Verified65% confidenceFactExact time
RAG (Retrieval-Augmented Generation) typically comprises three core components: a vector database, a retriever (which recalls relevant document chunks based on cosine similarity), and a generator.
3
Sources
65%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
Related Claims
VerifiedThe core architecture of RAG is divided into three key stages: document preprocessing and vectorization, semantic retrieval, and augmented generation.83% similarVerifiedRAG（检索增强生成）技术架构将文档切片、向量化、存入向量数据库，查询时先检索相关片段再交给模型生成回答83% similarUnverifiedRAG (Retrieval-Augmented Generation) is collaboratively composed of three components: a vector database, an embedding model, and a generative model.83% similarUnverifiedRAG系统通常包含三个核心组件：文档索引、检索器和生成器，无需重新训练模型就能实时更新知识并降低幻觉率79% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501747API
curl https://kongchang.com/api/v1/knowledge/claims/501747MCP
get_claim(id=501747)