Skip to main content
Deliberate AcademyProfessional AI Education
AI Glossary

RAG (Retrieval-Augmented Generation)

What is RAG (Retrieval-Augmented Generation)?

A technique that combines a language model with a search step, allowing the model to retrieve relevant documents before generating a response. Reduces hallucinations for factual queries.

Example in practice

A law firm's AI assistant that retrieves relevant case precedents from an internal document store before drafting a legal memo is using RAG — the response is grounded in real documents rather than model memory.