0\u884c (Windows, Linux or MacOS) \n\n1. \u4e0b\u8f7d\u9879\u76ee\n\n ```sh\n git clone --depth=1 https://github.com/binary-husky/gpt_academic.git\n cd gpt_academic\n ```\n\n2. \u914d\u7f6eAPI_KEY\u7b49\u53d8\u91cf\n\n \u5728`config.py`\u4e2d\uff0c\u914d\u7f6eAPI KEY\u7b49\u53d8\u91cf\u3002[\u7279\u6b8a\u7f51\u7edc\u73af\u5883\u8bbe\u7f6e\u65b9\u6cd5](https://github.com/binary-husky/gpt_academic/issues/1)\u3001[Wiki-\u9879\u76ee\u914d\u7f6e\u8bf4\u660e](https://github.com/binary-husky/gpt_academic/wiki/\u9879\u76ee\u914d\u7f6e\u8bf4\u660e)\u3002\n\n \u300c \u7a0b\u5e8f\u4f1a\u4f18\u5148\u68c0\u67e5\u662f\u5426\u5b58\u5728\u540d\u4e3a`config_private.py`\u7684\u79c1\u5bc6\u914d\u7f6e\u6587\u4ef6\uff0c\u5e76\u7528\u5176\u4e2d\u7684\u914d\u7f6e\u8986\u76d6`config.py`\u7684\u540c\u540d\u914d\u7f6e\u3002\u5982\u60a8\u80fd\u7406\u89e3\u4ee5\u4e0a\u8bfb\u53d6\u903b\u8f91\uff0c\u6211\u4eec\u5f3a\u70c8\u5efa\u8bae\u60a8\u5728`config.py`\u540c\u8def\u5f84\u4e0b\u521b\u5efa\u4e00\u4e2a\u540d\u4e3a`config_private.py`\u7684\u65b0\u914d\u7f6e\u6587\u4ef6\uff0c\u5e76\u4f7f\u7528`config_private.py`\u914d\u7f6e\u9879\u76ee\uff0c\u4ee5\u786e\u4fdd\u66f4\u65b0\u6216\u5176\u4ed6\u7528\u6237\u65e0\u6cd5\u8f7b\u6613\u67e5\u770b\u60a8\u7684\u79c1\u6709\u914d\u7f6e \u300d\u3002\n\n \u300c \u652f\u6301\u901a\u8fc7`\u73af\u5883\u53d8\u91cf`\u914d\u7f6e\u9879\u76ee\uff0c\u73af\u5883\u53d8\u91cf\u7684\u4e66\u5199\u683c\u5f0f\u53c2\u8003`docker-compose.yml`\u6587\u4ef6\u6216\u8005\u6211\u4eec\u7684[Wiki\u9875\u9762](https://github.com/binary-husky/gpt_academic/wiki/\u9879\u76ee\u914d\u7f6e\u8bf4\u660e)\u3002\u914d\u7f6e\u8bfb\u53d6\u4f18\u5148\u7ea7: `\u73af\u5883\u53d8\u91cf` > `config_private.py` > `config.py` \u300d\u3002\n\n\n3. \u5b89\u88c5\u4f9d\u8d56\n ```sh\n # \uff08\u9009\u62e9I: \u5982\u719f\u6089python, python\u63a8\u8350\u7248\u672c 3.9 ~ 3.11\uff09\u5907\u6ce8\uff1a\u4f7f\u7528\u5b98\u65b9pip\u6e90\u6216\u8005\u963f\u91ccpip\u6e90, \u4e34\u65f6\u6362\u6e90\u65b9\u6cd5\uff1apython -m pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/\n python -m pip install -r requirements.txt\n\n # \uff08\u9009\u62e9II: \u4f7f\u7528Anaconda\uff09\u6b65\u9aa4\u4e5f\u662f\u7c7b\u4f3c\u7684 (https://www.bilibili.com/video/BV1rc411W7Dr)\uff1a\n conda create -n gptac_venv python=3.11 # \u521b\u5efaanaconda\u73af\u5883\n conda activate gptac_venv # \u6fc0\u6d3banaconda\u73af\u5883\n python -m pip install -r requirements.txt # \u8fd9\u4e2a\u6b65\u9aa4\u548cpip\u5b89\u88c5\u4e00\u6837\u7684\u6b65\u9aa4\n ```\n\n\n<details><summary>\u5982\u679c\u9700\u8981\u652f\u6301\u6e05\u534eChatGLM2/\u590d\u65e6MOSS/RWKV\u4f5c\u4e3a\u540e\u7aef\uff0c\u8bf7\u70b9\u51fb\u5c55\u5f00\u6b64\u5904</summary>\n<p>\n\n\u3010\u53ef\u9009\u6b65\u9aa4\u3011\u5982\u679c\u9700\u8981\u652f\u6301\u6e05\u534eChatGLM2/\u590d\u65e6MOSS\u4f5c\u4e3a\u540e\u7aef\uff0c\u9700\u8981\u989d\u5916\u5b89\u88c5\u66f4\u591a\u4f9d\u8d56\uff08\u524d\u63d0\u6761\u4ef6\uff1a\u719f\u6089Python + \u7528\u8fc7Pytorch + \u7535\u8111\u914d\u7f6e\u591f\u5f3a\uff09\uff1a\n\n```sh\n# \u3010\u53ef\u9009\u6b65\u9aa4I\u3011\u652f\u6301\u6e05\u534eChatGLM2\u3002\u6e05\u534eChatGLM\u5907\u6ce8\uff1a\u5982\u679c\u9047\u5230\"Call ChatGLM fail \u4e0d\u80fd\u6b63\u5e38\u52a0\u8f7dChatGLM\u7684\u53c2\u6570\" \u9519\u8bef\uff0c\u53c2\u8003\u5982\u4e0b\uff1a 1\uff1a\u4ee5\u4e0a\u9ed8\u8ba4\u5b89\u88c5\u7684\u4e3atorch+cpu\u7248\uff0c\u4f7f\u7528cuda\u9700\u8981\u5378\u8f7dtorch\u91cd\u65b0\u5b89\u88c5torch+cuda\uff1b 2\uff1a\u5982\u56e0\u672c\u673a\u914d\u7f6e\u4e0d\u591f\u65e0\u6cd5\u52a0\u8f7d\u6a21\u578b\uff0c\u53ef\u4ee5\u4fee\u6539request_llm/bridge_chatglm.py\u4e2d\u7684\u6a21\u578b\u7cbe\u5ea6, \u5c06 AutoTokenizer.from_pretrained(\"THUDM/chatglm-6b\", trust_remote_code=True) \u90fd\u4fee\u6539\u4e3a AutoTokenizer.from_pretrained(\"THUDM/chatglm-6b-int4\", trust_remote_code=True)\npython -m pip install -r request_llms/requirements_chatglm.txt \n\n# \u3010\u53ef\u9009\u6b65\u9aa4II\u3011\u652f\u6301\u590d\u65e6MOSS\npython -m pip install -r request_llms/requirements_moss.txt\ngit clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss # \u6ce8\u610f\u6267\u884c\u6b64\u884c\u4ee3\u7801\u65f6\uff0c\u5fc5\u987b\u5904\u4e8e\u9879\u76ee\u6839\u8def\u5f84\n\n# \u3010\u53ef\u9009\u6b65\u9aa4III\u3011\u652f\u6301RWKV Runner\n\u53c2\u8003wiki\uff1ahttps://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner\n\n# \u3010\u53ef\u9009\u6b65\u9aa4IV\u3011\u786e\u4fddconfig.py\u914d\u7f6e\u6587\u4ef6\u7684AVAIL_LLM_MODELS\u5305\u542b\u4e86\u671f\u671b\u7684\u6a21\u578b\uff0c\u76ee\u524d\u652f\u6301\u7684\u5168\u90e8\u6a21\u578b\u5982\u4e0b(jittorllms\u7cfb\u5217\u76ee\u524d\u4ec5\u652f\u6301docker\u65b9\u6848)\uff1a\nAVAIL_LLM_MODELS = [\"gpt-3.5-turbo\", \"api2d-gpt-3.5-turbo\", \"gpt-4\", \"api2d-gpt-4\", \"chatglm\", \"moss\"] # + [\"jittorllms_rwkv\", \"jittorllms_pangualpha\", \"jittorllms_llama\"]\n```\n\n</p>\n</details>\n\n\n\n4. \u8fd0\u884c\n ```sh\n python main.py\n ```\n\n### \u5b89\u88c5\u65b9\u6cd5II\uff1a\u4f7f\u7528Docker\n\n0. \u90e8\u7f72\u9879\u76ee\u7684\u5168\u90e8\u80fd\u529b\uff08\u8fd9\u4e2a\u662f\u5305\u542bcuda\u548clatex\u7684\u5927\u578b\u955c\u50cf\u3002\u4f46\u5982\u679c\u60a8\u7f51\u901f\u6162\u3001\u786c\u76d8\u5c0f\uff0c\u5219\u4e0d\u63a8\u8350\u8be5\u65b9\u6cd5\u90e8\u7f72\u5b8c\u6574\u9879\u76ee\uff09\n[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-all-capacity.yml)\n\n ``` sh\n # \u4fee\u6539docker-compose.yml\uff0c\u4fdd\u7559\u65b9\u68480\u5e76\u5220\u9664\u5176\u4ed6\u65b9\u6848\u3002\u7136\u540e\u8fd0\u884c\uff1a\n docker-compose up\n ```\n\n1. \u4ec5ChatGPT+\u6587\u5fc3\u4e00\u8a00+spark\u7b49\u5728\u7ebf\u6a21\u578b\uff08\u63a8\u8350\u5927\u591a\u6570\u4eba\u9009\u62e9\uff09\n[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-without-local-llms.yml)\n[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-latex.yml)\n[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-audio-assistant.yml)\n\n ``` sh\n # \u4fee\u6539docker-compose.yml\uff0c\u4fdd\u7559\u65b9\u68481\u5e76\u5220\u9664\u5176\u4ed6\u65b9\u6848\u3002\u7136\u540e\u8fd0\u884c\uff1a\n docker-compose up\n ```\n\nP.S. \u5982\u679c\u9700\u8981\u4f9d\u8d56Latex\u7684\u63d2\u4ef6\u529f\u80fd\uff0c\u8bf7\u89c1Wiki\u3002\u53e6\u5916\uff0c\u60a8\u4e5f\u53ef\u4ee5\u76f4\u63a5\u4f7f\u7528\u65b9\u68484\u6216\u8005\u65b9\u68480\u83b7\u53d6Latex\u529f\u80fd\u3002\n\n2. ChatGPT + ChatGLM2 + MOSS + LLAMA2 + \u901a\u4e49\u5343\u95ee\uff08\u9700\u8981\u719f\u6089[Nvidia Docker](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#installing-on-ubuntu-and-debian)\u8fd0\u884c\u65f6\uff09\n[](https://github.com/binary-husky/gpt_academic/actions/workflows/build-with-chatglm.yml)\n\n ``` sh\n # \u4fee\u6539docker-compose.yml\uff0c\u4fdd\u7559\u65b9\u68482\u5e76\u5220\u9664\u5176\u4ed6\u65b9\u6848\u3002\u7136\u540e\u8fd0\u884c\uff1a\n docker-compose up\n ```\n\n\n### \u5b89\u88c5\u65b9\u6cd5III\uff1a\u5176\u4ed6\u90e8\u7f72\u65b9\u6cd5\n1. **Windows\u4e00\u952e\u8fd0\u884c\u811a\u672c**\u3002\n\u5b8c\u5168\u4e0d\u719f\u6089python\u73af\u5883\u7684Windows\u7528\u6237\u53ef\u4ee5\u4e0b\u8f7d[Release](https://github.com/binary-husky/gpt_academic/releases)\u4e2d\u53d1\u5e03\u7684\u4e00\u952e\u8fd0\u884c\u811a\u672c\u5b89\u88c5\u65e0\u672c\u5730\u6a21\u578b\u7684\u7248\u672c\u3002\u811a\u672c\u8d21\u732e\u6765\u6e90\uff1a[oobabooga](https://github.com/oobabooga/one-click-installers)\u3002\n\n2. \u4f7f\u7528\u7b2c\u4e09\u65b9API\u3001Azure\u7b49\u3001\u6587\u5fc3\u4e00\u8a00\u3001\u661f\u706b\u7b49\uff0c\u89c1[Wiki\u9875\u9762](https://github.com/binary-husky/gpt_academic/wiki/\u9879\u76ee\u914d\u7f6e\u8bf4\u660e)\n\n3. \u4e91\u670d\u52a1\u5668\u8fdc\u7a0b\u90e8\u7f72\u907f\u5751\u6307\u5357\u3002\n\u8bf7\u8bbf\u95ee[\u4e91\u670d\u52a1\u5668\u8fdc\u7a0b\u90e8\u7f72wiki](https://github.com/binary-husky/gpt_academic/wiki/%E4%BA%91%E6%9C%8D%E5%8A%A1%E5%99%A8%E8%BF%9C%E7%A8%8B%E9%83%A8%E7%BD%B2%E6%8C%87%E5%8D%97)\n\n4. \u5728\u5176\u4ed6\u5e73\u53f0\u90e8\u7f72&\u4e8c\u7ea7\u7f51\u5740\u90e8\u7f72\n - \u4f7f\u7528Sealos[\u4e00\u952e\u90e8\u7f72](https://github.com/binary-husky/gpt_academic/issues/993)\u3002\n - \u4f7f\u7528WSL2\uff08Windows Subsystem for Linux \u5b50\u7cfb\u7edf\uff09\u3002\u8bf7\u8bbf\u95ee[\u90e8\u7f72wiki-2](https://github.com/binary-husky/gpt_academic/wiki/%E4%BD%BF%E7%94%A8WSL2%EF%BC%88Windows-Subsystem-for-Linux-%E5%AD%90%E7%B3%BB%E7%BB%9F%EF%BC%89%E9%83%A8%E7%BD%B2)\n - \u5982\u4f55\u5728\u4e8c\u7ea7\u7f51\u5740\uff08\u5982`http://localhost/subpath`\uff09\u4e0b\u8fd0\u884c\u3002\u8bf7\u8bbf\u95ee[FastAPI\u8fd0\u884c\u8bf4\u660e](docs/WithFastapi.md)\n\n<br><br>\n\n# Advanced Usage\n### I\uff1a\u81ea\u5b9a\u4e49\u65b0\u7684\u4fbf\u6377\u6309\u94ae\uff08\u5b66\u672f\u5feb\u6377\u952e\uff09\n\n\u4efb\u610f\u6587\u672c\u7f16\u8f91\u5668\u6253\u5f00`core_functional.py`\uff0c\u6dfb\u52a0\u5982\u4e0b\u6761\u76ee\uff0c\u7136\u540e\u91cd\u542f\u7a0b\u5e8f\u3002\uff08\u5982\u679c\u6309\u94ae\u5df2\u5b58\u5728\uff0c\u90a3\u4e48\u53ef\u4ee5\u76f4\u63a5\u4fee\u6539\uff08\u524d\u7f00\u3001\u540e\u7f00\u90fd\u5df2\u652f\u6301\u70ed\u4fee\u6539\uff09\uff0c\u65e0\u9700\u91cd\u542f\u7a0b\u5e8f\u5373\u53ef\u751f\u6548\u3002\uff09\n\u4f8b\u5982\n\n```python\n\"\u8d85\u7ea7\u82f1\u8bd1\u4e2d\": {\n # \u524d\u7f00\uff0c\u4f1a\u88ab\u52a0\u5728\u4f60\u7684\u8f93\u5165\u4e4b\u524d\u3002\u4f8b\u5982\uff0c\u7528\u6765\u63cf\u8ff0\u4f60\u7684\u8981\u6c42\uff0c\u4f8b\u5982\u7ffb\u8bd1\u3001\u89e3\u91ca\u4ee3\u7801\u3001\u6da6\u8272\u7b49\u7b49\n \"Prefix\": \"\u8bf7\u7ffb\u8bd1\u628a\u4e0b\u9762\u4e00\u6bb5\u5185\u5bb9\u6210\u4e2d\u6587\uff0c\u7136\u540e\u7528\u4e00\u4e2amarkdown\u8868\u683c\u9010\u4e00\u89e3\u91ca\u6587\u4e2d\u51fa\u73b0\u7684\u4e13\u6709\u540d\u8bcd\uff1a\\n\\n\", \n \n # \u540e\u7f00\uff0c\u4f1a\u88ab\u52a0\u5728\u4f60\u7684\u8f93\u5165\u4e4b\u540e\u3002\u4f8b\u5982\uff0c\u914d\u5408\u524d\u7f00\u53ef\u4ee5\u628a\u4f60\u7684\u8f93\u5165\u5185\u5bb9\u7528\u5f15\u53f7\u5708\u8d77\u6765\u3002\n \"Suffix\": \"\",\n},\n```\n\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/226899272-477c2134-ed71-4326-810c-29891fe4a508.png\" width=\"500\" >\n</div>\n\n### II\uff1a\u81ea\u5b9a\u4e49\u51fd\u6570\u63d2\u4ef6\n\u7f16\u5199\u5f3a\u5927\u7684\u51fd\u6570\u63d2\u4ef6\u6765\u6267\u884c\u4efb\u4f55\u4f60\u60f3\u5f97\u5230\u7684\u548c\u60f3\u4e0d\u5230\u7684\u4efb\u52a1\u3002\n\u672c\u9879\u76ee\u7684\u63d2\u4ef6\u7f16\u5199\u3001\u8c03\u8bd5\u96be\u5ea6\u5f88\u4f4e\uff0c\u53ea\u8981\u60a8\u5177\u5907\u4e00\u5b9a\u7684python\u57fa\u7840\u77e5\u8bc6\uff0c\u5c31\u53ef\u4ee5\u4eff\u7167\u6211\u4eec\u63d0\u4f9b\u7684\u6a21\u677f\u5b9e\u73b0\u81ea\u5df1\u7684\u63d2\u4ef6\u529f\u80fd\u3002\n\u8be6\u60c5\u8bf7\u53c2\u8003[\u51fd\u6570\u63d2\u4ef6\u6307\u5357](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)\u3002\n\n<br><br>\n\n# Updates\n### I\uff1a\u52a8\u6001\n\n1. \u5bf9\u8bdd\u4fdd\u5b58\u529f\u80fd\u3002\u5728\u51fd\u6570\u63d2\u4ef6\u533a\u8c03\u7528 `\u4fdd\u5b58\u5f53\u524d\u7684\u5bf9\u8bdd` \u5373\u53ef\u5c06\u5f53\u524d\u5bf9\u8bdd\u4fdd\u5b58\u4e3a\u53ef\u8bfb+\u53ef\u590d\u539f\u7684html\u6587\u4ef6\uff0c\n\u53e6\u5916\u5728\u51fd\u6570\u63d2\u4ef6\u533a\uff08\u4e0b\u62c9\u83dc\u5355\uff09\u8c03\u7528 `\u8f7d\u5165\u5bf9\u8bdd\u5386\u53f2\u5b58\u6863` \uff0c\u5373\u53ef\u8fd8\u539f\u4e4b\u524d\u7684\u4f1a\u8bdd\u3002\nTip\uff1a\u4e0d\u6307\u5b9a\u6587\u4ef6\u76f4\u63a5\u70b9\u51fb `\u8f7d\u5165\u5bf9\u8bdd\u5386\u53f2\u5b58\u6863` \u53ef\u4ee5\u67e5\u770b\u5386\u53f2html\u5b58\u6863\u7f13\u5b58\u3002\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/235222390-24a9acc0-680f-49f5-bc81-2f3161f1e049.png\" width=\"500\" >\n</div>\n\n2. \u2b50Latex/Arxiv\u8bba\u6587\u7ffb\u8bd1\u529f\u80fd\u2b50\n<div align=\"center\">\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/002a1a75-ace0-4e6a-94e2-ec1406a746f1\" height=\"250\" > ===>\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/9fdcc391-f823-464f-9322-f8719677043b\" height=\"250\" >\n</div>\n\n3. \u865a\u7a7a\u7ec8\u7aef\uff08\u4ece\u81ea\u7136\u8bed\u8a00\u8f93\u5165\u4e2d\uff0c\u7406\u89e3\u7528\u6237\u610f\u56fe+\u81ea\u52a8\u8c03\u7528\u5176\u4ed6\u63d2\u4ef6\uff09\n\n- \u6b65\u9aa4\u4e00\uff1a\u8f93\u5165 \u201c \u8bf7\u8c03\u7528\u63d2\u4ef6\u7ffb\u8bd1PDF\u8bba\u6587\uff0c\u5730\u5740\u4e3ahttps://openreview.net/pdf?id=rJl0r3R9KX \u201d\n- \u6b65\u9aa4\u4e8c\uff1a\u70b9\u51fb\u201c\u865a\u7a7a\u7ec8\u7aef\u201d\n\n<div align=\"center\">\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/66f1b044-e9ff-4eed-9126-5d4f3668f1ed\" width=\"500\" >\n</div>\n\n4. \u6a21\u5757\u5316\u529f\u80fd\u8bbe\u8ba1\uff0c\u7b80\u5355\u7684\u63a5\u53e3\u5374\u80fd\u652f\u6301\u5f3a\u5927\u7684\u529f\u80fd\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/229288270-093643c1-0018-487a-81e6-1d7809b6e90f.png\" height=\"400\" >\n<img src=\"https://user-images.githubusercontent.com/96192199/227504931-19955f78-45cd-4d1c-adac-e71e50957915.png\" height=\"400\" >\n</div>\n\n5. \u8bd1\u89e3\u5176\u4ed6\u5f00\u6e90\u9879\u76ee\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/226935232-6b6a73ce-8900-4aee-93f9-733c7e6fef53.png\" height=\"250\" >\n<img src=\"https://user-images.githubusercontent.com/96192199/226969067-968a27c1-1b9c-486b-8b81-ab2de8d3f88a.png\" height=\"250\" >\n</div>\n\n6. \u88c5\u9970[live2d](https://github.com/fghrsh/live2d_demo)\u7684\u5c0f\u529f\u80fd\uff08\u9ed8\u8ba4\u5173\u95ed\uff0c\u9700\u8981\u4fee\u6539`config.py`\uff09\n<div align=\"center\">\n<img src=\"https://user-images.githubusercontent.com/96192199/236432361-67739153-73e8-43fe-8111-b61296edabd9.png\" width=\"500\" >\n</div>\n\n7. OpenAI\u56fe\u50cf\u751f\u6210\n<div align=\"center\">\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/bc7ab234-ad90-48a0-8d62-f703d9e74665\" width=\"500\" >\n</div>\n\n8. OpenAI\u97f3\u9891\u89e3\u6790\u4e0e\u603b\u7ed3\n<div align=\"center\">\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/709ccf95-3aee-498a-934a-e1c22d3d5d5b\" width=\"500\" >\n</div>\n\n9. Latex\u5168\u6587\u6821\u5bf9\u7ea0\u9519\n<div