Verified90% confidenceFactTime unknown
混合检索（Hybrid Search）将向量检索与BM25关键词检索的结果通过RRF（倒数排名融合）等算法合并，兼顾语义理解与精确匹配
21
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHybrid 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.85% similarUnverifiedWeaviate和Elasticsearch的BM25+向量混合检索方案通过RRF算法合并两路结果，在语义相似性与词汇精确性之间取得平衡83% similarUnverifiedHybrid retrieval, which fuses BM25 keyword scores with vector similarity scores through weighted combination (typically using the RRF reciprocal rank fusion algorithm), has become the mainstream paradigm for RAG systems.83% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4285API
curl https://kongchang.com/api/v1/knowledge/claims/4285MCP
get_claim(id=4285)