# Hybrid search (retrieval)

**Source:** https://promtable.com/glossary/hybrid-search

> Hybrid search combines dense vector retrieval with sparse keyword (BM25) retrieval, then fuses the two ranked lists — the production retrieval default for RAG in 2026.

---
Hybrid search combines dense vector retrieval with sparse keyword (BM25) retrieval, then fuses the two ranked lists — the production retrieval default for RAG in 2026.

Pure vector search misses exact-match queries (product SKUs, error codes, named entities). Pure keyword search misses semantic intent. Hybrid combines them — typically retrieve top 50-100 from each, fuse with reciprocal rank fusion (RRF) or weighted score, then re-rank the top 20-30 with a cross-encoder. Empirically beats both single approaches on production corpora. By 2026 hybrid retrieval is the default in serious RAG stacks (Cohere Rerank pipeline, Voyage AI Rerank, Pinecone hybrid, Weaviate hybrid, Vespa).

## When to use

- Any production RAG over diverse corpora.
- Mixed query types (some keyword-heavy, some semantic).

## Common mistakes

- Fusing scores directly across normalisation regimes — use RRF or rank-based fusion.
- Skipping the re-ranker — first-stage fusion is noisy.

## Related terms

- [rag](https://promtable.com/glossary/rag)
- [semantic-search](https://promtable.com/glossary/semantic-search)
- [embeddings](https://promtable.com/glossary/embeddings)
- [vector-database](https://promtable.com/glossary/vector-database)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/hybrid-search
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/hybrid-search".
Contact: info@vibecodingturkey.com.