align=\"center\">\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/651ccd98-02c9-4464-91e1-77a6b7d1b033\" height=\"200\" > ===>\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/476f66d9-7716-4537-b5c1-735372c25adb\" height=\"200\">\n</div>\n\n10. \u8bed\u8a00\u3001\u4e3b\u9898\u5207\u6362\n<div align=\"center\">\n<img src=\"https://github.com/binary-husky/gpt_academic/assets/96192199/b6799499-b6fb-4f0c-9c8e-1b441872f4e8\" width=\"500\" >\n</div>\n\n\n\n### II\uff1a\u7248\u672c:\n\n- version 3.70\uff08todo\uff09: \u4f18\u5316AutoGen\u63d2\u4ef6\u4e3b\u9898\u5e76\u8bbe\u8ba1\u4e00\u7cfb\u5217\u884d\u751f\u63d2\u4ef6\n- version 3.60: \u5f15\u5165AutoGen\u4f5c\u4e3a\u65b0\u4e00\u4ee3\u63d2\u4ef6\u7684\u57fa\u77f3\n- version 3.57: \u652f\u6301GLM3\uff0c\u661f\u706bv3\uff0c\u6587\u5fc3\u4e00\u8a00v4\uff0c\u4fee\u590d\u672c\u5730\u6a21\u578b\u7684\u5e76\u53d1BUG\n- version 3.56: \u652f\u6301\u52a8\u6001\u8ffd\u52a0\u57fa\u7840\u529f\u80fd\u6309\u94ae\uff0c\u65b0\u6c47\u62a5PDF\u6c47\u603b\u9875\u9762\n- version 3.55: \u91cd\u6784\u524d\u7aef\u754c\u9762\uff0c\u5f15\u5165\u60ac\u6d6e\u7a97\u53e3\u4e0e\u83dc\u5355\u680f\n- version 3.54: \u65b0\u589e\u52a8\u6001\u4ee3\u7801\u89e3\u91ca\u5668\uff08Code Interpreter\uff09\uff08\u5f85\u5b8c\u5584\uff09\n- version 3.53: \u652f\u6301\u52a8\u6001\u9009\u62e9\u4e0d\u540c\u754c\u9762\u4e3b\u9898\uff0c\u63d0\u9ad8\u7a33\u5b9a\u6027&\u89e3\u51b3\u591a\u7528\u6237\u51b2\u7a81\u95ee\u9898\n- version 3.50: \u4f7f\u7528\u81ea\u7136\u8bed\u8a00\u8c03\u7528\u672c\u9879\u76ee\u7684\u6240\u6709\u51fd\u6570\u63d2\u4ef6\uff08\u865a\u7a7a\u7ec8\u7aef\uff09\uff0c\u652f\u6301\u63d2\u4ef6\u5206\u7c7b\uff0c\u6539\u8fdbUI\uff0c\u8bbe\u8ba1\u65b0\u4e3b\u9898\n- version 3.49: \u652f\u6301\u767e\u5ea6\u5343\u5e06\u5e73\u53f0\u548c\u6587\u5fc3\u4e00\u8a00\n- version 3.48: \u652f\u6301\u963f\u91cc\u8fbe\u6469\u9662\u901a\u4e49\u5343\u95ee\uff0c\u4e0a\u6d77AI-Lab\u4e66\u751f\uff0c\u8baf\u98de\u661f\u706b\n- version 3.46: \u652f\u6301\u5b8c\u5168\u8131\u624b\u64cd\u4f5c\u7684\u5b9e\u65f6\u8bed\u97f3\u5bf9\u8bdd\n- version 3.45: \u652f\u6301\u81ea\u5b9a\u4e49ChatGLM2\u5fae\u8c03\u6a21\u578b\n- version 3.44: \u6b63\u5f0f\u652f\u6301Azure\uff0c\u4f18\u5316\u754c\u9762\u6613\u7528\u6027\n- version 3.4: +arxiv\u8bba\u6587\u7ffb\u8bd1\u3001latex\u8bba\u6587\u6279\u6539\u529f\u80fd\n- version 3.3: +\u4e92\u8054\u7f51\u4fe1\u606f\u7efc\u5408\u529f\u80fd\n- version 3.2: \u51fd\u6570\u63d2\u4ef6\u652f\u6301\u66f4\u591a\u53c2\u6570\u63a5\u53e3 (\u4fdd\u5b58\u5bf9\u8bdd\u529f\u80fd, \u89e3\u8bfb\u4efb\u610f\u8bed\u8a00\u4ee3\u7801+\u540c\u65f6\u8be2\u95ee\u4efb\u610f\u7684LLM\u7ec4\u5408)\n- version 3.1: \u652f\u6301\u540c\u65f6\u95ee\u8be2\u591a\u4e2agpt\u6a21\u578b\uff01\u652f\u6301api2d\uff0c\u652f\u6301\u591a\u4e2aapikey\u8d1f\u8f7d\u5747\u8861\n- version 3.0: \u5bf9chatglm\u548c\u5176\u4ed6\u5c0f\u578bllm\u7684\u652f\u6301\n- version 2.6: \u91cd\u6784\u4e86\u63d2\u4ef6\u7ed3\u6784\uff0c\u63d0\u9ad8\u4e86\u4ea4\u4e92\u6027\uff0c\u52a0\u5165\u66f4\u591a\u63d2\u4ef6\n- version 2.5: \u81ea\u66f4\u65b0\uff0c\u89e3\u51b3\u603b\u7ed3\u5927\u5de5\u7a0b\u6e90\u4ee3\u7801\u65f6\u6587\u672c\u8fc7\u957f\u3001token\u6ea2\u51fa\u7684\u95ee\u9898\n- version 2.4: \u65b0\u589ePDF\u5168\u6587\u7ffb\u8bd1\u529f\u80fd; \u65b0\u589e\u8f93\u5165\u533a\u5207\u6362\u4f4d\u7f6e\u7684\u529f\u80fd\n- version 2.3: \u589e\u5f3a\u591a\u7ebf\u7a0b\u4ea4\u4e92\u6027\n- version 2.2: \u51fd\u6570\u63d2\u4ef6\u652f\u6301\u70ed\u91cd\u8f7d\n- version 2.1: \u53ef\u6298\u53e0\u5f0f\u5e03\u5c40\n- version 2.0: \u5f15\u5165\u6a21\u5757\u5316\u51fd\u6570\u63d2\u4ef6\n- version 1.0: \u57fa\u7840\u529f\u80fd\n\nGPT Academic\u5f00\u53d1\u8005QQ\u7fa4\uff1a`610599535`\n\n- \u5df2\u77e5\u95ee\u9898\n - \u67d0\u4e9b\u6d4f\u89c8\u5668\u7ffb\u8bd1\u63d2\u4ef6\u5e72\u6270\u6b64\u8f6f\u4ef6\u524d\u7aef\u7684\u8fd0\u884c\n - \u5b98\u65b9Gradio\u76ee\u524d\u6709\u5f88\u591a\u517c\u5bb9\u6027\u95ee\u9898\uff0c\u8bf7**\u52a1\u5fc5\u4f7f\u7528`requirement.txt`\u5b89\u88c5Gradio**\n\n### III\uff1a\u4e3b\u9898\n\u53ef\u4ee5\u901a\u8fc7\u4fee\u6539`THEME`\u9009\u9879\uff08config.py\uff09\u53d8\u66f4\u4e3b\u9898\n1. `Chuanhu-Small-and-Beautiful` [\u7f51\u5740](https://github.com/GaiZhenbiao/ChuanhuChatGPT/)\n\n\n### IV\uff1a\u672c\u9879\u76ee\u7684\u5f00\u53d1\u5206\u652f\n\n1. `master` \u5206\u652f: \u4e3b\u5206\u652f\uff0c\u7a33\u5b9a\u7248\n2. `frontier` \u5206\u652f: \u5f00\u53d1\u5206\u652f\uff0c\u6d4b\u8bd5\u7248\n3. \u5982\u4f55\u63a5\u5165\u5176\u4ed6\u5927\u6a21\u578b\uff1a[\u63a5\u5165\u5176\u4ed6\u5927\u6a21\u578b](request_llms/README.md)\n\n\n### V\uff1a\u53c2\u8003\u4e0e\u5b66\u4e60\n\n```\n\u4ee3\u7801\u4e2d\u53c2\u8003\u4e86\u5f88\u591a\u5176\u4ed6\u4f18\u79c0\u9879\u76ee\u4e2d\u7684\u8bbe\u8ba1\uff0c\u987a\u5e8f\u4e0d\u5206\u5148\u540e\uff1a\n\n# \u6e05\u534eChatGLM2-6B:\nhttps://github.com/THUDM/ChatGLM2-6B\n\n# \u6e05\u534eJittorLLMs:\nhttps://github.com/Jittor/JittorLLMs\n\n# ChatPaper:\nhttps://github.com/kaixindelele/ChatPaper\n\n# Edge-GPT:\nhttps://github.com/acheong08/EdgeGPT\n\n# ChuanhuChatGPT:\nhttps://github.com/GaiZhenbiao/ChuanhuChatGPT\n\n# Oobabooga one-click installer:\nhttps://github.com/oobabooga/one-click-installers\n\n# More\uff1a\nhttps://github.com/gradio-app/gradio\nhttps://github.com/fghrsh/live2d_demo\n```\n",
"bugtrack_url": null,
"license": "",
"summary": "ChatGPT Academic",
"version": "3.60.3",
"project_urls": {
"Homepage": "https://github.com/haiiliin/chatgpt-academic/"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "06051b58a2c6fa5b9dd33c2fc5d79569c2e377ff13d9fb41cb67b6f429b54bae",
"md5": "04ede7ab6278ce9a2cb76375d2299377",
"sha256": "38d99ab7e0d37b6ed8eeadb8c77e9f030da46411387ad49d5d7e66c0f2c53676"
},
"downloads": -1,
