AI Glossary
Retrieval-Augmented Generation (RAG)
Giving AI models access to your own data
Definition
RAG is a technique that combines a language model with a retrieval system — typically a vector database — to ground responses in specific documents or knowledge bases. Instead of relying solely on training data, the model retrieves relevant chunks of text at inference time and uses them as context. RAG is the foundation of most enterprise AI search and document Q&A tools.