RAG - Retrieval-Augmented Generation
Version 1.0.0 · Updated 2026-07-30
CORE DEFINITION
Before asking AI to answer a question, first retrieve relevant information from an external knowledge base (such as your company's documents), then feed the retrieved information to AI as a 'cheat sheet', so that it generates answers based on these facts.
SCAFFOLDING EFFECT
Reduce cognitive load
An external hard drive for the brain. It solves the problem of AI 'confidently making up nonsense' (hallucination). For individuals, RAG metaphorically represents the separation of 'memory' and 'thinking' — do not try to memorize all knowledge (model parameters), but rather build an efficient retrieval system (external knowledge base).
Anchor fast decisions
RAG retrieves relevant documents from an external knowledge base before generation, then combines the retrieved content to answer, reducing hallucination and introducing traceable knowledge. Retrieve first, then answer.
MINIMUM ACTION
In progress 0/4Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- zh.wikipedia.orghttps://zh.wikipedia.org/wiki/%E6%AA%A2%E7%B4%A2%E5%A2%9E%E5%BC%B7%E7%94%9F%E6%88%90verified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS