ashare-llm-analyst  by Ogannesson

Python tool for stock analysis using LLMs

created 5 months ago
266 stars

Top 96.9% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides an automated A-share stock analysis tool that leverages large language models for data-driven investment advice. It's designed for individual investors and researchers interested in technical analysis and AI-powered market insights. The tool generates comprehensive HTML reports with technical indicators, charts, and AI-generated recommendations.

How It Works

The tool fetches A-share historical data using the Ashare library and calculates over 25 technical indicators (e.g., MACD, KDJ, RSI) via MyTT. Matplotlib is used for generating detailed charts. The core innovation lies in integrating the Deepseek LLM API to provide professional investment analysis and recommendations, transforming raw data into actionable insights and a readable HTML report.

Quick Start & Requirements

  • Install dependencies: pip install pandas numpy matplotlib pytz
  • Configure LLM API key and base URL (Deepseek recommended) via environment variables (LLM_API_KEY, LLM_BASE_URL, LLM_MODEL) or directly in code.
  • Run analysis: python main.py (after setting stock code in main.py).
  • Reports are saved to public/index.html.
  • Official documentation and demo links are not explicitly provided, but the README details setup and usage.

Highlighted Details

  • Automates A-share data acquisition.
  • Calculates over 25 technical indicators.
  • Integrates Deepseek LLM for AI-driven investment advice.
  • Generates comprehensive HTML analysis reports.

Maintenance & Community

This is a personal, privately used repository made public. No specific community channels, roadmap, or notable contributors are mentioned.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: Permissive MIT license allows for commercial use and integration with closed-source projects.

Limitations & Caveats

The project is a personal tool with minimal security measures for API credentials; users must manage sensitive information carefully. It currently supports single stock analysis, with plans to add batch processing and backtesting. The tool is for learning and research only, not financial advice.

Health Check
Last commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
0
Star History
44 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.