Merge pull request #4 from jihe520/main

update readme

Author: jihe520

README.md

@@ -15,7 +15,9 @@
 自动完整一份可以获奖级别的建模论文
 
 <p align="center">
-    <img src="./docs/webui.png">
+    <img src="./docs/index.png">
+    <img src="./docs/coder.png">
+    <img src="./docs/writer.png">
 </p>
 
 ## ✨ 功能特性
@@ -41,50 +43,93 @@
 - [ ] 引入用户的交互（选择模型，重写等等）
 - [ ] codeinterpreter 接入云端 如 e2b 等供应商..
 - [ ] 多语言: R 语言, matlab
-
-clone 项目后，下载**Todo Tree**插件，可以查看代码中所有具体位置的 todo
+- [ ] 绘图 napki,draw.io
 
 ## 视频demo
 
-<video src="https://github.com/user-attachments/assets/10b3145a-feb7-4894-aaca-30d44bb35b9e"></video>
+<video src="https://github.com/user-attachments/assets/954cb607-8e7e-45c6-8b15-f85e204a0c5d"></video>
 
 ## 📖 使用教程
 
-1. 安装依赖
+> 确保电脑中安装好 Python, Nodejs, **Redis** 环境
+
+> 如果你想运行 命令行版本 cli 切换到 [master](https://github.com/jihe520/MathModelAgent/tree/master) 分支,部署更简单，但未来不会更新
 
-```bash
-git clone https://github.com/jihe520/MathModelAgent.git # 克隆项目
-pip install uv # 推荐使用 uv 管理 python 项目
-uv venv # 创建虚拟环境
-uv sync # 安装依赖
-```
 
-2. 配置模型
 
-复制`/config/config.toml.example`到`/config/config.toml`, 填写配置模型和 APIKEY
+1. 配置模型
+
+复制`/backend/.env.dev.example`到`/backend/.env.dev`(删除`.example` 后缀), 填写配置模型和 APIKEY
 [deepseek开发者平台](https://platform.deepseek.com/)
 
+```bash
+ENV=dev
+#兼容 OpenAI 格式都行，具体看官方文档
+DEEPSEEK_API_KEY=
+DEEPSEEK_MODEL=
+DEEPSEEK_BASE_URL=
+# 模型最大问答次数
+MAX_CHAT_TURNS=60
+# 思考反思次数
+MAX_RETRIES=5
+# https://e2b.dev/ 
+E2B_API_KEY=
+
+LOG_LEVEL=DEBUG
+DEBUG=true
+# 确保安装 Redis
+REDIS_URL=redis://localhost:6379/0
+REDIS_MAX_CONNECTIONS=20
+CORS_ALLOW_ORIGINS=http://localhost:5173,http://localhost:3000
+```
+
 推荐模型能力较强的、参数量大的模型。
 
-3. 运行测试 和 启动项目
+2. 安装依赖
+
+下载项目
+
+```bash
+git clone https://github.com/jihe520/MathModelAgent.git # 克隆项目
+```
+
+启动后端
 
 ```bash
-uv run example.py # 简单测试能否正确运行
-uv run webui.py # 推荐: 启动 webui
-uv run terminal.py # 启动终端项目
+cd backend # 切换到 backend 目录下
+pip install uv # 推荐使用 uv 管理 python 项目
+uv sync # 安装依赖
+# 启动后端
+ENV=DEV uvicorn app.main:app --host 0.0.0.0 --port 8000 --ws-ping-interval 60 --ws-ping-timeout 120
 ```
 
-运行的结果在`/project/work_dir/`目录下
+启动前端
 
-## 🤝 贡献
+```bash
+cd frontend # 切换到 frontend 目录下
+pnpm i #确保电脑安装了 pnpm
+pnpm run dev
+```
+
+
+运行的结果和产生在`backend/project/work_dir/xxx/*`目录下
+- notebook.ipynb: 保存运行过程中产生的代码
+- res.md: 保存最后运行产生的结果为 markdown 格式，使用 markdown 转 word(研究下 pandoc)
 
