AI glossary

What is RAG?

A technique that retrieves relevant documents at question time and gives them to the model, so it answers from your data with citations.

Introduced by Lewis et al. (2020). A RAG pipeline chunks, embeds and stores documents, then retrieves the best chunks for each question and grounds the answer in them.

▶Practice it hands-onBuilding a RAG Pipeline

Related terms

Embedding Vector Database Hybrid Search

← All 43 AI terms