public sealed class AutoraterConfig : IMessage<AutoraterConfig>, IEquatable<AutoraterConfig>, IDeepCloneable<AutoraterConfig>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class AutoraterConfig.
The configs for autorater. This is applicable to both EvaluateInstances and
EvaluateDataset.
Optional. Default is true. Whether to flip the candidate and baseline
responses. This is only applicable to the pairwise metric. If enabled, also
provide PairwiseMetricSpec.candidate_response_field_name and
PairwiseMetricSpec.baseline_response_field_name. When rendering
PairwiseMetricSpec.metric_prompt_template, the candidate and baseline
fields will be flipped for half of the samples to reduce bias.
[[["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 2025-08-14 UTC."],[[["\u003cp\u003eThis document provides reference documentation for the \u003ccode\u003eAutoraterConfig\u003c/code\u003e class within the Vertex AI v1beta1 API, which is used for configuring autoraters for both \u003ccode\u003eEvaluateInstances\u003c/code\u003e and \u003ccode\u003eEvaluateDataset\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eAutoraterConfig\u003c/code\u003e class inherits from \u003ccode\u003eobject\u003c/code\u003e and implements several interfaces, including \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, enabling various functionalities like message handling, comparison, deep cloning, and buffered messaging.\u003c/p\u003e\n"],["\u003cp\u003eKey properties of \u003ccode\u003eAutoraterConfig\u003c/code\u003e include \u003ccode\u003eAutoraterModel\u003c/code\u003e for specifying the model or endpoint, \u003ccode\u003eFlipEnabled\u003c/code\u003e to enable response flipping for pairwise metrics, and \u003ccode\u003eSamplingCount\u003c/code\u003e to define the number of samples per dataset instance, with a default of 4 if not specified.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eAutoraterConfig\u003c/code\u003e class is found within the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1Beta1\u003c/code\u003e namespace, contained in the \u003ccode\u003eGoogle.Cloud.AIPlatform.V1Beta1.dll\u003c/code\u003e assembly, and includes constructors for creating new instances either empty or based on an existing config.\u003c/p\u003e\n"],["\u003cp\u003eThe class has several inherited members from \u003ccode\u003eobject\u003c/code\u003e, such as \u003ccode\u003eGetHashCode()\u003c/code\u003e, \u003ccode\u003eGetType()\u003c/code\u003e, and \u003ccode\u003eToString()\u003c/code\u003e, which provide standard object functionalities, and also details if \u003ccode\u003eFlipEnabled\u003c/code\u003e and \u003ccode\u003eSamplingCount\u003c/code\u003e properties are set via \u003ccode\u003eHasFlipEnabled\u003c/code\u003e and \u003ccode\u003eHasSamplingCount\u003c/code\u003e properties.\u003c/p\u003e\n"]]],[],null,[]]