Concept
Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) is a technique that gives a text generator access to an external document store at inference time, so the model conditions its output on retrieved passages rather than relying only on what it memorized during training. Think of it like a…
The rest of “Retrieval-Augmented Generation” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→