FirebaseVertexAI Framework Reference

SafetyRating

@available(iOS 15.0, macOS 11.0, *)
public struct SafetyRating : Equatable, Hashable
extension SafetyRating: Decodable

A type defining potentially harmful media categories and their model-assigned ratings. A value of this type may be assigned to a category for every model-generated response, not just responses that exceed a certain threshold.

  • The category describing the potential harm a piece of content may pose. See HarmCategory for a list of possible values.

    Declaration

    Swift

    public let category: SafetySetting.HarmCategory

  • The model-generated probability that a given piece of content falls under the harm category described in HarmCategory. This does not indicate the severity of harm for a piece of content. See HarmProbability for a list of possible values.

    Declaration

    Swift

    public let probability: HarmProbability

  • Initializes a new SafetyRating instance with the given category and probability. Use this initializer for SwiftUI previews or tests.

    Declaration

    Swift

    public init(category: SafetySetting.HarmCategory, probability: HarmProbability)

  • The probability that a given model output falls under a harmful content category. This does not indicate the severity of harm for a piece of content.

    Declaration

    Swift

    public enum HarmProbability : String
    extension SafetyRating.HarmProbability: Codable