Package software.amazon.awssdk.services.bedrock.model

Class GuardrailContentFilterConfig

  • All Implemented Interfaces:
    Serializable, SdkPojo, ToCopyableBuilder<GuardrailContentFilterConfig.Builder,​GuardrailContentFilterConfig>
    @Generated("software.amazon.awssdk:codegen")
public final class GuardrailContentFilterConfig
extends Object
implements SdkPojo, Serializable, ToCopyableBuilder<GuardrailContentFilterConfig.Builder,​GuardrailContentFilterConfig>

    Contains filter strengths for harmful content. Guardrails support the following content filters to detect and filter harmful user inputs and FM-generated outputs.

    • Hate – Describes language or a statement that discriminates, criticizes, insults, denounces, or dehumanizes a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).

    • Insults – Describes language or a statement that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.

    • Sexual – Describes language or a statement that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.

    • Violence – Describes language or a statement that includes glorification of or threats to inflict physical pain, hurt, or injury toward a person, group or thing.

    Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.

    For more information, see Guardrails content filters.

    See Also:
    Serialized Form

    • Method Detail

      • inputStrength

        public final GuardrailFilterStrength inputStrength()

        The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

        If the service returns an enum value that is not available in the current SDK version, inputStrength will return GuardrailFilterStrength.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from inputStrengthAsString().

        Returns:
        The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
        See Also:
        GuardrailFilterStrength

      • inputStrengthAsString

        public final String inputStrengthAsString()

        The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

        If the service returns an enum value that is not available in the current SDK version, inputStrength will return GuardrailFilterStrength.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from inputStrengthAsString().

        Returns:
        The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
        See Also:
        GuardrailFilterStrength

      • outputStrength

        public final GuardrailFilterStrength outputStrength()

        The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

        If the service returns an enum value that is not available in the current SDK version, outputStrength will return GuardrailFilterStrength.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from outputStrengthAsString().

        Returns:
        The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
        See Also:
        GuardrailFilterStrength

      • outputStrengthAsString

        public final String outputStrengthAsString()

        The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.

        If the service returns an enum value that is not available in the current SDK version, outputStrength will return GuardrailFilterStrength.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from outputStrengthAsString().

        Returns:
        The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
        See Also:
        GuardrailFilterStrength

      • inputModalities

        public final List<GuardrailModality> inputModalities()

        The input modalities selected for the guardrail content filter configuration.

        Attempts to modify the collection returned by this method will result in an UnsupportedOperationException.

        This method will never return null. If you would like to know whether the service returned this field (so that you can differentiate between null and empty), you can use the hasInputModalities() method.

        Returns:
        The input modalities selected for the guardrail content filter configuration.

      • hasInputModalities

        public final boolean hasInputModalities()
        For responses, this returns true if the service returned a value for the InputModalities property. This DOES NOT check that the value is non-empty (for which, you should check the isEmpty() method on the property). This is useful because the SDK will never return a null collection or map, but you may need to differentiate between the service returning nothing (or null) and the service returning an empty collection or map. For requests, this returns true if a value for the property was specified in the request builder, and false if a value was not specified.

      • inputModalitiesAsStrings

        public final List<String> inputModalitiesAsStrings()

        The input modalities selected for the guardrail content filter configuration.

        Attempts to modify the collection returned by this method will result in an UnsupportedOperationException.

        This method will never return null. If you would like to know whether the service returned this field (so that you can differentiate between null and empty), you can use the hasInputModalities() method.

        Returns:
        The input modalities selected for the guardrail content filter configuration.

      • outputModalities

        public final List<GuardrailModality> outputModalities()

        The output modalities selected for the guardrail content filter configuration.

        Attempts to modify the collection returned by this method will result in an UnsupportedOperationException.

        This method will never return null. If you would like to know whether the service returned this field (so that you can differentiate between null and empty), you can use the hasOutputModalities() method.

        Returns:
        The output modalities selected for the guardrail content filter configuration.

      • hasOutputModalities

        public final boolean hasOutputModalities()
        For responses, this returns true if the service returned a value for the OutputModalities property. This DOES NOT check that the value is non-empty (for which, you should check the isEmpty() method on the property). This is useful because the SDK will never return a null collection or map, but you may need to differentiate between the service returning nothing (or null) and the service returning an empty collection or map. For requests, this returns true if a value for the property was specified in the request builder, and false if a value was not specified.

      • outputModalitiesAsStrings

        public final List<String> outputModalitiesAsStrings()

        The output modalities selected for the guardrail content filter configuration.

        Attempts to modify the collection returned by this method will result in an UnsupportedOperationException.

        This method will never return null. If you would like to know whether the service returned this field (so that you can differentiate between null and empty), you can use the hasOutputModalities() method.

        Returns:
        The output modalities selected for the guardrail content filter configuration.

      • inputAction

        public final GuardrailContentFilterAction inputAction()

        Specifies the action to take when harmful content is detected. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        If the service returns an enum value that is not available in the current SDK version, inputAction will return GuardrailContentFilterAction.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from inputActionAsString().

        Returns:
        Specifies the action to take when harmful content is detected. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        See Also:
        GuardrailContentFilterAction

      • inputActionAsString

        public final String inputActionAsString()

        Specifies the action to take when harmful content is detected. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        If the service returns an enum value that is not available in the current SDK version, inputAction will return GuardrailContentFilterAction.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from inputActionAsString().

        Returns:
        Specifies the action to take when harmful content is detected. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        See Also:
        GuardrailContentFilterAction

      • outputAction

        public final GuardrailContentFilterAction outputAction()

        Specifies the action to take when harmful content is detected in the output. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        If the service returns an enum value that is not available in the current SDK version, outputAction will return GuardrailContentFilterAction.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from outputActionAsString().

        Returns:
        Specifies the action to take when harmful content is detected in the output. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        See Also:
        GuardrailContentFilterAction

      • outputActionAsString

        public final String outputActionAsString()

        Specifies the action to take when harmful content is detected in the output. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        If the service returns an enum value that is not available in the current SDK version, outputAction will return GuardrailContentFilterAction.UNKNOWN_TO_SDK_VERSION. The raw value returned by the service is available from outputActionAsString().

        Returns:
        Specifies the action to take when harmful content is detected in the output. Supported values include:

        • BLOCK – Block the content and replace it with blocked messaging.

        • NONE – Take no action but return detection information in the trace response.

        See Also:
        GuardrailContentFilterAction

      • inputEnabled

        public final Boolean inputEnabled()

        Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

        Returns:
        Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

      • outputEnabled

        public final Boolean outputEnabled()

        Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

        Returns:
        Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

      • hashCode

        public final int hashCode()
        Overrides:
        hashCode in class Object

      • equals

        public final boolean equals​(Object obj)
        Overrides:
        equals in class Object

      • toString

        public final String toString()
        Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be redacted from this string using a placeholder value.
        Overrides:
        toString in class Object

      • getValueForField

        public final <T> Optional<T> getValueForField​(String fieldName,
                                              Class<T> clazz)