🤖 CodeChat AI

Your AI-Powered Code Companion for Intelligent Repository Analysis

Demo • Documentation • Report Bug • Request Feature

---

🎯 Overview

CodeChat AI revolutionizes code understanding by combining the power of RAG (Retrieval-Augmented Generation) with advanced language models. It enables developers to have meaningful conversations about their codebase while maintaining deep context across multiple repositories.

✨ Key Features

🔄 Smart Repository Integration

• Seamless GitHub repository connection
• Automatic code analysis and indexing
• Support for multiple programming languages

🧠 Advanced Context Understanding

• RAG-powered code comprehension
• Maintains context across conversations
• Deep understanding of code structure

🤖 Multi-Model AI Support

• Google Gemini integration
• Extensible model architecture
• Optimized for code understanding

💬 Interactive Development Experience

• Natural language code queries
• Contextual code suggestions
• Real-time response generation

🚀 Getting Started

Prerequisites

Before you begin, ensure you have:

• Python 3.8 or higher

⚡ Quick Install

1. Clone & Setup

# Clone the repository
git clone https://github.com/sheicky/codebaseRAG.git
cd codebaseRAG

# Create and activate virtual environment
python -m venv venv
source venv/bin/activate  # Unix/macOS
# or
.\venv\Scripts\activate  # Windows

2. Install Dependencies

pip install -r requirements.txt

3. Configure Environment

# Create .env file
cp .env.example .env

# Add your API keys to .env
PINECONE_API_KEY=your_pinecone_key
GOOGLE_API_KEY=your_google_key
GITHUB_TOKEN=your_github_token

4. Launch Application

streamlit run rag_app.py

🏗️ Architecture

graph TD
    A[GitHub Repository] --> B[Repository Handler]
    B --> C[Code Processor]
    C --> D[Embedding Generator]
    D --> E[Pinecone Vector Store]
    E --> F[RAG Engine]
    F --> G[LLM Interface]
    G --> H[User Interface]

Loading

🛠️ Technology Stack

Category	Technologies
Frontend
Backend
AI/ML
Vector Store
Version Control

📈 Performance

• Frontend: Streamlit
• Embeddings: Sentence Transformers
• Vector Store: Pinecone
• LLM: Google Gemini
• Code Processing: LangChain
• Version Control: Git

# Development workflow
git checkout -b feature/amazing-feature
git commit -m 'feat: add amazing feature'
git push origin feature/amazing-feature

👏 Acknowledgments

• LangChain for RAG implementation
• Pinecone for vector storage
• Google Gemini for AI capabilities
• Streamlit for the UI framework

📬 Contact & Support

• LinkedIn: Sheick

Made with ❤️ by Sheick | Copyright © 2024