MCP服务器React Agents基于RAG的聊天机器人
这个项目是一个 代理聊天机器人 使用 自定义MCP工具 来自MCP服务器，与 检索增强生成（RAG） 用于上下文感知响应。它包括一个FastAPI后端、一个基于FastMCP的工具服务器和一个基于Streamlit的用户交互UI。
______________________________________________________________________
🚀 特性
- ✅ 基于代理的推理使用 LangChain反应剂
- 🔧 与以下人员沟通 自定义MCP工具 超过
streamable_http - 📚 合并 检索增强生成 用于增强知识检索
- 🖥️ 界面友好 流线型UI
- ⚡ 模块化且易于运行的组件
______________________________________________________________________
📦 安装说明
1.克隆存储库
git clone https://github.com/your-username/MCP-server-React-Agents-RAG-based-chatbot.git
cd MCP-server-React-Agents-RAG-based-chatbot
### 2. Create & Activate a Virtual Environment
python -m venv venv
# Activate it
# On Windows:
venv\Scripts\activate
# On Mac/Linux:
source venv/bin/activate
### 3. Install Requirements
pip install -r requirements.txt
📁 Main Components & How to Run
🔹 app.py - Agent Server (FastAPI)
This is the main entry point for your agent. It connects to the MCP server and invokes tools to perform actions based on the user input.
Run with:
uvicorn app:app --reload --port 8001
🔹 server.py - MCP Tool Server (FastMCP)
This file defines your custom MCP tools that are called by the agent in app.py via streamable_http transport.
Run with:
python server.py
🔹 ui.py - User Interface (Streamlit)
Provides a simple Streamlit web interface for interacting with the agent.
Run with:
streamlit run ui.py --server.port 8502
Then open http://localhost:8502 in your browser.
✅ Execution Order
Start the MCP Tool Server:
python server.py
Start the Agent Server:
uvicorn app:app --reload --port 8001
Start the Streamlit UI:
streamlit run ui.py --server.port 8502
📁 Directory Structure
MCP-server-React-Agents-RAG-based-chatbot/
│
├── app.py # FastAPI agent using MCP tools
├── server.py # FastMCP tool server
├── ui.py # Streamlit UI
├── requirements.txt
└── README.md
💡 Tips
Make sure all ports (8001 and 8502) are free before starting.
You can customize your tools in server.py to extend functionality.
Update the agent logic in app.py to adjust behavior or tools used.
🛠️ Requirements
Python 3.9+
FastAPI
FastMCP
LangChain
Streamlit
Uvicorn
Other dependencies listed in requirements.txt
📝 License
This project is licensed under the MIT License. See the LICENSE file for more details.