EvaluationContext class abstract

Base class for contextual information beyond the conversation history that an Evaluator may need to accurately evaluate a response.

Subclasses are free to add domain-specific properties. However, the contents list should always represent all contextual information as AIContent objects so that it can be serialized when recording results.

Implementers

• BLEUEvaluatorContext
• CompletenessEvaluatorContext
• EquivalenceEvaluatorContext
• F1EvaluatorContext
• GLEUEvaluatorContext
• GroundednessEvaluatorContext
• GroundednessProEvaluatorContext
• IntentResolutionEvaluatorContext
• RetrievalEvaluatorContext
• TaskAdherenceEvaluatorContext
• ToolCallAccuracyEvaluatorContext
• UngroundedAttributesEvaluatorContext

Annotations

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

Constructors

EvaluationContext(String name, {List<AIContent>? contents, String? text})

Creates an EvaluationContext with the given name and optional contents.

Properties

contents ↔ List<AIContent>

All contextual information decomposed into AIContent objects.

getter/setter pair

hashCode → int

The hash code for this object.

no setter, inherited

name ↔ String

The name of this context, used as the key in metric context maps.

getter/setter pair

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

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