RAG Giving an LLM access to knowledge it was never trained on: the retrieval pipeline, its building blocks, and the production fixes that keep it accurate.
01 RAG The retrieval pipeline Ask a company chatbot "what's our refund policy for annual plans?" and it hits a wall: the answer lives in a document the model has never read. A large language model (LLM) answers from what training froze into it, so it does one of two things — admits it doesn't know, or invents something fluent, confident and wrong. That second failure is a hallucination, and it is the expensive one, because nothing in the answer looks wrong. → 02 Production RAG Where retrieval breaks The naive pipeline — chunk, embed, store, search, stuff into a prompt — demos well. Point it at a real company's documentation and it degrades in four specific, repeatable ways. None of them is exotic; all four are consequences of the design choices the simple version makes. →