Retrieval-Augmented Generation (RAG).

An AI technique that improves language model responses by fetching relevant, up-to-date information from an external database before generating an answer.

Retrieval-Augmented Generation (RAG) bridges the gap between a language model’s static training data and dynamic real-world knowledge. When a user asks a question, the system first retrieves factual documents from a vector database. It then feeds this context to the language model, which generates a highly accurate, grounded response. This reduces hallucinations and allows organizations to use AI securely with their private data.