What is Retrieval augmented generation (RAG)?
Retrieval augmented generation (RAG) is a technique where an AI model retrieves relevant documents from a knowledge source and uses them to ground its answer. It lets a model give accurate, up-to-date, source-backed responses about information it was not trained on, such as your company's own documents.
RAG reduces hallucination by giving the model real, relevant text to work from instead of relying only on memory. It is how most "chat with your documents" tools work under the hood.
Put the theory to work.
Kognitaa teaches these ideas by doing, on real tasks in Claude. The free Foundations level costs nothing.
Related terms