RelevanceTruthAndCompletenessEvaluator class

Evaluates an AI response on three dimensions — Relevance, Truth, and Completeness — in a single model call, returning one NumericMetric per dimension (each scored 1–5).

Requires a ChatConfiguration; unlike other quality evaluators this one asks the model to respond with a JSON object rather than XML score tags.

Implemented types

• Evaluator

Annotations

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

Constructors

RelevanceTruthAndCompletenessEvaluator()

Properties

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

Constants

completenessMetricName → const String

The name of the Completeness NumericMetric returned by this evaluator.

relevanceMetricName → const String

The name of the Relevance NumericMetric returned by this evaluator.

truthMetricName → const String

The name of the Truth NumericMetric returned by this evaluator.