Unverified50% confidenceFactExact time
BM25 requires global statistics (document frequency, average document length), so it usually needs support from a dedicated index structure, whereas PostgreSQL's built-in ts_rank lacks whole-database document frequency statistics.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFTS5 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69% similarUnverifiedPostgreSQL has a built-in tsvector for full-text search, along with plugins such as PGSearch that provide BM25-like capabilities.66% similarUnverifiedTraditional search systems mostly rely on statistical algorithms like TF-IDF or BM25 that rank results by term frequency and uniqueness in documents64% 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64% 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63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1080170API
curl https://kongchang.com/api/v1/knowledge/claims/1080170MCP
get_claim(id=1080170)