Retrieval-Augmented Generation

Retrieval-Augmented Generation, usually shortened to RAG, is a common way to make a language model answer using your own data. Instead of relying only on what the model learned during training, the system first retrieves the most relevant passages from a document store and adds them to the prompt, so the model can ground its answer in those sources.

RAG is the backbone of most “chat with your documents” tools. As context windows grow, some simple cases can skip it — but for large or frequently changing knowledge bases, retrieval remains the practical approach.