Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation (RAG) is an AI technique that retrieves relevant information from an external knowledge source at query time and feeds it to a large language model as context before it generates an answer. By grounding output in current, authoritative data, RAG improves accuracy, reduces hallucinations, and lets models use information beyond their training cutoff without retraining. It underpins many AI search and assistant products that cite their sources.

Source: cloud.google.com