Glossary
/// Definition
RAG (Retrieval-Augmented Generation)
RAG is an LLM architecture where the model retrieves relevant documents from an external index before generating an answer.
In depth
Retrieval-augmented generation (RAG) is a pattern where an LLM is grounded in an external knowledge base at inference time. The system embeds a user query, retrieves the top-k most relevant chunks from a vector index, and injects them into the prompt so the LLM's answer is grounded in real content rather than parametric memory. RAG dramatically reduces hallucination and enables private-data question-answering without fine-tuning.