A fully-customized CustomMetric that can be used to evaluate a single model
by defining a metric function for a computation-based metric. The
CustomMetric is computed on the client-side using the user-defined metric
function in SDK only, not by the Vertex Gen AI Evaluation Service.
Attributes:
name: The name of the metric.
metric_function: The user-defined evaluation function to compute a metric
score. Must use the dataset row dictionary as the metric function
input and return per-instance metric result as a dictionary output.
The metric score must mapped to the name of the CustomMetric as key.
[[["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 2025-08-07 UTC."],[],[],null,["# Class CustomMetric (1.95.1)\n\nVersion latestkeyboard_arrow_down\n\n- [1.95.1 (latest)](/python/docs/reference/vertexai/latest/vertexai.evaluation.CustomMetric)\n- [1.94.0](/python/docs/reference/vertexai/1.94.0/vertexai.evaluation.CustomMetric)\n- [1.93.1](/python/docs/reference/vertexai/1.93.1/vertexai.evaluation.CustomMetric)\n- [1.92.0](/python/docs/reference/vertexai/1.92.0/vertexai.evaluation.CustomMetric)\n- [1.91.0](/python/docs/reference/vertexai/1.91.0/vertexai.evaluation.CustomMetric)\n- [1.90.0](/python/docs/reference/vertexai/1.90.0/vertexai.evaluation.CustomMetric)\n- [1.89.0](/python/docs/reference/vertexai/1.89.0/vertexai.evaluation.CustomMetric)\n- [1.88.0](/python/docs/reference/vertexai/1.88.0/vertexai.evaluation.CustomMetric)\n- [1.87.0](/python/docs/reference/vertexai/1.87.0/vertexai.evaluation.CustomMetric)\n- [1.86.0](/python/docs/reference/vertexai/1.86.0/vertexai.evaluation.CustomMetric)\n- [1.85.0](/python/docs/reference/vertexai/1.85.0/vertexai.evaluation.CustomMetric)\n- [1.84.0](/python/docs/reference/vertexai/1.84.0/vertexai.evaluation.CustomMetric)\n- [1.83.0](/python/docs/reference/vertexai/1.83.0/vertexai.evaluation.CustomMetric)\n- [1.82.0](/python/docs/reference/vertexai/1.82.0/vertexai.evaluation.CustomMetric)\n- [1.81.0](/python/docs/reference/vertexai/1.81.0/vertexai.evaluation.CustomMetric)\n- [1.80.0](/python/docs/reference/vertexai/1.80.0/vertexai.evaluation.CustomMetric)\n- [1.79.0](/python/docs/reference/vertexai/1.79.0/vertexai.evaluation.CustomMetric)\n- [1.78.0](/python/docs/reference/vertexai/1.78.0/vertexai.evaluation.CustomMetric)\n- [1.77.0](/python/docs/reference/vertexai/1.77.0/vertexai.evaluation.CustomMetric)\n- [1.76.0](/python/docs/reference/vertexai/1.76.0/vertexai.evaluation.CustomMetric)\n- [1.75.0](/python/docs/reference/vertexai/1.75.0/vertexai.evaluation.CustomMetric)\n- [1.74.0](/python/docs/reference/vertexai/1.74.0/vertexai.evaluation.CustomMetric)\n- [1.73.0](/python/docs/reference/vertexai/1.73.0/vertexai.evaluation.CustomMetric)\n- [1.72.0](/python/docs/reference/vertexai/1.72.0/vertexai.evaluation.CustomMetric)\n- [1.71.1](/python/docs/reference/vertexai/1.71.1/vertexai.evaluation.CustomMetric)\n- [1.70.0](/python/docs/reference/vertexai/1.70.0/vertexai.evaluation.CustomMetric)\n- [1.69.0](/python/docs/reference/vertexai/1.69.0/vertexai.evaluation.CustomMetric)\n- [1.68.0](/python/docs/reference/vertexai/1.68.0/vertexai.evaluation.CustomMetric)\n- [1.67.1](/python/docs/reference/vertexai/1.67.1/vertexai.evaluation.CustomMetric)\n- [1.66.0](/python/docs/reference/vertexai/1.66.0/vertexai.evaluation.CustomMetric)\n- [1.65.0](/python/docs/reference/vertexai/1.65.0/vertexai.evaluation.CustomMetric)\n- [1.63.0](/python/docs/reference/vertexai/1.63.0/vertexai.evaluation.CustomMetric)\n- [1.62.0](/python/docs/reference/vertexai/1.62.0/vertexai.evaluation.CustomMetric)\n- [1.60.0](/python/docs/reference/vertexai/1.60.0/vertexai.evaluation.CustomMetric)\n- [1.59.0](/python/docs/reference/vertexai/1.59.0/vertexai.evaluation.CustomMetric) \n\n CustomMetric(\n name: str,\n metric_function: typing.Callable[\n [typing.Dict[str, typing.Any]], typing.Dict[str, typing.Any]\n ],\n )\n\nThe custom evaluation metric.\n\nA fully-customized CustomMetric that can be used to evaluate a single model\nby defining a metric function for a computation-based metric. The\nCustomMetric is computed on the client-side using the user-defined metric\nfunction in SDK only, not by the Vertex Gen AI Evaluation Service.\n\nAttributes:\nname: The name of the metric.\nmetric_function: The user-defined evaluation function to compute a metric\nscore. Must use the dataset row dictionary as the metric function\ninput and return per-instance metric result as a dictionary output.\nThe metric score must mapped to the name of the CustomMetric as key.\n\nMethods\n-------\n\n### CustomMetric\n\n CustomMetric(\n name: str,\n metric_function: typing.Callable[\n [typing.Dict[str, typing.Any]], typing.Dict[str, typing.Any]\n ],\n )\n\nInitializes the evaluation metric."]]