A comprehensive stock market analysis and AI-powered financial assistant tool that combines data visualization, RAG (Retrieval-Augmented Generation), and AI analysis capabilities.
- Dashboard: Visualize stock data with interactive charts and performance metrics
- RAG Query: Ask questions about stocks and get AI-generated answers based on retrieved information
- AI Analysis: Get AI-powered analysis of stock performance and trends
- AI Assistant Chat: Chat with an AI assistant about stocks and financial topics
- Python 3.8 or higher
- Ollama installed and running
- Required Ollama models: llama3, mistral, gemma, phi
-
Clone the repository:
git clone https://github.com/jaganthoutam/StoxChai.git cd StoxChai -
Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install the required packages:
pip install -r requirements.txt -
Run the setup script to initialize the application:
streamlit run analysis-tool.py
-
Run the application:
streamlit run analysis-tool.py -
The application will open in your default web browser at http://localhost:8501
-
Enter a stock symbol (e.g., HDFCBANK.NS, RELIANCE.NS) in the sidebar
-
Select the time period and interval for the data
-
Navigate between different pages using the sidebar
If you encounter issues with the Yahoo Finance API (e.g., "No price data found" or "429 Client Error: Too Many Requests"), try the following:
- Wait a few minutes before trying again
- Use a different stock symbol
- Try a different time period or interval
- Check your internet connection
If you encounter issues with Torch, try the following:
-
Reinstall Torch:
pip uninstall torch pip install torch -
Set environment variables to disable CUDA:
export CUDA_VISIBLE_DEVICES=""
This project is licensed under the MIT License - see the LICENSE file for details.
- Streamlit for the web application framework
- Yahoo Finance for the stock data
- Ollama for the AI models
- LangChain for the RAG implementation