"filename": "chatgpt_academic-3.60.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "04ede7ab6278ce9a2cb76375d2299377",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.8",
"size": 19170717,
"upload_time": "2023-12-01T02:23:04",
"upload_time_iso_8601": "2023-12-01T02:23:04.256980Z",
"url": "https://files.pythonhosted.org/packages/06/05/1b58a2c6fa5b9dd33c2fc5d79569c2e377ff13d9fb41cb67b6f429b54bae/chatgpt_academic-3.60.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "dff5e762d5a88e762ad99aae2de45a63fa9e3f21bf4001d05f9330403271de96",
"md5": "b6579b65630bbeb7568680b86e005330",
"sha256": "3bc53f1ad56e1957a923296d839e7c6a407dc324bf9747d882dfd8e662bfbe99"
},
"downloads": -1,
"filename": "chatgpt-academic-3.60.3.tar.gz",
"has_sig": false,
"md5_digest": "b6579b65630bbeb7568680b86e005330",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.8",
"size": 18930068,
"upload_time": "2023-12-01T02:23:08",
"upload_time_iso_8601": "2023-12-01T02:23:08.286988Z",
"url": "https://files.pythonhosted.org/packages/df/f5/e762d5a88e762ad99aae2de45a63fa9e3f21bf4001d05f9330403271de96/chatgpt-academic-3.60.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-01 02:23:08",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "haiiliin",
"github_project": "chatgpt-academic",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": null,
"specs": []
},
{
"name": "fastapi",
"specs": [
[
"==",
"0.110"
]
]
},
{
"name": "gradio-client",
"specs": [
[
"==",
"0.8"
]
]
},
{
"name": "pypdf2",
"specs": [
[
"==",
"2.12.1"
]
]
},
{
"name": "zhipuai",
"specs": [
[
"==",
"2.0.1"
]
]
},
{
"name": "tiktoken",
"specs": [
[
">=",
"0.3.3"
]
]
},
{
"name": "requests",
"specs": []
},
{
"name": "pydantic",
"specs": [
[
"==",
"2.5.2"
]
]
},
{
"name": "llama-index",
"specs": [
[
"==",
"0.10"
]
]
},
{
"name": "protobuf",
"specs": [
[
"==",
"3.20"
]
]
},
{
"name": "transformers",
"specs": [
[
">=",
"4.27.1"
],
[
"<",
"4.42"
]
]
},
{
"name": "scipdf_parser",
"specs": [
[
">=",
"0.52"
]
]
},
{
"name": "anthropic",
"specs": [
[
">=",
"0.18.1"
]
]
},
{
"name": "python-markdown-math",
"specs": []
},
{
"name": "pymdown-extensions",
"specs": []
},
{
"name": "websocket-client",
"specs": []
},
{
"name": "beautifulsoup4",
"specs": []
},
{
"name": "prompt_toolkit",
"specs": []
},
{
"name": "latex2mathml",
"specs": []
},
{
"name": "python-docx",
"specs": []
},
{
"name": "mdtex2html",
"specs": []
},
{
"name": "dashscope",
"specs": []
},
{
"name": "pyautogen",
"specs": []
},
{
"name": "colorama",
"specs": []
},
{
"name": "Markdown",
"specs": []
},
{
"name": "pygments",
"specs": []
},
{
"name": "edge-tts",
"specs": []
},
{
"name": "pymupdf",
"specs": []
},
{
"name": "openai",
"specs": []
},
{
"name": "rjsmin",
"specs": []
},
{
"name": "arxiv",
"specs": []
},
{
"name": "numpy",
"specs": []
},
{
"name": "rich",
"specs": []
}
],
"lcname": "chatgpt-academic"
}
JSON
