Interface GuardrailManagedWordsConfig.Builder

All Superinterfaces:
Buildable, CopyableBuilder<GuardrailManagedWordsConfig.Builder,GuardrailManagedWordsConfig>, SdkBuilder<GuardrailManagedWordsConfig.Builder,GuardrailManagedWordsConfig>, SdkPojo
Enclosing class:
GuardrailManagedWordsConfig
@Mutable @NotThreadSafe public static interface GuardrailManagedWordsConfig.Builder extends SdkPojo, CopyableBuilder<GuardrailManagedWordsConfig.Builder,GuardrailManagedWordsConfig>

  • Method Details

    • type

      GuardrailManagedWordsConfig.Builder type(String type)

      The managed word type to configure for the guardrail.

      Parameters:
      type - The managed word type to configure for the guardrail.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • type

      GuardrailManagedWordsConfig.Builder type(GuardrailManagedWordsType type)

      The managed word type to configure for the guardrail.

      Parameters:
      type - The managed word type to configure for the guardrail.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • inputAction

      GuardrailManagedWordsConfig.Builder inputAction(String inputAction)

      Specifies the action to take when harmful content is detected in the input. 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.

      Parameters:
      inputAction - Specifies the action to take when harmful content is detected in the input. 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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • inputAction

      GuardrailManagedWordsConfig.Builder inputAction(GuardrailWordAction inputAction)

      Specifies the action to take when harmful content is detected in the input. 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.

      Parameters:
      inputAction - Specifies the action to take when harmful content is detected in the input. 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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • outputAction

      GuardrailManagedWordsConfig.Builder outputAction(String 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • outputAction

      GuardrailManagedWordsConfig.Builder outputAction(GuardrailWordAction 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.

      Parameters:
      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.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:

    • inputEnabled

      GuardrailManagedWordsConfig.Builder inputEnabled(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.

      Parameters:
      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:
      Returns a reference to this object so that method calls can be chained together.

    • outputEnabled

      GuardrailManagedWordsConfig.Builder outputEnabled(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.

      Parameters:
      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:
      Returns a reference to this object so that method calls can be chained together.