Unverified50% confidenceFactExact time
A common approach to relevance ranking is a TF-IDF/BM25-like weighted model that also considers field weights; MiniSearch allows configuring weights for different fields and supports applying different score coefficients to prefix-match and fuzzy-match results.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedHybrid Search combines dense vector semantic similarity with BM25 sparse keyword matching, with results from both paths re-ranked by a Re-Ranker model before being injected into the LLM context.71% similarUnverifiedFTS5 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71% similarUnverified单纯的向量语义检索对精确术语（如参数名、错误码）容易失准，推荐向量检索加关键词检索（BM25）的混合方案70% similarUnverifiedRanked retrieval typically relies on mechanisms such as BM25, bi-encoder models, or cross-encoders to place the most relevant documents at the top.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1051176API
curl https://kongchang.com/api/v1/knowledge/claims/1051176MCP
get_claim(id=1051176)