# Semantic Search

> Search that matches on meaning rather than exact keywords, using embeddings to find passages whose sense is close to the query.

_The Agentic Web Lexicon · /glossary/semantic-search · [JSON](/api/glossary/semantic-search) · [all The Agentic Web Lexicon](/glossary)_

- **term:** Semantic Search
- **category:** optimization
- **short_def:** Search that matches on meaning rather than exact keywords, using embeddings to find passages whose sense is close to the query.
- **long_def:** Semantic search embeds both the query and the corpus into a vector space and retrieves by similarity, so 'how do I make my site readable to bots' can match a page titled 'agent-readiness' with no shared keywords. It is the retrieval backbone of RAG and the reason meaning-rich, well-structured content is found even without literal keyword overlap.
- **see_also:** embeddings, vector-database, rag
- **etymology_origin:** — (verify-against-primary-at-build)
- **related_to:** embeddings, vector-database, rag, reranking
- **contrast_with:** Unlike lexical (keyword) search that matches exact strings, semantic search matches meaning via embeddings — it can retrieve a relevant page that shares no words with the query.
- **example:** A query for 'stop AI bots scraping me' semantically matches a page about robots.txt and pay-per-crawl even though it never uses the word 'scraping'.
- **source:** https://en.wikipedia.org/wiki/Semantic_search
- **status:** active
- **why_it_matters:** Semantic search is how agents find your content by meaning; writing clear, entity-rich, self-contained passages is what makes you retrievable when the words don't match.
- **sameAs:** https://en.wikipedia.org/wiki/Semantic_search
- **bridge_entity:** rag
- **last_verified:** 2026-07-06
- **md_twin:** /glossary/semantic-search.md