Skip to content

GuardrailContentFilterConfigDict

Dictionary Type

GuardrailContentFilterConfigDict

Bases: TypedDict

Dictionary form of GuardrailContentFilterConfig.

Attributes

input_action instance-attribute
input_action: str | None

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.

input_enabled instance-attribute
input_enabled: bool | None

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.

input_modalities instance-attribute
input_modalities: Sequence[str] | None

The input modalities selected for the guardrail content filter configuration.

input_strength instance-attribute
input_strength: Required[str]

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.

output_action instance-attribute
output_action: str | None

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.

output_enabled instance-attribute
output_enabled: bool | None

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.

output_modalities instance-attribute
output_modalities: Sequence[str] | None

The output modalities selected for the guardrail content filter configuration.

output_strength instance-attribute
output_strength: Required[str]

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 instance-attribute
type: Required[str]

The harmful category that the content filter is applied to.