Cosine Distance. Defined as 1 - cosine similarity.
We strongly suggest using DOT_PRODUCT_DISTANCE + UNIT_L2_NORM instead
of COSINE distance. Our algorithms have been more optimized for
DOT_PRODUCT distance which, when combined with UNIT_L2_NORM, is
mathematically equivalent to COSINE distance and results in the same
ranking.
DotProductDistance
Dot Product Distance. Defined as a negative of the dot product.
[[["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 versioned documentation for the `DistanceMeasureType` enum within the Google Cloud AI Platform v1 API, specifically for the `.NET` library, with the latest version being 3.22.0."],["The `DistanceMeasureType` enum defines the different types of distance measures that can be used in nearest neighbor searches, which include `CosineDistance`, `DotProductDistance`, `SquaredL2Distance`, and `Unspecified`."],["Each version listed in the documentation provides access to the reference for the `DistanceMeasureType` enum within the `FeatureView.Types.IndexConfig.Types` class, for a total of 56 different versions listed."],["The documentation includes detailed descriptions of each distance measure type, clarifying their definitions and offering recommendations on which types to use, such as using `DOT_PRODUCT_DISTANCE` instead of `COSINE`."]]],[]]
