CrawlCheck
Glossary · Retrieval engineering

Cosine similarity

A comparison of vector direction that largely ignores magnitude.

What Cosine similarity does not show

A high score means geometric closeness under one embedding model, not that two passages state the same fact.

Terms this definition uses

embedding

Related terms in Retrieval engineering

How pages become chunks, vectors and candidates inside an answer engine, and why being retrieved is not being cited.

Corpus · Document ingestion · Data connector · Parsing · OCR · Layout-aware parsing · Semantic chunking · Fixed-size chunking · Chunk overlap · Parent-child retrieval · Metadata filtering · Vector database · Vector index · Sparse vector · Dense vector · Dot-product similarity · Approximate nearest neighbor · HNSW · Top-k · Retrieval recall · Retrieval precision · Mean reciprocal rank · Normalized discounted cumulative gain · Relevance score · Candidate generation · Query rewriting · Query expansion · HyDE · Multi-query retrieval · Reciprocal rank fusion · Late interaction · Lexical retrieval · Semantic search · Exact-match retrieval · Freshness boosting · Authority weighting · Source diversity · Deduplication · Near-duplicate detection · Semantic cache · Retrieval latency · Retrieval cutoff · Citation mapping · Answer synthesis

Questions about Cosine similarity

What is Cosine similarity?

A comparison of vector direction that largely ignores magnitude.

What does Cosine similarity not show or guarantee?

A high score means geometric closeness under one embedding model, not that two passages state the same fact.

Which area of the glossary does Cosine similarity belong to?

Retrieval engineering: How pages become chunks, vectors and candidates inside an answer engine, and why being retrieved is not being cited.

← Dense vector  ·  Dot-product similarity →

See it in the full glossary · 772 terms across 19 areas.

Free browser extension

See this on any site you visit, in one click.

CrawlCheck for Chrome grades every site you visit A–F and shows, from your own browser, what search engines and AI assistants are actually served. Free, no account.