Retrieval-augmented generation makes a language model answer from your documents instead of its training memory. Before answering, the system searches your knowledge base for the relevant passages and hands them to the model as context. The answer cites your actual policies, prices and procedures — and can say "I don't know" when the documents don't cover it.
RAG is the standard architecture for a company assistant, and far cheaper than training a model. We detail the build in our guide to a chatbot on your own documents.