HateAndUnfairnessEvaluator Class

Reference

Definition

Namespace:: Microsoft.Extensions.AI.Evaluation.Safety

Assembly:: Microsoft.Extensions.AI.Evaluation.Safety.dll

Package:: Microsoft.Extensions.AI.Evaluation.Safety v9.5.0-preview.1.25265.7

Source:: HateAndUnfairnessEvaluator.cs

Important

Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.

An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of content that is hateful or unfair.

public ref class HateAndUnfairnessEvaluator sealed : Microsoft::Extensions::AI::Evaluation::Safety::ContentHarmEvaluator

public sealed class HateAndUnfairnessEvaluator : Microsoft.Extensions.AI.Evaluation.Safety.ContentHarmEvaluator

type HateAndUnfairnessEvaluator = class
    inherit ContentHarmEvaluator

Public NotInheritable Class HateAndUnfairnessEvaluator
Inherits ContentHarmEvaluator

Inheritance: Object

ContentSafetyEvaluator

ContentHarmEvaluator
HateAndUnfairnessEvaluator

Remarks

HateAndUnfairnessEvaluator returns a NumericMetric with a value between 0 and 7, with 0 indicating an excellent score, and 7 indicating a poor score.

Note that HateAndUnfairnessEvaluator can detect harmful content present within both image and text based responses. Supported file formats include JPG/JPEG, PNG and GIF. Other modalities such as audio and video are currently not supported.

Constructors

HateAndUnfairnessEvaluator()

An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of content that is hateful or unfair.

Properties

EvaluationMetricNames	Gets the Names of the EvaluationMetrics produced by this IEvaluator. (Inherited from ContentSafetyEvaluator)
HateAndUnfairnessMetricName	Gets the Name of the NumericMetric returned by HateAndUnfairnessEvaluator.

Methods

EvaluateAsync(IEnumerable<ChatMessage>, ChatResponse, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	(Inherited from ContentHarmEvaluator)
EvaluateContentSafetyAsync(IChatClient, IEnumerable<ChatMessage>, ChatResponse, IEnumerable<EvaluationContext>, String, Boolean, CancellationToken)	Evaluates the supplied `modelResponse` using the Azure AI Foundry Evaluation Service and returns an EvaluationResult containing one or more EvaluationMetrics. (Inherited from ContentSafetyEvaluator)
FilterAdditionalContext(IEnumerable<EvaluationContext>)	Filters the EvaluationContexts supplied by the caller via `additionalContext` down to just the EvaluationContexts that are relevant to the evaluation being performed by this ContentSafetyEvaluator. (Inherited from ContentSafetyEvaluator)

Extension Methods

EvaluateAsync(IEvaluator, ChatMessage, ChatMessage, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	Evaluates the supplied `modelResponse` and returns an EvaluationResult containing one or more EvaluationMetrics.
EvaluateAsync(IEvaluator, ChatMessage, ChatResponse, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	Evaluates the supplied `modelResponse` and returns an EvaluationResult containing one or more EvaluationMetrics.
EvaluateAsync(IEvaluator, ChatMessage, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	Evaluates the supplied `modelResponse` and returns an EvaluationResult containing one or more EvaluationMetrics.
EvaluateAsync(IEvaluator, ChatResponse, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	Evaluates the supplied `modelResponse` and returns an EvaluationResult containing one or more EvaluationMetrics.
EvaluateAsync(IEvaluator, String, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	Evaluates the supplied `modelResponse` and returns an EvaluationResult containing one or more EvaluationMetrics.
EvaluateAsync(IEvaluator, String, String, ChatConfiguration, IEnumerable<EvaluationContext>, CancellationToken)	Evaluates the supplied `modelResponse` and returns an EvaluationResult containing one or more EvaluationMetrics.

Applies to

通过