What is RAG (retrieval-augmented generation)?

Retrieval-augmented generation (RAG) is an AI technique that retrieves relevant information from trusted sources before generating a response. By combining retrieved data with a language model, RAG helps produce answers that are more accurate, current, and grounded.

Example: An accounting assistant retrieves information from a company's ledger before answering a question about monthly revenue instead of relying only on its training data.

Related terms: Grounding, Model Context, Large Language Model (LLM), Hallucination