Microsoft.Extensions.AI.Evaluation.Quality Namespace
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.
Contains evaluator classes that assess the quality of large language model (LLM) responses in an app according to various metrics.
Classes
| CoherenceEvaluator |
An IEvaluator that evaluates the 'Coherence' of a response produced by an AI model. |
| CompletenessEvaluator |
An IEvaluator that evaluates the 'Completeness' of a response produced by an AI model. |
| CompletenessEvaluatorContext |
Contextual information that the CompletenessEvaluator uses to evaluate the 'Completeness' of a response. |
| EquivalenceEvaluator |
An IEvaluator that evaluates the 'Equivalence' of a response produced by an AI model with another response supplied via GroundTruth. |
| EquivalenceEvaluatorContext |
Contextual information that the EquivalenceEvaluator uses to evaluate the 'Equivalence' of a response. |
| FluencyEvaluator |
An IEvaluator that evaluates the 'Fluency' of a response produced by an AI model. |
| GroundednessEvaluator |
An IEvaluator that evaluates the 'Groundedness' of a response produced by an AI model. |
| GroundednessEvaluatorContext |
Contextual information that the GroundednessEvaluator uses to evaluate the 'Groundedness' of a response. |
| IntentResolutionEvaluator |
An IEvaluator that evaluates an AI system's effectiveness at identifying and resolving user intent. |
| IntentResolutionEvaluatorContext |
Contextual information that the IntentResolutionEvaluator uses to evaluate an AI system's effectiveness at identifying and resolving user intent. |
| RelevanceEvaluator |
An IEvaluator that evaluates the 'Relevance' of a response produced by an AI model. |
| RelevanceTruthAndCompletenessEvaluator |
An IEvaluator that evaluates the 'Relevance', 'Truth' and 'Completeness' of a response produced by an AI model. |
| RetrievalEvaluator |
An IEvaluator that evaluates an AI system's performance in retrieving information for additional context in response to a user request (for example, in a Retrieval Augmented Generation (RAG) scenario). |
| RetrievalEvaluatorContext |
Contextual information that the RetrievalEvaluator uses to evaluate an AI system's performance in retrieving information for additional context. |
| TaskAdherenceEvaluator |
An IEvaluator that evaluates an AI system's effectiveness at adhering to the task assigned to it. |
| TaskAdherenceEvaluatorContext |
Contextual information that the TaskAdherenceEvaluator uses to evaluate an AI system's effectiveness at adhering to the task assigned to it. |
| ToolCallAccuracyEvaluator |
An IEvaluator that evaluates an AI system's effectiveness at using the tools supplied to it. |
| ToolCallAccuracyEvaluatorContext |
Contextual information that the ToolCallAccuracyEvaluator uses to evaluate an AI system's effectiveness at using the tools supplied to it. |
