# What is Hybrid Search? Definition & Technical Mechanics

> **Source:** [SPIDITS AI AI Glossary](https://spidits.com/ai-glossary)  
> **Category:** Information Retrieval  
> **Canonical Citation:** [https://spidits.com/ai-glossary/hybrid-search](https://spidits.com/ai-glossary/hybrid-search)

## Definition
Hybrid Search is a retrieval technique that combines dense vector search (semantic similarity) with sparse keyword search (BM25 lexical matching). By merging their results, it captures both high-level meaning and precise keyword matches.

## Architectural Mechanics & Deep Dive
Hybrid Search is an advanced retrieval strategy that combines the strengths of dense vector search and sparse lexical search. Dense search uses embeddings to capture semantic concepts and synonyms, while sparse search uses BM25 to match exact keywords and unique identifiers. By merging and ranking their respective results using Reciprocal Rank Fusion, hybrid search optimizes retrieval precision and recall.

## Industry Applications & Real-World Use Cases
RAG database indexing, enterprise document search, and product catalog filtering

## Frequently Asked Questions

### Why combine dense and sparse search?
Dense search is great for understanding synonyms and intent, but bad at matching exact IDs, product codes, or rare jargon where sparse search excels.

### How are hybrid search results merged?
Commonly using Reciprocal Rank Fusion (RRF), which scores documents based on their rank positions in both search lists.

## Related Terminology
- [semantic-search](https://spidits.com/ai-glossary/semantic-search)
- [bm25](https://spidits.com/ai-glossary/bm25)
- [vector-database](https://spidits.com/ai-glossary/vector-database)

---
*From the SPIDITS AI Knowledge Base (300+ terms indexed). Explore full technical definitions: [https://spidits.com/ai-glossary](https://spidits.com/ai-glossary)*