-- 项目处于**开发阶段**（我有时间就会更新），变更较多，还存在许多 Bug，我正着手修复。
-- 欢迎提交 issues 和 PRs
+## 🤝 贡献和开发
+
+- 项目处于**开发实验阶段**（我有时间就会更新），变更较多，还存在许多 Bug，我正着手修复。
+- 希望大家一起参与，让这个项目变得更好
+- 非常欢迎使用和提交  **PRs** 和 issues 
 - 需求参考 后期计划
 
+clone 项目后，下载 **Todo Tree** 插件，可以查看代码中所有具体位置的 todo
+
+`.cursor/*` 有项目整体架构、rules、mcp 可以方便开发使用
+
 ## 📄 版权License
 
-请勿商业用途，商业用途联系我（作者）
+个人免费使用，请勿商业用途，商业用途联系我（作者）
 
 ## 🙏 Reference
 
@@ -101,5 +146,6 @@ Thanks to the following projects:
 [danmo-tyc](https://github.com/danmo-tyc)
 
 有问题可以进群问
+[QQ 群：699970403](http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=rFKquDTSxKcWpEhRgpJD-dPhTtqLwJ9r&authKey=xYKvCFG5My4uYZTbIIoV5MIPQedW7hYzf0%2Fbs4EUZ100UegQWcQ8xEEgTczHsyU6&noverify=0&group_code=699970403)
 
 <img src="./docs/qq.jpg" height="400px">

README_EN.md

@@ -7,25 +7,33 @@
     Automatically complete mathematical modeling and generate a ready-to-submit paper.
 </h4>
 
-<br>
-<h5 align="center"> <a href="README.md">简体中文</a> | English </h5>
+<h5 align="center"><a href="README.md">简体中文</a> | English</h5>
 
-## Vision:
-3 days to 1 hour <br>
-Automatically generate an award-worthy mathematical modeling paper
+## 🌟 Vision
+
+Turn 3 days of competition into 1 hour <br>
+Automatically generate an award-level modeling paper
+
+<p align="center">
+    <img src="./docs/index.png">
+    <img src="./docs/coder.png">
+    <img src="./docs/writer.png">
+</p>
 
 ## ✨ Features
 
 - 🔍 Automatic problem analysis, mathematical modeling, code writing, error correction, and paper writing
 - 💻 Local code interpreter
 - 📝 Generate a well-formatted paper
 - 🤝 Multi-agents: ~~modeling expert~~, coding expert (reflection module, local code interpreter), paper expert
-- 🔄 Multi-llms: Different models for each agent
+- 🔄 Multi-LLMs: Different models for each agent
+- 💰 Low cost agentless (about 1 RMB per task)
 
 ## 🚀 Future Plans
 
+- [x] Add and complete webui, cli
 - [ ] Comprehensive tutorials and documentation
-- [ ] Web service
+- [ ] Provide web service
 - [ ] English support (MCM/ICM)
 - [ ] LaTeX template integration
 - [ ] Vision model integration
@@ -34,49 +42,106 @@ Automatically generate an award-worthy mathematical modeling paper
 - [ ] Docker deployment
 - [ ] User interaction (model selection, rewriting, etc.)
 - [ ] Cloud integration for code interpreter (e.g., e2b providers)
-
-After cloning the project, install the **Todo Tree** plugin to view all specific todo locations in the code
+- [ ] Multi-language: R, Matlab
+- [ ] Drawing: napki, draw.io
 
 ## Video Demo
 
 <video src="https://github.com/user-attachments/assets/10b3145a-feb7-4894-aaca-30d44bb35b9e"></video>
 
