Retrieval-augmented generation, or RAG, is an architecture where a system retrieves external context and provides it to a model before generation. The goal is to make outputs more accurate, current, and grounded in source material than the model could produce from weights alone.
RAG quality depends on both retrieval and generation. If retrieval fails, the model may not have the information needed to answer. If generation fails, the model may ignore, misread, or overstate the retrieved context.