Chat With Your Documents Data Ingestion & RAG Pipeline(Beginner Friendly)

In this video, we build the complete data ingestion and RAG pipeline so your chatbot can read Markdown files, PDF files,docs and CSV files— with accurate answers and sources. In this video, we build the core of a RAG chatbot — the data ingestion and retrieval pipeline. You’ll learn how to: ✅ Load PDFs, TXT, DOCX, CSV, and Markdown files ✅ Split documents into chunks ✅ Create embeddings ✅ Store data in ChromaDB (vector database) ✅ Retrieve relevant chunks ✅ Use them in a RAG pipeline to answer questions accurately This is a step-by-step beginner tutorial using: Groq (LLM) LangChain FastAPI ChromaDB Streamlit 👉 This video is part of the Customer Support RAG Chatbot series.