Cosine distance

As explained in The Art of AI Product Development

Cosine distance measures the difference in orientation between two vectors and is commonly used to compare embeddings.

Cosine distance compares the orientation of two vectors. In semantic search, it estimates how relevant an embedded query is to embedded text by measuring their distance in embedding space. section 7.2.2

Applied in embedding-based retrieval:

• Embed the user query with the same embedding model used for the text chunks. section 7.2.2
• Retrieve the top-k text embeddings with the closest similarity; tune k because overly broad or narrow retrieval can hurt results. section 7.2.2
• Treat the score as an approximation of relevance, not a guarantee: embeddings can lose information from the original text. section 7.2.2

Semantic search

A retrieval system embeds a user query, compares it with stored text embeddings using cosine distance, and returns the most similar documents. A Weaviate search may still return irrelevant results, requiring evaluation and tuning. section 7.2.2

Figure 7.6 The process of semantic search

Trace how query embedding, similarity comparison, and top-k retrieval form a semantic-search pipeline. section 7.2.2

How The Art of AI Product Development covers it

How deep it goes

Explains query embedding, similarity-based top-k retrieval, tuning trade-offs, and information loss without deriving the mathematics.

Examples

Uses embedded queries, stored text chunks, top-k results, and Weaviate retrieval as concrete examples.

What it assumes

Assumes familiarity with embeddings and introduces their use for comparing queries with stored text representations.

What you can do after

Apply it via an embedding database while tuning retrieval breadth and evaluating relevance problems.

How it connects

Connects cosine distance with embeddings, semantic search, information retrieval, and retrieval-augmented generation.

liveBookmanning.com

Read The Art of AI Product Development on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Just Use Postgres!Cosine distance is a dissimilarity measure derived from the angle between two vectors, commonly defined as one minus cosine similarity.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionThe cosine distance metric measures the angular dissimilarity between vectors and is commonly used to estimate similarity in their encoded meanings.
• 

  liveBookmanning.com
  Software Testing with Generative AIA distance measure derived from the cosine of the angle between vectors, where a lower value indicates greater directional similarity.
• 

  liveBookmanning.com
  AI Agents in ActionCosine distance is a vector distance measure defined as one minus cosine similarity, ranging from zero for most similar vectors to two for semantically opposite vectors.
• 

  liveBookmanning.com
  AI Agents in Action, Second EditionCosine distance is a metric equal to one minus cosine similarity that measures angular dissimilarity between vectors.

Compare how 6 books explain cosine distance →

Related concepts

• cosine similarityequivalent to · Cosine similarity measures the directional alignment of two nonzero vectors as the cosine of the angle between them, equivalently their dot product divided by the product of their magnitudes.
• Euclidean distancealternative to · Euclidean distance is the straight-line distance between two points in Euclidean space, calculated as the square root of the sum of squared differences between corresponding coordinates.
• followed by operatorkind of · The PostgreSQL full-text search followed-by operator matches lexemes occurring in the specified positional sequence.
• Apache Commons Textused by · A Java library providing utilities for text processing, comparison, escaping, and related operations.
• similarity metricproduces · A similarity measure is a rule that quantifies or characterizes how alike two objects or representations are according to selected properties.

This explainer was generated by Manning's knowledge graph from the text of The Art of AI Product Development. The section links point to the parts of the book it draws on.