RAG
In plain terms
Improving AI answers by retrieving relevant documents before generating.
Going deeper
Retrieval-Augmented Generation fetches information from a knowledge source and feeds it to the model as context, so answers stay grounded and current without retraining. It reduces hallucination.
Under the hood
Quality hinges on chunking, embedding choice, retrieval relevance, and reranking; it grounds answers and updates knowledge without retraining, but can still err on bad retrieval.
Examples
Chatbots over company docs, vector DB + LLM, semantic search, citation-backed Q&A.
Think of it like...
Like an open-book exam: instead of answering from memory alone, the student looks up the relevant pages first.