Codebase Intelligence

A Retrieval-Augmented Generation (RAG) application for intelligent codebase analysis. Upload any GitHub repository and get instant AI-powered insights, summaries, and context-aware Q&A about your code through semantic search and vector embeddings.

Features

• Repository Analysis: Automatically analyze GitHub repositories and extract meaningful insights
• Project Summarization: Generate AI-powered summaries including tech stack, architecture patterns, and code statistics
• RAG-Powered Chat: Ask natural language questions and receive context-aware answers by retrieving relevant code snippets and augmenting LLM prompts
• Vector Embeddings: Uses Pinecone vector database for semantic search and efficient code context retrieval

Tech Stack

Frontend & Backend

• Next.js 14 - React framework with App Router and API routes
• React 19 - UI framework
• TypeScript - Type safety
• Tailwind CSS - Styling
• Zod - Runtime type validation

AI & Vector Database (RAG Stack)

• LangChain - Document loading, chunking, and LLM orchestration
• Pinecone - Vector database for semantic search and retrieval
• OpenAI - GPT-4o for generation, text-embedding-3-small for retrieval

Getting Started

Prerequisites

• Node.js 18+
• Git
• OpenAI API key
• Pinecone API key
• GitHub Personal Access Token

Installation

1. Clone the repository:

git clone <repository-url>
cd codebase-intelligence

2. Install dependencies:

npm install

3. Set up environment variables:

cp .env.local

Development

Start the Next.js development server:

npm run dev

The application will be available at http://localhost:3000

RAG Pipeline

The application implements a three-stage RAG workflow:

1. Ingestion (/api/ingest): Loads GitHub repository files, chunks them into semantic segments, generates vector embeddings, and stores them in Pinecone with metadata
2. Summarization (/api/summarize): Retrieves code context vectors and augments GPT-4o prompts to generate architecture summaries and tech stack analysis
3. Conversation (/api/chat): For each user query, retrieves relevant code context from Pinecone and augments the LLM prompt to provide accurate, code-informed responses

Build

npm run build

Validation

• Zod Schemas for request validation across all endpoints
• Type-safe API responses with TypeScript inference
• Client-side validation before API calls

Contributing

This project is open source and contributions are welcome! Feel free to open issues, submit pull requests, or suggest improvements.