RAG, or Retrieval-Augmented Generation, is a technique where an AI model is given relevant documents or data at query time, rather than relying solely on what it memorized during training. When you ask a question, a retrieval system first finds the most relevant chunks of text from a database, then passes those chunks to the model as context alongside your question.

The reason RAG is so popular is that it solves a core limitation of LLMs: their knowledge is frozen at training time. RAG lets apps stay current without retraining, and it gives the model specific, trustworthy source material to reason from — reducing hallucinations. It's the backbone of most enterprise AI tools, document assistants, and customer support bots you encounter today.