Blog Studio Go to console

FirebaseVertexAI Framework Reference

SafetyRating

@available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
public struct SafetyRating : Equatable, Hashable, Sendable
 
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: HarmCategory

  • The model-generated probability that the content falls under the specified harm category.

    See HarmProbability for a list of possible values. This is a discretized representation of the probabilityScore.

    Important

    This does not indicate the severity of harm for a piece of content.

    Declaration

    Swift

    public let probability: HarmProbability

  • The confidence score that the response is associated with the corresponding harm category.

    The probability safety score is a confidence score between 0.0 and 1.0, rounded to one decimal place; it is discretized into a HarmProbability in probability. See probability scores in the Google Cloud documentation for more details.

    Declaration

    Swift

    public let probabilityScore: Float

  • The severity reflects the magnitude of how harmful a model response might be.

    See HarmSeverity for a list of possible values. This is a discretized representation of the severityScore.

    Declaration

    Swift

    public let severity: HarmSeverity

  • The severity score is the magnitude of how harmful a model response might be.

    The severity score ranges from 0.0 to 1.0, rounded to one decimal place; it is discretized into a HarmSeverity in severity. See severity scores in the Google Cloud documentation for more details.

    Declaration

    Swift

    public let severityScore: Float

  • If true, the response was blocked.

    Declaration

    Swift

    public let blocked: Bool

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

    Declaration

    Swift

    public init(category: HarmCategory,
            probability: HarmProbability,
            probabilityScore: Float,
            severity: HarmSeverity,
            severityScore: Float,
            blocked: Bool)

  • The probability that a given model output falls under a harmful content category.

    Note

    This does not indicate the severity of harm for a piece of content.

    Declaration

    Swift

    @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
public struct HarmProbability : DecodableProtoEnum, Hashable, Sendable

  • The magnitude of how harmful a model response might be for the respective HarmCategory.

    Declaration

    Swift

    @available(iOS 15.0, macOS 12.0, tvOS 15.0, watchOS 8.0, *)
public struct HarmSeverity : DecodableProtoEnum, Hashable, Sendable

Codable Conformances

  • Declaration

    Swift

    public init(from decoder: any Decoder) throws