This project aims to build a functional real-time chat application enhanced with Retrieval-Augmented Generation (RAG), demonstrating how to combine WebSockets with AI-driven information retrieval and generation for live conversations.

This project is broken down into the following units. See each unit's README for details:

1. Unit 1: RAG Fundamentals & Basic Demo - ✅ Complete! Basic RAG implementation with document processing, embedding generation, and query answering. (See demo output)
2. Unit 2: Real-Time WebSocket Chat - ✅ Complete! Built a functional real-time chat server and client with Socket.IO. (See demo output)
3. Unit 3: Integrating RAG with Real-Time Chat - (TBA) Focuses on combining RAG (Unit 1) with the chat system (Unit 2).
4. Unit 4: Advanced RAG Techniques & Optimization - (TBA) Explores improvements to the RAG pipeline.
5. Unit 5: User Interface Enhancements - (TBA) Focuses on improving the chat UI/UX.
6. Unit 6: Deployment & Scalability - (TBA) Covers preparing the application for deployment.

Initial Setup: Run npm install in the root directory and create a .env file with your OPENAI_API_KEY.