How deeply does Machine Learning System Design cover similarity metric?

Separates vector generation and index querying, then specifies serving constraints without detailing the similarity calculation.

Similarity metric

As explained in Machine Learning System Design

Vector similarity is a measure of how closely two numerical vectors correspond in direction, distance, or another defined geometric relationship.

A similarity metric supports search by comparing a user-query vector with vectors representing searchable items. Production design separates vector generation and index querying because they have different operational constraints. section 15.5.2

Treat the two sides of vector similarity as separate serving paths:

Update the index in batches, including daily refreshes and on-demand creation or recreation after a core-model update. section 15.5.2
Query the index in real time, minimizing latency and preparing for uneven traffic and sudden peaks. section 15.5.2
Reuse one model, converted to ONNX, for batch and real-time inference when simplifying the design is valuable. section 15.5.2

Photo search

A photo-search service refreshes its index daily, supports on-demand reindexing, processes large item volumes, and handles query spikes of roughly 100 requests per second. section 15.5.2

How Machine Learning System Design covers it

liveBook manning.com

Read Machine Learning System Design on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Grokking Machine LearningA numerical measure of the closeness between two data points.
liveBook manning.com

AI-Powered SearchA similarity metric is a numerical measure that quantifies how closely two representations or objects correspond.
liveBook manning.com

Math and Architectures of Deep LearningA measure of how alike two represented items are, especially when computed from their vector representations.
liveBook manning.com

MongoDB 8.0 in Action, Third EditionA similarity score is a numeric measure of how closely a query vector matches a document vector embedding.
liveBook manning.com

Get Programming: Learn to code with PythonSimilarity is the degree to which two texts or other objects share comparable characteristics.
liveBook manning.com

Natural Language Processing in Action, Second EditionSimilarity is a numerical or qualitative measure of how closely two patterns or signals resemble each other.
liveBook manning.com

Data Without LabelsA similarity measure is a quantitative function that assesses how alike two data points, objects, or representations are.
liveBook manning.com

Transformers in ActionA similarity score is a numerical value indicating how closely two represented items align according to a specified similarity measure.
liveBook manning.com

Bayesian Optimization in ActionA similarity metric is a numerical rule for quantifying how similar two data points are.

Compare how 10 books explain similarity metric →

Related concepts

kernel functionincludes · A kernel function is a mathematical function that measures similarity between pairs of inputs, often representing an inner product in an implicit feature space.
recommender systemused by · A recommender system is software that predicts, selects, or ranks items, content, or actions for users based on available information about users, items, or context.
embeddinguses · A numerical vector representation of an item or input that encodes features or relationships useful for computational tasks.
similarity searchused by · Similarity search is a retrieval technique that finds or ranks items by comparing their representations with a query according to a similarity or distance measure.
cosine similarityincludes · 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.
distancemeasured by · Distance is a measure of separation between points or entities in a defined space or context.

This explainer was generated by Manning's knowledge graph from the text of Machine Learning System Design. The section links point to the parts of the book it draws on.