> ## Documentation Index
> Fetch the complete documentation index at: https://wiki.platelunchcollective.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Cosine Similarity

> Cosine similarity is a mathematical measure of the angle between two vectors in a high-dimensional space — used by AI retrieval systems to determine how sema...

*Technical implementation* · *AI Search Infrastructure*

## Definition

Cosine similarity is a mathematical measure of the angle between two vectors in a high-dimensional space — used by AI retrieval systems to determine how semantically similar a query is to a piece of content. A cosine similarity of 1 indicates identical meaning; 0 indicates no relationship.

## Why It Matters for AI Search

Cosine similarity is a key computation used to determine whether your content is retrieved in response to a query. Two documents can share no keywords and still have high cosine similarity if they are semantically related — and two documents can share many keywords but have low cosine similarity if they mean different things in context. Understanding this explains why semantic relevance outperforms keyword density as a content strategy.

## Related Terms

<CardGroup cols={2}>
  <Card title="Embedding" href="/ai-search-glossary/embedding" />

  <Card title="Vector database" href="/ai-search-glossary/vector-database" />

  <Card title="Semantic search" href="/ai-search-glossary/semantic-search" />

  <Card title="Dense retrieval" href="/ai-search-glossary/dense-retrieval" />

  <Card title="Word embedding" href="/ai-search-glossary/word-embedding" />
</CardGroup>

## Relevant Plate Lunch Collective Services

[AI SEO](https://www.platelunchcollective.com/services/ai-seo)