Unverified50% confidenceSolutionExact time
父子块策略将文档同时索引为大块和小块，检索时用小块精准定位，生成时返回大块提供完整上下文
1
Sources
50%
Confidence
Long-term
Relevance
7/25/2026
First Seen
Sources
RAG检索增强生成详解：原理、工作流程与核心优势
bilibiliAI小公举-timi7/9/2026
Related Claims
VerifiedRAG通过将文档切分为语义块后经嵌入模型转化为高维向量存入向量数据库，查询时通过近似最近邻（ANN）搜索找到语义最相近的文档片段70% 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.68% similarUnverifiedThe biggest bottleneck when scaling context is historical tool outputs, including text chunks from past retrievals, tool call and result pairs, and file search records.68% similarVerifiedRAG addresses the limitation of large models' knowledge cutoff dates by splitting private documents into text chunks, converting them into vector representations stored in a vector database, and injecting retrieved relevant content into the Prompt.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/615569API
curl https://kongchang.com/api/v1/knowledge/claims/615569MCP
get_claim(id=615569)