Hybrid Search
Hybrid Search is an information retrieval approach that combines keyword-based retrieval (such as sparse retrieval methods like BM25) with vector-based dense semantic retrieval. By merging and re-ranking results from both methods, it captures the advantages of exact term matching and semantic similarity matching, compensating for the limitations of either approach alone in recall or semantic understanding. It is widely used in search engines, question-answering systems, and Retrieval-Augmented Generation (RAG) pipelines.
Core Facts
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
Hybrid retrieval typically merges results from two retrieval pipelines using a weighted combination via the RRF (Reciprocal Rank Fusion) algorithm.
Hybrid retrieval (combining dense vector retrieval with BM25 sparse retrieval) performs better than either method alone on most benchmarks.
Timeline (last 90 days)
Hybrid retrieval (RRF) combines semantic search with keyword search and, at the cost of slightly increased compute, delivers noticeably better retrieval quality over time.
Platforms such as Microsoft Azure AI Search and Elasticsearch already have built-in hybrid retrieval capabilities.
The Retriever is responsible for quickly recalling candidate passages from a large-scale document library, and common implementations include dense retrieval, sparse retrieval, and hybrid retrieval.
Semantic retrieval and keyword retrieval are often used together in mature RAG systems (hybrid retrieval), then results are optimized through a reranking model, to balance recall and precision.
Many retrieval systems run two paths in parallel, vector embeddings and BM25, and then merge the results, which is known as hybrid retrieval.
Production-grade RAG retrieval should adopt hybrid search, i.e., dense vectors plus sparse vectors plus reranking, rather than pure vector retrieval.
Hybrid retrieval outperforms pure keyword or pure vector approaches: keywords excel at exact matching, vectors excel at fuzzy recall, and the combination yields more stable recall and precision rates.
Memory retrieval should layer in time decay, importance weighting, and hybrid retrieval, rather than relying solely on vector similarity.
Hybrid Search, Re-ranking, and multi-path retrieval are advanced techniques in RAG.
NemoClaw's retrieval system adopts a hybrid strategy combining keyword matching and semantic similarity search.
2 more timeline events
All Facts (20)
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
90%VerifiedHybrid retrieval typically merges results from two retrieval pipelines using a weighted combination via the RRF (Reciprocal Rank Fusion) algorithm.
80%VerifiedHybrid retrieval (combining dense vector retrieval with BM25 sparse retrieval) performs better than either method alone on most benchmarks.
75%VerifiedHybrid Search combines Dense Retrieval with sparse retrieval (BM25).
75%VerifiedMemory retrieval should layer in time decay, importance weighting, and hybrid retrieval, rather than relying solely on vector similarity.
65%VerifiedHybrid 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.
65%VerifiedHybrid retrieval combines BM25 sparse retrieval with dense vector retrieval, merging ranking results via RRF or linear weighting.
65%VerifiedIn multiple real-world business scenarios, hybrid retrieval can improve recall accuracy by 15% to 30% compared to single retrieval methods.
65%UnverifiedHybrid retrieval combining vector similarity and keyword-based BM25 can significantly improve recall accuracy.
70%Unverified成熟的大厂RAG项目统一采用混合检索架构，不会单独使用向量检索
70%Partially VerifiedRAG系统的召回主要有两种方式：向量相似度计算和关键词匹配
65%UnverifiedHybrid Search fuses the results of dense vector retrieval and sparse BM25 retrieval.
60%UnverifiedIn actual production, hybrid retrieval combining both vector similarity and keyword matching is typically used.
60%UnverifiedHybrid retrieval (RRF) combines semantic search with keyword search and, at the cost of slightly increased compute, delivers noticeably better retrieval quality over time.
50%UnverifiedPlatforms such as Microsoft Azure AI Search and Elasticsearch already have built-in hybrid retrieval capabilities.
50%UnverifiedThe Retriever is responsible for quickly recalling candidate passages from a large-scale document library, and common implementations include dense retrieval, sparse retrieval, and hybrid retrieval.
50%UnverifiedSemantic retrieval and keyword retrieval are often used together in mature RAG systems (hybrid retrieval), then results are optimized through a reranking model, to balance recall and precision.
50%UnverifiedMany retrieval systems run two paths in parallel, vector embeddings and BM25, and then merge the results, which is known as hybrid retrieval.
50%UnverifiedProduction-grade RAG retrieval should adopt hybrid search, i.e., dense vectors plus sparse vectors plus reranking, rather than pure vector retrieval.
50%UnverifiedHybrid retrieval outperforms pure keyword or pure vector approaches: keywords excel at exact matching, vectors excel at fuzzy recall, and the combination yields more stable recall and precision rates.
50%