-
 ## 📖 Usage Guide
 
-1. Install Dependencies
+> **Notice:** Please make sure Python, Nodejs, and **Redis** are installed on your computer.
+>
+> If you want to run the CLI version, switch to the [master](https://github.com/jihe520/MathModelAgent/tree/master) branch. It's easier to deploy, but will not be updated in the future.
+
+1. Configure Model
+
+Copy `/backend/.env.dev.example` to `/backend/.env.dev` (remove the `.example` suffix), and fill in the model configuration and APIKEY  
+[Deepseek Developer Platform](https://platform.deepseek.com/)
+
+```bash
+ENV=dev
+# Compatible with OpenAI format, refer to official docs
+DEEPSEEK_API_KEY=
+DEEPSEEK_MODEL=
+DEEPSEEK_BASE_URL=
+# Max Q&A turns
+MAX_CHAT_TURNS=60
+# Reflection retries
+MAX_RETRIES=5
+# https://e2b.dev/
+E2B_API_KEY=
+
+LOG_LEVEL=DEBUG
+DEBUG=true
+# Make sure Redis is installed
+REDIS_URL=redis://localhost:6379/0
+REDIS_MAX_CONNECTIONS=20
+CORS_ALLOW_ORIGINS=http://localhost:5173,http://localhost:3000
+```
+
+It is recommended to use models with strong capabilities and large parameter counts.
+
+2. Install Dependencies
+
+Clone the project
+
 ```bash
 git clone https://github.com/jihe520/MathModelAgent.git
-pip install uv
-uv venv # create venv
-uv sync # install dependencies
 ```
-2. Configure Model
-Copy `/config/config.toml.example` to `/config/config.toml` and fill in the model configuration
 
-Recommend using models with strong capabilities and large parameter counts.
+Start backend
 
-3. Run Tests and Start Project
 ```bash
-uv run example.py # simple test to verify correct operation
-uv run main.py # complete project
+cd backend
+pip install uv # Recommended: use uv to manage python projects
+uv sync # Install dependencies
+# Start backend
+ENV=DEV uvicorn app.main:app --host 0.0.0.0 --port 8000 --ws-ping-interval 60 --ws-ping-timeout 120
 ```
 
-Results will be in the `/project/work_dir/` directory
+Start frontend
+
+```bash
+cd frontend
+pnpm i # Make sure pnpm is installed
+pnpm run dev
+```
+
+Results and outputs are generated in the `backend/project/work_dir/xxx/*` directory:
+- notebook.ipynb: code generated during execution
+- res.md: final results in markdown format, can be converted to Word (try pandoc)
+
+## 🤝 Contribution & Development
 
-## 🤝 Contribution
+- The project is in **experimental development stage** (updated when I have time), with frequent changes and some bugs being fixed.
+- Everyone is welcome to participate and make the project better.
+- PRs and issues are very welcome.
+- For requirements, refer to Future Plans.
 
-- Project is in **development stage** (I update when time permits), with frequent changes and some bugs that I'm working to fix.
-- Issues and PRs are welcome
-- For requirements, refer to Future Plans
+After cloning the project, install the **Todo Tree** plugin to view all todo locations in the code.
+
+`.cursor/*` contains overall architecture, rules, and mcp for easier development.
 
 ## 📄 License
 
-Not for commercial use. Contact me (author) for commercial purposes.
+Free for personal use. For commercial use, please contact me (the author).
 
 ## 🙏 Reference
+
 Thanks to the following projects:
 - [OpenCodeInterpreter](https://github.com/OpenCodeInterpreter/OpenCodeInterpreter/tree/main)
 - [TaskWeaver](https://github.com/microsoft/TaskWeaver)
 - [Code-Interpreter](https://github.com/MrGreyfun/Local-Code-Interpreter/tree/main)
 - [Latex](https://github.com/Veni222987/MathModelingLatexTemplate/tree/main)
+
+## Others
+
+Thanks to sponsors  
+[danmo-tyc](https://github.com/danmo-tyc)
+
+For questions, join the group  
+[QQ Group: 699970403](http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=rFKquDTSxKcWpEhRgpJD-dPhTtqLwJ9r&authKey=xYKvCFG5My4uYZTbIIoV5MIPQedW7hYzf0%2Fbs4EUZ100UegQWcQ8xEEgTczHsyU6&noverify=0&group_code=699970403)
+
+<img src="./docs/qq.jpg" height="400px">