# Semantic Search

> Search that finds text by what it means, not by its exact words.

**Field:** Artificial Intelligence  
**Category:** Retrieval & Search  
**Also known as:** Meaning-Based Search, Vector Search (Semantic)

## Think of it like

Think of it like a friend who knows what you mean. You can use the wrong words, and they still get it.

## Definition

Semantic search finds text by its meaning rather than by matching the exact words. The question and every stored text are turned into embeddings. The texts whose embeddings sit closest to the question come back first. So a search for 'fix a flat tyre' can find a page about 'mending a punctured wheel'. It is weaker on exact names, codes and rare terms, which is where keyword search does better.

## Example

Jack's staff search the help pages for 'can't get into my account'. Semantic search returns the 'reset your password' page, though the words differ.

## Why it matters

People rarely use the same words as the page that answers them. Semantic search closes that gap.

## Common mistake

Using it alone for part numbers or names. It can miss 'XJ-200' because the meaning of a code is not in its words.

## Three principles

- **Meaning, not words.** Matches ideas.
- **Built on embeddings.** Closest vectors first.
- **Weak on exact codes.** Pair it with keywords.

## Related terms

- [Keyword Search](https://learn.benibix.com/term/ai/keyword-search)
- [Hybrid Search](https://learn.benibix.com/term/ai/hybrid-search)
- [Embedding (AI)](https://learn.benibix.com/term/ai/embedding)
- [Nearest Neighbor Search](https://learn.benibix.com/term/ai/nearest-neighbor-search)
- [Dense Vector](https://learn.benibix.com/term/ai/dense-vector)

## Told apart from

- [Semantic Search vs Keyword Search](https://learn.benibix.com/compare/semantic-search-vs-keyword-search): People often think semantic search is just a smarter keyword search that wins every time. Keyword search matches the exact words, so it is best at names, codes and rare terms. Semantic search matches meaning, so it finds the same idea in other words. Each misses what the other finds. That is why most good systems run both.
- [RAG vs Semantic Search](https://learn.benibix.com/compare/rag-vs-semantic-search): People often think RAG is just semantic search. Semantic search only finds the passages that match a question by meaning. RAG is the whole system: a search finds the passages, then a language model reads them and writes the answer. The search inside RAG can be semantic, keyword or both.

![A question about fixing a flat tyre. Keyword search finds nothing, since no words match. Semantic search finds a page about mending a punctured wheel.](https://learn.benibix.com/diagrams/rt-semantic-search.svg)

---

Source: https://learn.benibix.com/term/ai/semantic-search
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-18
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
