Chat With Your Documents (RAG Chatbot with Sources) | Beginner Friendly|Part 1- Intro+Setup

In this video, we start building a RAG Chatbot that can answer customer support questions using your own documents — with sources/citations like RefundPolicy.md. This is the Part 1 of the full series where we will build the complete project using: ✅ Groq (LLM) ✅ LangChain (RAG pipeline) ✅ FastAPI (Backend API) ✅ Streamlit (Chat UI) ✅ ChromaDB (Vector Database) 🎯 In this part i have: Demo the final chatbot Understand what RAG is (simple explanation) Create the full project folder structure Setup Python virtual environment + install dependencies Build a FastAPI backend with a /health endpoint Test in Swagger UI (/docs) Run FastAPI backend: uvicorn backend.app:app --reload --port 8001 ✅ Test API: http://127.0.0.1:8001/health http://127.0.0.1:8001/docs 🔥 Part 2 Coming Next In the next video, we will build ingestion: ✅ Load files from Data/ ✅ Chunk documents ✅ Store embeddings in ChromaDB ✅ Verify what’s stored in the vector database ⭐ If this helped you ✅ Like the video ✅ Subscribe for Part 2 ✅ Comment “RAG” and I’ll share the full repo link 🔗 Useful Links Git Hub Link: https://github.com/chethannj/CSA_RAG_Chatbot Groq: https://groq.com/ FastAPI: https://fastapi.tiangolo.com/ Streamlit: https://streamlit.io/ LangChain: https://www.langchain.com/ ChromaDB: https://www.trychroma.com/ #RAG #LangChain #Groq #Streamlit #FastAPI #ChromaDB #Chroma #VectorDatabase #AIChatbot #CustomerSupport #GenAI #LLM