Retrieval-Augmented Generation, or RAG, is a technique that makes AI answers more accurate by giving the model real information to work from. Instead of relying only on what it memorized during training, a RAG system first retrieves relevant documents (often using embeddings), then feeds them to the language model to generate an answer grounded in those sources.
This matters because it directly tackles two big weaknesses of language models: hallucinations and out-of-date knowledge. RAG is how tools answer questions about your own documents, a company's help center, or recent information the base model never saw. The answer is only as good as the retrieved sources, so quality of the underlying data still counts.