bedrock/aws.sdk.kotlin.services.bedrock.model/GuardrailContentFilter/Builder

Builder

Properties

var inputAction: GuardrailContentFilterAction?

The action to take when harmful content is detected in the input. Supported values include:

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.

inputModalities

var inputModalities: List<GuardrailModality>?

The input modalities selected for the guardrail content filter.

inputStrength

var inputStrength: GuardrailFilterStrength?

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.

outputAction

var outputAction: GuardrailContentFilterAction?

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

outputEnabled

var outputEnabled: Boolean?

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.

outputModalities

var outputModalities: List<GuardrailModality>?

The output modalities selected for the guardrail content filter.

outputStrength

var outputStrength: GuardrailFilterStrength?

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.

type

var type: GuardrailContentFilterType?

The harmful category that the content filter is applied to.