Glossary

What is Hybrid search?

Hybrid search is a search method that combines classic keyword search (for example BM25) with semantic vector search based on embeddings, and merges the results of both into one ranked list. It finds exact terms such as case numbers or legal sections as well as passages that express the same idea in different words.

In simple terms

Picture two librarians. One knows every word in the catalogue and instantly finds everything that contains exactly "Section 1295". The other understands what you are after and also brings books that cover your topic in other words. Each alone misses something. With hybrid search, you ask both at once and get a single list with the best hits from each at the top.

In the enterprise

At the engineering firm Muster & Partner, a technician searches for "ÖNORM B 1300" and for "owner's inspection duties". Pure vector search could easily miss the standard number; pure keyword search would miss the sections that talk about "checks by the building owner". Hybrid search merges both result lists. The technician gets the passages with the exact standard and the passages that match in meaning, in one list.

Related terms

Sources

  1. Microsoft Learn: Hybrid search using vectors and full text in Azure AI Search
  2. Elastic: What is hybrid search?

How we use this: UNID AI Second Brain · The second brain for your company's knowledge

← All terms

See it working on your own material.

In a 30-minute call we show the products live and work out which use case makes sense for you first. No obligation, in German or English, in Vienna or online.

UNID AI · Leonard-Bernstein-Straße 10 · 1220 Vienna · +43 660 476 30 89