---
title: Semantic Search — AI Glossary
description: Semantic search retrieves content by meaning rather than exact keyword match, comparing embedding vectors of the query and documents to find conceptually related results. It surfaces relevant material even when wording differs, complementing traditional lexical search that depends on shared terms.
canonical: https://prompeteer.ai/glossary/semantic-search
---

# Semantic Search

Semantic search retrieves content by meaning rather than exact keyword match, comparing embedding vectors of the query and documents to find conceptually related results. It surfaces relevant material even when wording differs, complementing traditional lexical search that depends on shared terms.

## Definition

Keyword search matches literal terms and misses paraphrases or synonyms. Semantic search instead embeds both query and documents into a shared vector space and ranks by vector similarity, so a query about "car" can retrieve passages about "automobiles." This is powered by embedding models and a vector database for fast nearest-neighbor lookup.

In practice semantic and keyword search are often combined into hybrid retrieval, since each catches cases the other misses. Semantic search is a building block of retrieval-augmented generation, providing the relevant context that grounds a model's answers.

## Sources

- [Karpukhin et al. (2020), Dense Passage Retrieval for Open-Domain Question Answering](https://arxiv.org/abs/2004.04906)
- [OpenAI — Embeddings guide (semantic search)](https://platform.openai.com/docs/guides/embeddings)

## Related terms

- [embedding](https://prompeteer.ai/glossary/embedding)
- [vector-database](https://prompeteer.ai/glossary/vector-database)
- [retrieval-augmented-generation](https://prompeteer.ai/glossary/retrieval-augmented-generation)
- [reranking](https://prompeteer.ai/glossary/reranking)