RAG Chatbot

A retrieval-augmented generation chatbot that answers questions from a custom knowledge base using embeddings and LangChain.

Features

• Document ingestion with configurable chunking
• FAISS vector store for fast similarity search
• LLM-powered response generation with source citations
• Interactive CLI interface

Setup

pip install -r requirements.txt
cp .env.example .env  # Add your OpenAI API key

Usage

python main.py ingest
python main.py query "How does the life support system work?"

Interactive Demo

Try the browser-based RAG pipeline visualizer to see how the pipeline works step-by-step.