A-Scope-Research

# A-Scope Research - 金融智能体团队 Based on MCP (Model Context Protocol), this is an intelligent analysis system for the Chinese A-share market. Through the collaboration and debate of multiple professional intelligent agents, it provides comprehensive analysis support for investment decisions. ## 🌟 System Features ### 🤖 Professional Intelligent Agent Team - **Technical Analyst (Li Jishu)**: Focuses on technical indicators, chart patterns, and trend analysis - **Fundamental Analyst (Wang Jiben)**: Focuses on financial data, company value, and industry analysis - **Quantitative Analyst (Zhang Lianghua)**: Uses mathematical models, statistical methods, and risk quantification - **Market Sentiment Analyst (Chen Qingxu)**: Analyzes investor sentiment, market psychology, and public opinion - **Risk Manager (Liu Fengkong)**: Assesses investment risks and formulates risk control strategies ### 🔄 Intelligent Collaboration Process 1. **Parallel Analysis**: Each intelligent agent independently analyzes the target stock from a professional perspective 2. **Team Debate**: Multiple rounds of debate to exchange views and question assumptions 3. **Final Decision**: Investment recommendations are made based on the consensus of the debate 4. **Risk Assessment**: Comprehensive risk analysis and control recommendations ### 🛠️ Technical Architecture - **MCP Protocol Integration**: Real-time access to A-share market data and analysis tools - **Multi-Model Support**: Compatible with mainstream large models such as OpenAI, Zhipu GLM, and Tongyi Qianwen - **Real-time Web Interface**: Intelligent agent dialogue interface similar to WeChat group chat - **Flexible Configuration**: Supports YAML configuration files to customize models and parameters ## 🚀 Quick Start ### 1. Environment Preparation ```bash # Clone the project git clone <repository-url> cd A-Scope-Research # Create a virtual environment (recommended) python -m venv .venv # Activate the virtual environment # Windows .venv\Scripts\activate # Linux/Mac source .venv/bin/activate # Install dependencies pip install -r requirements.txt ``` ### 2. Configuration Settings #### Edit `config.yaml` ```yaml agents: technical_analyst: name: "李技术" model: "gpt-3.5-turbo" # 或其他支持的模型 api_key: "your_api_key_here" # 替换为您的API密钥 base_url: "https://api.openai.com/v1" # 或其他API地址 temperature: 0.7 max_tokens: 2000 # ... Other intelligent agent configurations ``` #### Supported Model Providers | Service Provider | base_url | Model Example | |--------|----------|----------| | OpenAI | `https://api.openai.com/v1` | `gpt-3.5-turbo`, `gpt-4` | | 智谱GLM | `https://open.bigmodel.cn/api/paas/v4/` | `glm-4`, `glm-3-turbo` | | 通义千问 | `https://dashscope.aliyuncs.com/compatible-mode/v1` | `qwen-turbo`, `qwen-plus` | | 月之暗面 | `https://api.moonshot.cn/v1` | `moonshot-v1-8k`, `moonshot-v1-32k` | | DeepSeek | `https://api.deepseek.com/v1` | `deepseek-chat`, `deepseek-coder` | ### 3. Running Methods #### 🌐 Web Interface Mode (Recommended) ```bash python main.py --mode web ``` Visit `http://localhost:8501` to open the Web interface #### 💻 Command Line Mode ```bash # Analyze the specified stock python main.py --mode cli --stock 000001 ``` #### 🎭 Demo Mode ```bash # Interactive demo python main.py --mode demo ``` ## 📊 Web Interface Features ### Main Features - **Real-time Team Status**: Displays the initialization status and number of tools for each intelligent agent - **Stock Analysis Input**: Supports 6-digit A-share code input - **Analysis Result Display**: Professional analysis reports from each intelligent agent - **Debate Process Visualization**: Real-time debate interface similar to group chat - **Final Decision Summary**: Investment recommendations and risk assessment - **Result Export**: Complete analysis report in JSON format ### Interface Features - 🎨 **Intelligent Agent Avatar**: Each intelligent agent has a unique emoji avatar - 🎨 **Color Differentiation**: Different roles use different color themes - ⏰ **Timestamp Display**: Complete analysis timeline - 🔧 **Tool Call Display**: Real-time display of MCP tool calls - 📱 **Responsive Design**: Adapts to different screen sizes ## 🔧 Project Structure ``` A-Scope-Research/ ├── main.py # Main entry file ├── config.yaml # Intelligent agent configuration file ├── mcp.json # MCP server configuration ├── requirements.txt # Python dependency package ├── README.md # Project documentation ├── src/ │ ├── __init__.py │ ├── agents/ # Intelligent agent module │ │ ├── __init__.py │ │ ├── base_agent.py # Base intelligent agent class │ │ └── team_manager.py # Team manager │ ├── prompts/ # Intelligent agent Prompt │ │ ├── __init__.py │ │ ├── technical_analyst.py # Technical analyst │ │ ├── fundamental_analyst.py # Fundamental analyst │ │ ├── quantitative_analyst.py # Quantitative analyst │ │ ├── sentiment_analyst.py # Sentiment analyst │ │ └── risk_manager.py # Risk manager │ └── ui/ # User interface │ ├── __init__.py │ └── streamlit_app.py # Streamlit Web application └── .venv/ # Virtual environment (automatically generated) ``` ## 🎯 Use Cases ### Individual Investors - Obtain multi-faceted professional analysis opinions - Understand the advantages and disadvantages of different investment strategies - Make more rational investment decisions ### Investment Institutions - Assist the decision-making process of the investment research team - Provide a standardized analysis framework - Reduce analysis bias from a single perspective ### Financial Education - Learn the application of different analysis methods - Understand the complexity of investment decisions - Observe the thinking process of professional analysts ## 🔍 Analysis Example ### Input ``` Stock Code: 000001 (Ping An Bank) ``` ### Output Example #### Technical Analyst View > 📈 From a technical perspective, 000001 is currently in an upward channel, MA20 support is effective, MACD golden cross signal is clear, it is recommended to buy on dips... #### Fundamental Analyst View > 📋 Ping An Bank's Q3 financial report shows that ROE is stable above 13%, the non-performing loan ratio is well controlled, and the valuation is relatively reasonable, with long-term investment value... #### Quantitative Analyst View > 🔢 Based on historical data backtesting, the risk-adjusted return at the current price is 1.8, and the volatility is at the historical median, it is recommended to allocate a standard position... #### Market Sentiment Analyst View > 😊 Recently, sentiment in the banking sector has rebounded, and institutional funds have flowed in significantly, but it is necessary to be wary of the impact of policy expectation changes on sentiment... #### Risk Manager View > 🛡️ The main risks come from changes in interest rate policies and the credit cycle. It is recommended to set an 8% stop loss and the position should not exceed 15% of the portfolio... ## ⚙️ Advanced Configuration ### Customize Intelligent Agents You can customize the behavior and professional expertise of intelligent agents by modifying the files in the `src/prompts/` directory. ### MCP Tool Extension Add a new MCP server in `mcp.json` to extend data sources and analysis tools. ### Model Parameter Tuning Adjust the `temperature` and `max_tokens` parameters of each intelligent agent in `config.yaml` to optimize output quality. ## 🐛 Troubleshooting ### Common Issues 1. **Model Connection Failed** - Check if the API key is correct - Verify the base_url format - Confirm that the network connection is normal 2. **MCP Tool Connection Failed** - Check the accessibility of the MCP server URL - Verify firewall settings - Confirm that the timeout setting is reasonable 3. **Dependency Package Installation Failed** - Use a domestic mirror source: `pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt` - Upgrade the pip version: `pip install --upgrade pip` ### Debug Mode Enable detailed log output: ```bash # Set environment variables export LOG_LEVEL=DEBUG python main.py --mode cli --stock 000001 ``` ## 🤝 Contribution Guide Welcome to submit Issues and Pull Requests to improve the project! ### Development Environment Setup ```bash # Install development dependencies pip install -r requirements.txt pip install pytest black flake8 mypy # Code formatting black src/ # Code check flake8 src/ # Type check mypy src/ # Run tests pytest ``` ## 📄 License This project is licensed under the MIT License, see the [LICENSE](LICENSE) file for details. ## 🙏 Acknowledgements - [LangChain](https://github.com/langchain-ai/langchain) - Large model application framework - [MCP](https://github.com/modelcontextprotocol) - Model Context Protocol - [Streamlit](https://streamlit.io/) - Web application framework ## 📞 Contact Information If you have any questions or suggestions, please contact us through the following methods: - Submit a [GitHub Issue](https://github.com/guangxiangdebizi/A-Scope-Research/issues) - Send an email to: guangxiangdebizi@gmail.com --- **Disclaimer**: This system is for learning and research purposes only and does not constitute investment advice. Investment is risky, and decisions should be made with caution.