Definition
Retrieval-augmented generation (RAG)
Retrieval-augmented generation, or RAG, is a pattern where a system retrieves relevant source material before asking a model to generate an answer. The model is still generative, but the answer is grounded in selected documents, records, or knowledge-base passages.
Last updated: 25 June 2026
Why it matters
RAG can reduce hallucination and make AI useful on private knowledge, but only if retrieval quality is measured.
Signals to watch
- Source passages are retrieved
- Answers cite or use documents
- Bad retrieval causes bad answers