🧠 LLM-Powered FAQ Assistant (RAG) This project is building an AI-powered FAQ assistant that answers user questions based on a custom document or knowledge base using Retrieval-Augmented Generation (RAG).

🚀 What It Is Doing The system is:

• Ingesting FAQ documents and structured text data
• Converting content into semantic embeddings using Hugging Face models
• Storing vectors in ChromaDB for efficient similarity search
• Retrieving relevant context based on user queries
• Generating grounded answers using an open-source LLM
• Serving responses through a simple Streamlit web interface

⚙️ Tech Stack

• Python
• Hugging Face Transformers
• Open-source LLMs
• ChromaDB (Vector Database)
• Streamlit

🎯 Purpose This assistant is helping users quickly navigate and query large FAQ or documentation sets by combining semantic search with LLM-based response generation.