Unverified50% confidenceOpinionExact time
references 文件夹本质上是 RAG（检索增强生成）思想的一种静态化实现
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
Agent Skills入门：AI技能包的结构、原理与实战用法
Related Claims
Unverifiedreferences 目录采用显式打包的结构化文档，与 RAG（检索增强生成）动态检索向量片段的思路一脉相承但方式不同84% similarVerifiedThe core logic of RAG is to slice documents and store them as vectors, then retrieve relevant fragments through semantic similarity at query time and inject them into the context.72% 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68% similarUnverifiedRAG (Retrieval-Augmented Generation) introduces external memory during the inference phase to constrain the model's generation boundaries, by chunking documents, embedding them as vectors stored in a vector database, and retrieving relevant chunks to inject into the prompt at inference time.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/504045API
curl https://kongchang.com/api/v1/knowledge/claims/504045MCP
get_claim(id=504045)