Model Armor v1 API - Class RaiFilterResult (1.0.0-beta04) 

public sealed class RaiFilterResult : IMessage<RaiFilterResult>, IEquatable<RaiFilterResult>, IDeepCloneable<RaiFilterResult>, IBufferMessage, IMessage

Reference documentation and code samples for the Model Armor v1 API class RaiFilterResult.

Responsible AI Result.

Inheritance

object > RaiFilterResult

Namespace

Google.Cloud.ModelArmor.V1

Assembly

Google.Cloud.ModelArmor.V1.dll

Constructors

RaiFilterResult()

public RaiFilterResult()

RaiFilterResult(RaiFilterResult)

public RaiFilterResult(RaiFilterResult other)
Parameter
Name Description
other RaiFilterResult

Properties

ExecutionState

public FilterExecutionState ExecutionState { get; set; }

Output only. Reports whether the RAI filter was successfully executed or not.

Property Value
Type Description
FilterExecutionState

MatchState

public FilterMatchState MatchState { get; set; }

Output only. Overall filter match state for RAI. Value is MATCH_FOUND if at least one RAI filter confidence level is equal to or higher than the confidence level defined in configuration.

Property Value
Type Description
FilterMatchState

MessageItems

public RepeatedField<MessageItem> MessageItems { get; }

Optional messages corresponding to the result. A message can provide warnings or error details. For example, if execution state is skipped then this field provides related reason/explanation.

Property Value
Type Description
RepeatedFieldMessageItem

RaiFilterTypeResults

public MapField<string, RaiFilterResult.Types.RaiFilterTypeResult> RaiFilterTypeResults { get; }

The map of RAI filter results where key is RAI filter type - either of "sexually_explicit", "hate_speech", "harassment", "dangerous".

Property Value
Type Description
MapFieldstringRaiFilterResultTypesRaiFilterTypeResult