COSINE distance compares vectors based on the angle between them, which
allows you to measure similarity that isn't based on the vectors
magnitude. We recommend using DOT_PRODUCT with unit normalized vectors
instead of COSINE distance, which is mathematically equivalent with
better performance. See Cosine
Similarity to learn
more about COSINE similarity and COSINE distance. The resulting
COSINE distance decreases the more similar two vectors are.
DotProduct
Similar to cosine but is affected by the magnitude of the vectors. See
Dot Product to learn more.
The resulting distance increases the more similar two vectors are.
Euclidean
Measures the EUCLIDEAN distance between the vectors. See
Euclidean to learn
more. The resulting distance decreases the more similar two vectors
are.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-03-21 UTC."],[[["This page provides documentation for the `StructuredQuery.Types.FindNearest.Types.DistanceMeasure` enum within the Firestore v1 API."],["The latest version of the documentation is for version 3.10.0, with older versions available dating back to version 2.3.0."],["The `DistanceMeasure` enum defines four fields: `Cosine`, `DotProduct`, `Euclidean`, and `Unspecified`, each with its specific use in comparing vectors."],["The `Cosine`, `DotProduct`, and `Euclidean` fields represent different methods for measuring the distance or similarity between vectors, each with links to Wikipedia for further explanation."],["The documentation is part of the Google Cloud Firestore v1 API, specifically within the `Google.Cloud.Firestore.V1` namespace, and is contained in the `Google.Cloud.Firestore.V1.dll` assembly."]]],[]]
