Glossary
What is Naive RAG? Definition and meaning
The basic pattern of embedding a question, fetching the nearest document chunks and giving them to a model as context.
Definition
Naive RAG: The basic pattern of embedding a question, fetching the nearest document chunks and giving them to a model as context.
In short: Retrieve chunks, then generate.
When it is used
A simple baseline for grounding answers in documents.
Learn more
The full guide to Naive RAG explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: Naive Bayes · Next term: NATS