Retrieval augmented generation (RAG)
Also known as: RAG
Definition
Retrieval augmented generation is a technique in which a system retrieves relevant documents and gives them to a language model to use when writing an answer.
Why it matters
RAG is how many AI search products keep answers current and cite sources. Being retrievable, and clear enough to quote, matters for brand visibility.
Example
A search assistant fetches several pages, then writes a summary with links to them.
Related terms
Concepts
Grounding
Grounding is connecting an AI model's answer to external sources, such as search results, so that claims can be supported and cited.
Concepts
Large language model (LLM)
A large language model is an AI system trained on very large amounts of text to predict and generate language.
Platforms
Query fan-out
Query fan-out is when an AI search system breaks one question into several related sub-queries, runs them and combines the results into one answer.
What is Retrieval augmented generation?
Retrieval augmented generation is a technique in which a system retrieves relevant documents and gives them to a language model to use when writing an answer.
Why does retrieval augmented generation matter?
RAG is how many AI search products keep answers current and cite sources. Being retrievable, and clear enough to quote, matters for brand visibility.
See these terms measured on your brand.
Start with a first audit. We show where you appear, who is named instead, and what to fix first.