Retrieval-Augmented Generation
Retrieval-Augmented Generation, or RAG, finds outside evidence at run time. It gives that evidence to a model before writing.
Another example
A policy assistant finds the newest handbook sections and cites them in its answer.
Main parts
- 01User intent and context
- 02Model or tool decision
- 03Grounded result and fallback
Use it when
Use RAG for changing or private knowledge that can be indexed and linked to a source.
Do not use it when
Never treat RAG as fine-tuning. RAG supplies evidence; it doesn't change model weights.
Name used in code
retrieve → rerank → generate Before you ship
Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback.
Outcome: Use or evaluate Retrieval-Augmented Generation to make AI behavior measurable and tied to evidence. User context: A policy assistant finds the newest handbook sections and cites them in its answer. AI method or concept: Retrieval-Augmented Generation. Why it fits: Use RAG for changing or private knowledge that can be indexed and linked to a source. Do not use it when: Never treat RAG as fine-tuning. RAG supplies evidence; it doesn't change model weights. AI requirements: Define the input and source evidence. Set model and tool permissions. Use versioned evaluation data and measures. Define failure, decline-to-answer, privacy, speed, and cost limits. Operational safeguards: Keep a clear trace and hide sensitive log data. Show users a safe fallback. Mark steps that need human review. Define how to roll back the model or prompt. Acceptance criteria: Record baseline and target measures on a versioned evaluation set. Test edge cases and hostile inputs. Verify fallback, monitoring, permissions, and rollback. Evidence and limits (evidence boundary): No single official standard controls the whole term. Its meaning may change across teams, platforms, or frameworks. Unknowns to confirm: Target task, model and version, evaluation owner, source data, risk limit, tool permissions, and production fallback.
Check this request
Review the current use of Retrieval-Augmented Generation. Definition: Retrieval-Augmented Generation, or RAG, finds outside evidence at run time. It gives that evidence to a model before writing. Release checks: Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback. Before changing code, report the evidence you found, gaps, severity, and the smallest safe fix.