Retrieval-augmented generation (RAG)

Retrieval-augmented generation is a technique where a model retrieves relevant documents from a knowledge source and uses them to ground its response. Rather than relying only on what the model learned during training, it answers from material supplied at query time, which allows citation and keeps answers current.

RAG is how most enterprise AI systems answer questions about a specific organization. The model itself has no knowledge of your policies or customers; retrieval supplies that at the moment of the question.

In an enterprise setting the hard part is not retrieval quality but permissions. Retrieval has to respect who is allowed to see what, enforced at the retrieval layer rather than in the interface, or the system becomes an efficient way to reach documents a user could not otherwise open.