LLM Reference
Concepts & capability filters
technique

RAG (Retrieval Augmented Generation)

Retrieval Augmented Generation (RAG) retrieves relevant documents and adds them to the prompt so the model answers from your data instead of parametric memory, reducing hallucination on knowledge tasks.

Category
technique
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • Its quality depends on retrieval more than the model; the tradeoffs to weigh are retrieval relevance, added latency and token cost, and keeping the source index fresh.