ModelRefs / Semantic Search — AI Glossary

Semantic Search — AI Glossary

Search that matches by meaning rather than keyword overlap, using embedding similarity to find relevant documents. Hybrid search combines both.

Overview

Semantic search retrieves documents whose embeddings are closest to the query embedding. Outperforms keyword search on paraphrase and concept queries; weaker on exact-match and rare-term recall. Hybrid search combines both.

Reference details

Topicrag
Last reviewed2026-06-24

Example: The query it gets wrong

“Documents that do not mention pricing” — semantic search returns documents about pricing, because negation barely registers in embedding space and the topic dominates. The same weakness explains why “increase” and “decrease” retrieve each other: they are about the same thing while meaning opposites.

Commonly confused with

Semantic search is the goal, not the technique. Dense bi-encoder retrieval is the usual implementation, but sparse methods like SPLADE also target meaning while staying sparse. Conflating the goal with one implementation hides that hybrid approaches exist.

When to use it

Reach for it when:

  • Users describe what they want rather than naming it
  • Vocabulary differs between query and document
  • Concept-level recall matters more than exact matching

Reach for something else when:

  • The query is an identifier, code or exact name
  • Negation or opposition must be distinguished
  • You need an auditable reason why a result was returned

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Semantic Search — AI Glossary.

Frequently asked questions

What is Semantic Search?

Search that matches by meaning rather than keyword overlap, using embedding similarity to find relevant documents.

What concepts are related to Semantic Search?

Closely related concepts include embedding, vector database, hybrid search, bm25.