AI glossary

What is RAG?

Retrieval-augmented generation supplies retrieved material to a model when it answers.

A retrieval system finds potentially relevant documents or passages. The application includes them in the model’s context so the generated answer can use that material.

A practical example

A company help assistant can retrieve sections of an internal manual before explaining how to request equipment.

What to remember

RAG does not guarantee correctness. Retrieval can miss a relevant page, select outdated material or provide a passage that the model misinterprets.

Put it into practice

Use the answer-checking guide to keep evidence and uncertainty visible when working with AI.

Found something that needs updating?

Tools change quickly. Send a correction and include this page’s address.

Keep exploring.

View all