CodeBase RAG

A powerful RAG (Retrieval-Augmented Generation) system for querying codebases using natural language. This tool allows you to ask questions about any codebase and get AI-powered responses based on the actual code content.

Features

• Clone and process GitHub repositories
• Extract code from multiple file types
• Generate embeddings using HuggingFace models
• Store and retrieve code snippets using Pinecone vector database
• Query codebase using natural language
• Get AI-powered responses using OpenRouter's LLM API

Prerequisites

• Python 3.8+
• Pinecone API key
• OpenRouter API key

Installation

1. Clone the repository:

git clone https://github.com/yourusername/CodeBase_RAG.git
cd CodeBase_RAG

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Create a .env file in the root directory with your API keys:

PINECONE_API_KEY=your_pinecone_key
OPENROUTER_API_KEY=your_openrouter_key

Usage

1. Run the main script:

python main.py

2. The script will:

   • Clone the specified GitHub repository
   • Process all supported code files
   • Generate embeddings and store them in Pinecone
   • Allow you to query the codebase

3. Example query:

response = rag_system.perform_rag("How to improve this repo?")

Supported File Types

• Python (.py)
• JavaScript (.js)
• TypeScript (.ts, .tsx)
• Java (.java)
• C/C++ (.c, .cpp, .h)
• Go (.go)
• Rust (.rs)
• Vue (.vue)
• Swift (.swift)
• Jupyter Notebooks (.ipynb)

Project Structure

CodeBase_RAG/
├── config/
│   ├── __init__.py
│   └── settings.py      # Configuration and constants
├── src/
│   ├── __init__.py
│   ├── repository.py    # Repository operations
│   ├── embeddings.py    # Embedding generation
│   └── rag.py          # RAG system implementation
├── main.py             # Main entry point
├── requirements.txt    # Project dependencies
└── README.md          # This file

Contributing

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.