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

Interface GuardrailContentFilter.Builder

All Superinterfaces:

Buildable, CopyableBuilder<GuardrailContentFilter.Builder,GuardrailContentFilter>, SdkBuilder<GuardrailContentFilter.Builder,GuardrailContentFilter>, SdkPojo

Enclosing class:

GuardrailContentFilter

@Mutable
@NotThreadSafe
public static interface GuardrailContentFilter.Builder
extends SdkPojo, CopyableBuilder<GuardrailContentFilter.Builder,GuardrailContentFilter>

Method Summary

Modifier and Type	Method	Description
GuardrailContentFilter.Builder	inputAction(String inputAction)	The action to take when harmful content is detected in the input.
GuardrailContentFilter.Builder	inputAction(GuardrailContentFilterAction inputAction)	The action to take when harmful content is detected in the input.
GuardrailContentFilter.Builder	inputEnabled(Boolean inputEnabled)	Indicates whether guardrail evaluation is enabled on the input.
GuardrailContentFilter.Builder	inputModalities(Collection<GuardrailModality> inputModalities)	The input modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	inputModalities(GuardrailModality... inputModalities)	The input modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	inputModalitiesWithStrings(String... inputModalities)	The input modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	inputModalitiesWithStrings(Collection<String> inputModalities)	The input modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	inputStrength(String inputStrength)	The strength of the content filter to apply to prompts.
GuardrailContentFilter.Builder	inputStrength(GuardrailFilterStrength inputStrength)	The strength of the content filter to apply to prompts.
GuardrailContentFilter.Builder	outputAction(String outputAction)	The action to take when harmful content is detected in the output.
GuardrailContentFilter.Builder	outputAction(GuardrailContentFilterAction outputAction)	The action to take when harmful content is detected in the output.
GuardrailContentFilter.Builder	outputEnabled(Boolean outputEnabled)	Indicates whether guardrail evaluation is enabled on the output.
GuardrailContentFilter.Builder	outputModalities(Collection<GuardrailModality> outputModalities)	The output modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	outputModalities(GuardrailModality... outputModalities)	The output modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	outputModalitiesWithStrings(String... outputModalities)	The output modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	outputModalitiesWithStrings(Collection<String> outputModalities)	The output modalities selected for the guardrail content filter.
GuardrailContentFilter.Builder	outputStrength(String outputStrength)	The strength of the content filter to apply to model responses.
GuardrailContentFilter.Builder	outputStrength(GuardrailFilterStrength outputStrength)	The strength of the content filter to apply to model responses.
GuardrailContentFilter.Builder	type(String type)	The harmful category that the content filter is applied to.
GuardrailContentFilter.Builder	type(GuardrailContentFilterType type)	The harmful category that the content filter is applied to.

Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder

copy

Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder

applyMutation, build

Methods inherited from interface software.amazon.awssdk.core.SdkPojo

equalsBySdkFields, sdkFieldNameToField, sdkFields

Method Detail

type

GuardrailContentFilter.Builder type(String type)

The harmful category that the content filter is applied to.

Parameters:

type - The harmful category that the content filter is applied to.

Returns:

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

See Also:

GuardrailContentFilterType, GuardrailContentFilterType

type

GuardrailContentFilter.Builder type(GuardrailContentFilterType type)

The harmful category that the content filter is applied to.

Parameters:

type - The harmful category that the content filter is applied to.

Returns:

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

See Also:

GuardrailContentFilterType, GuardrailContentFilterType

inputStrength

GuardrailContentFilter.Builder inputStrength(String 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.

Parameters:

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.

Returns:

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

See Also:

GuardrailFilterStrength, GuardrailFilterStrength

inputStrength

GuardrailContentFilter.Builder inputStrength(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.

Parameters:

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.

Returns:

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

See Also:

GuardrailFilterStrength, GuardrailFilterStrength

outputStrength

GuardrailContentFilter.Builder outputStrength(String 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.

Parameters:

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.

Returns:

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

See Also:

GuardrailFilterStrength, GuardrailFilterStrength

outputStrength

GuardrailContentFilter.Builder outputStrength(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.

Parameters:

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.

Returns:

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

See Also:

GuardrailFilterStrength, GuardrailFilterStrength

inputModalitiesWithStrings

GuardrailContentFilter.Builder inputModalitiesWithStrings(Collection<String> inputModalities)

The input modalities selected for the guardrail content filter.

Parameters:

inputModalities - The input modalities selected for the guardrail content filter.

Returns:

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

inputModalitiesWithStrings

GuardrailContentFilter.Builder inputModalitiesWithStrings(String... inputModalities)

The input modalities selected for the guardrail content filter.

Parameters:

inputModalities - The input modalities selected for the guardrail content filter.

Returns:

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

inputModalities

GuardrailContentFilter.Builder inputModalities(Collection<GuardrailModality> inputModalities)

The input modalities selected for the guardrail content filter.

Parameters:

inputModalities - The input modalities selected for the guardrail content filter.

Returns:

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

inputModalities

GuardrailContentFilter.Builder inputModalities(GuardrailModality... inputModalities)

The input modalities selected for the guardrail content filter.

Parameters:

inputModalities - The input modalities selected for the guardrail content filter.

Returns:

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

outputModalitiesWithStrings

GuardrailContentFilter.Builder outputModalitiesWithStrings(Collection<String> outputModalities)

The output modalities selected for the guardrail content filter.

Parameters:

outputModalities - The output modalities selected for the guardrail content filter.

Returns:

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

outputModalitiesWithStrings

GuardrailContentFilter.Builder outputModalitiesWithStrings(String... outputModalities)

The output modalities selected for the guardrail content filter.

Parameters:

outputModalities - The output modalities selected for the guardrail content filter.

Returns:

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

outputModalities

GuardrailContentFilter.Builder outputModalities(Collection<GuardrailModality> outputModalities)

The output modalities selected for the guardrail content filter.

Parameters:

outputModalities - The output modalities selected for the guardrail content filter.

Returns:

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

outputModalities

GuardrailContentFilter.Builder outputModalities(GuardrailModality... outputModalities)

The output modalities selected for the guardrail content filter.

Parameters:

outputModalities - The output modalities selected for the guardrail content filter.

Returns:

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

inputAction

GuardrailContentFilter.Builder inputAction(String inputAction)

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 - 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:

GuardrailContentFilterAction, GuardrailContentFilterAction

inputAction

GuardrailContentFilter.Builder inputAction(GuardrailContentFilterAction inputAction)

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 - 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:

GuardrailContentFilterAction, GuardrailContentFilterAction

outputAction

GuardrailContentFilter.Builder outputAction(String outputAction)

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 - 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:

GuardrailContentFilterAction, GuardrailContentFilterAction

outputAction

GuardrailContentFilter.Builder outputAction(GuardrailContentFilterAction outputAction)

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 - 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:

GuardrailContentFilterAction, GuardrailContentFilterAction

inputEnabled

GuardrailContentFilter.Builder inputEnabled(Boolean inputEnabled)

Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

Parameters:

inputEnabled - Indicates whether guardrail evaluation is enabled 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

GuardrailContentFilter.Builder outputEnabled(Boolean outputEnabled)

Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.

Parameters:

outputEnabled - Indicates whether guardrail evaluation is enabled 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.