NodpickWhat is RAG?
Also: Retrieval-augmented generation
Retrieval-augmented generation (RAG) is a technique where an AI system first retrieves relevant documents, for example from a search index, and then generates an answer using them. It reduces reliance on training data and lets answers include current information and source links.
How it works
A user question is turned into one or more search queries. The system retrieves matching passages, adds them to the model's input and asks the model to write an answer based on them. The quality of the retrieved sources largely determines the quality of the answer.
What it means for you
To be named, your content has to be retrievable and clearly relevant to the question. Pages that answer the exact question early and plainly are easier to retrieve and to quote.
Related terms
Be first when Nodpick opens
Nodpick opens soon. Join the waitlist for early access and the launch price.