Unverified50% confidenceFactExact time
FTS5 默认使用 BM25 排序算法，综合考虑词频、逆文档频率和文档长度归一化
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedBM25 is a classic keyword retrieval algorithm based on term frequency statistics, which is complementary to vector retrieval.73% similarPartially VerifiedFTS5 is SQLite's fifth-generation full-text search extension module, supporting relevance ranking based on the BM25 algorithm, prefix queries, phrase matching, and other features.70% similarUnverified传统RAG依赖基于BM25算法的关键词稀疏检索和基于FAISS、Chroma等向量数据库的稠密向量检索69% similarVerifiedBM25是一种基于词频统计（TF-IDF改进版）的经典信息检索算法，属于稀疏检索方法69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/804542API
curl https://kongchang.com/api/v1/knowledge/claims/804542MCP
get_claim(id=804542)