What is RAG?
Retrieval-augmented generation retrieves relevant documents from an organisation's own data and supplies them to a language model so answers are grounded in, and can cite, those sources.
Retrieval-augmented generation fetches relevant passages from your own documents or databases at question time and gives them to the model as context, so answers are grounded in your data rather than the model's memory. Quality depends mostly on retrieval: how documents are split, indexed and searched, and whether the right passage is found. Evaluate retrieval separately from generation, and show sources so users can check answers.