{
  "dataset": "glossary",
  "record": {
    "id": "semantic-search",
    "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": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://en.wikipedia.org/wiki/Semantic_search — established IR term predating LLMs; embedding-based revival is recent"
    },
    "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"
  }
}