---
title: "Hybrid Search"
description: "Hybrid search combines lexical retrieval with semantic vector search to produce one ranked set of results. It is commonly used in Retrieval-Augmented Generation (RAG) because the two retrieval methods have complementary strengths."
canonical_url: "https://promptmetheus.com/resources/llm-knowledge-base/hybrid-search"
---

> Index of every page on this site: [llms.txt](https://promptmetheus.com/llms.txt)

Hybrid search combines lexical retrieval with semantic [vector search](https://promptmetheus.com/resources/llm-knowledge-base/vector-search) to produce one ranked set of results. It is commonly used in [Retrieval-Augmented Generation (RAG)](https://promptmetheus.com/resources/llm-knowledge-base/retrieval-augmented-generation-rag) because the two retrieval methods have complementary strengths.

Lexical search, often based on BM25 or a related term-frequency method, matches exact words and phrases. It performs well for identifiers, product codes, error messages, names, and rare terminology. Vector search compares [embeddings](https://promptmetheus.com/resources/llm-knowledge-base/vector-embedding) and can retrieve conceptually related documents even when they use different vocabulary.

A hybrid system runs both searches and combines their result lists. Fusion methods include:

- weighted normalization of lexical and vector scores;
- Reciprocal Rank Fusion, which combines result positions rather than raw scores;
- learned ranking models; and
- retrieving a broad union before applying a separate [reranker](https://promptmetheus.com/resources/llm-knowledge-base/reranking).

Raw lexical and vector scores usually have different distributions and should not be added without calibration. The optimal weighting also depends on the corpus and query type. A query containing an exact serial number may need stronger lexical weighting, while a conceptual question may benefit from semantic retrieval.

Metadata filtering, access control, chunking, and index freshness remain important. Hybrid retrieval cannot recover a document that was never indexed or is excluded by an incorrect filter.

For [agentic RAG](https://promptmetheus.com/resources/llm-knowledge-base/agentic-rag), the agent may select hybrid search for broad discovery and then refine results with additional queries or tools.

Google Cloud's [hybrid search documentation](https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/vector-search/about-hybrid-search) describes combining dense vector and sparse token embeddings for retrieval.

## Sitemap

See the full [sitemap](https://promptmetheus.com/sitemap.md) for all pages.