# Hybrid Search

AI Glossary · Retrieval & RAG
Canonical URL: https://aisat.uk/glossary/hybrid-search
Author: Lucy Gilmore, Assistant General Counsel, Product, Privacy & AI at Sprinklr | Practical Privacy, Product & AI Governance & Defensible Risk Decisions (https://www.linkedin.com/in/lucy-gilmore/)
Breadcrumb: [Glossary](https://aisat.uk/glossary) > [Retrieval & RAG](https://aisat.uk/glossary?category=rag) > Hybrid Search

## TL;DR

> **Hybrid search** is a retrieval technique that combines sparse lexical keyword matching (such as BM25) with dense semantic vector search in a single query pipeline, merging and reranking both result sets to deliver high recall on both exact identifiers and conceptual queries.

## How Hybrid Search works in practice

Dense vector search and classic keyword search fail in opposite ways. Vector embeddings capture synonyms and conceptual intent ('how do I reset my credentials'), but smear out exact tokens such as part numbers (`SKU-9941-B`), statutory references (`Section 75 Consumer Credit Act`), acronyms, and stack-trace error codes. Conversely, sparse lexical algorithms like BM25 score exact term frequency and inverse document frequency with pinpoint precision, but miss relevant documents that use different phrasing.

A hybrid search pipeline executes both queries in parallel against the corpus. The lexical leg scores sparse token matches while the vector leg retrieves top semantic neighbours using ANN search. A fusion algorithm, most commonly Reciprocal Rank Fusion (RRF) or weighted score normalisation, merges the two candidate lists into a unified ranking. In production RAG pipelines, the top 20 to 50 fused results are then passed to a cross-encoder reranker model, which inspects the full query-passage pairs together to order the final five chunks sent to the LLM.

For example, a UK engineering parts distributor implemented hybrid search + reranking across 800,000 technical datasheets, lifting top-5 retrieval recall from 68 per cent (vector-only) to 91 per cent across mixed natural-language and part-number queries.

## Why it matters and trade-offs

Switching from naive vector-only search to hybrid search with a cross-encoder reranker is consistently the highest-ROI architectural upgrade in enterprise RAG. It eliminates the frustrating failure mode where a user pastes an exact policy code, postcode, or customer reference into an AI assistant and gets back vaguely related boilerplate instead of the exact record.

The trade-off is a modest increase in storage footprint (maintaining both an inverted lexical index and an HNSW vector index) and 50 to 150 milliseconds of added latency if a neural reranker stage is included. Because almost every major search store (Postgres with `pgvector` + full-text search, Elasticsearch, Qdrant, Weaviate, and Pinecone) now supports hybrid retrieval natively, it should be the default baseline for production RAG.

## Related AI concepts

- [Retrieval-Augmented Generation (RAG)](https://aisat.uk/glossary/retrieval-augmented-generation): Retrieval-Augmented Generation (RAG) is an AI architecture that retrieves relevant passages from external documents or databases at query time and injects them into a language model's context window to generate cited, grounded answers.
- [Vector Database](https://aisat.uk/glossary/vector-database): A Vector Database is a specialised storage engine, such as pgvector, Qdrant, Pinecone or Weaviate, built to index high-dimensional vector embeddings using approximate nearest-neighbour graphs and execute low-latency similarity queries alongside metadata filters.
- [Embeddings (Vector Embeddings)](https://aisat.uk/glossary/embeddings): Embeddings (Vector Embeddings) are dense arrays of floating-point numbers generated by an embedding model to represent the semantic meaning of text, code, images or audio so conceptually related items sit close together in vector space.
- [Evals (Evaluations)](https://aisat.uk/glossary/evals): Evals (Evaluations) are automated, repeatable testing pipelines that score an AI application's outputs against a golden dataset using deterministic assertions, reference metrics and LLM-as-a-judge rubrics before any prompt or model change ships.