What is RAG?

Retrieval-Augmented GenerationiFull definition for retrieval-augmented generation (opens in a new tab)Fetching relevant context from an external data source as additional context to inform a language model's response. (RAG) is an approach that enhances the responses of LLMsiGo to glossary for large language model (opens in a new tab)A model trained on text to predict the next token, and so to generate language. by providing them with relevant, up-to-date information retrieved from external sources.

RAG helps generate more accurate and tailored answers, especially when the required information is not present in the model’s training data.