Microsoft.Extensions.AI.Evaluation.Safety 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.

Classes

CodeVulnerabilityEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate code completion responses produced by an AI model for the presence of vulnerable code.
ContentHarmEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of a variety of harmful content such as violence, hate speech, etc.
ContentSafetyEvaluator	An `abstract` base class that can be used to implement IEvaluators that utilize the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of a variety of unsafe content such as protected material, vulnerable code, harmful content etc.
ContentSafetyServiceConfiguration	Specifies configuration parameters such as the Azure AI project that should be used, and the credentials that should be used, when a ContentSafetyEvaluator communicates with the Azure AI Foundry Evaluation service to perform evaluations.
ContentSafetyServiceConfigurationExtensions	Extension methods for ContentSafetyServiceConfiguration.
GroundednessProEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate the groundedness of responses produced by an AI model.
GroundednessProEvaluatorContext	Contextual information that the GroundednessProEvaluator uses to evaluate the groundedness of a response.
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.
IndirectAttackEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of indirect attacks such as manipulated content, intrusion and information gathering.
ProtectedMaterialEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for presence of protected material.
SelfHarmEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of content that indicates self harm.
SexualEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of sexual content.
UngroundedAttributesEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for presence of content that indicates ungrounded inference of human attributes.
UngroundedAttributesEvaluatorContext	Contextual information that the UngroundedAttributesEvaluator uses to evaluate whether a response is ungrounded.
ViolenceEvaluator	An IEvaluator that utilizes the Azure AI Foundry Evaluation service to evaluate responses produced by an AI model for the presence of violent content.