ContentSafetyEvaluator class abstract

Base class for evaluators that call the Azure AI Foundry Evaluation service to detect unsafe content.

Subclasses specify the annotation task name and the mapping from service metric names to the EvaluationMetric names returned to callers.

Implemented types

• Evaluator

Implementers

• CodeVulnerabilityEvaluator
• ContentHarmEvaluator
• GroundednessProEvaluator
• HateAndUnfairnessEvaluator
• IndirectAttackEvaluator
• ProtectedMaterialEvaluator
• SelfHarmEvaluator
• SexualEvaluator
• UngroundedAttributesEvaluator
• ViolenceEvaluator

Annotations

• @Source(name: 'ContentSafetyEvaluator.cs', namespace: 'Microsoft.Extensions.AI.Evaluation.Safety', repository: 'dotnet/extensions', path: 'src/Libraries/Microsoft.Extensions.AI.Evaluation.Safety/')

Constructors

ContentSafetyEvaluator({required ContentSafetyServiceConfiguration configuration, required String annotationTask, required Map<String, String> metricNames})

Creates a ContentSafetyEvaluator.

Properties

annotationTask → String

The annotation task name sent to the service.

final

configuration → ContentSafetyServiceConfiguration

Azure AI Foundry service configuration.

final

evaluationMetricNames → List<String>

The names of the EvaluationMetrics produced by this evaluator.

no setter, override

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

evaluate(Iterable<ChatMessage> messages, ChatResponse modelResponse, {ChatConfiguration? chatConfiguration, Iterable<EvaluationContext>? additionalContext, CancellationToken? cancellationToken}) → Future<EvaluationResult>

Evaluates modelResponse and returns an EvaluationResult.

override

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited