Skip to content

Bedrock  >  Structures  >  GuardrailTopic

GuardrailTopic

Structure Class

GuardrailTopic dataclass

Details about topics for the guardrail to identify and deny.

This data type is used in the following API operations:

Attributes

definition class-attribute instance-attribute 
definition: str = field(repr=False)

A definition of the topic to deny.

examples class-attribute instance-attribute 
examples: list[str] | None = None

A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.

input_action class-attribute instance-attribute 
input_action: GuardrailTopicAction | None = field(repr=False, default=None)

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.

input_enabled class-attribute instance-attribute 
input_enabled: bool | None = None

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.

name class-attribute instance-attribute 
name: str = field(repr=False)

The name of the topic to deny.

output_action class-attribute instance-attribute 
output_action: GuardrailTopicAction | None = field(repr=False, default=None)

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 class-attribute instance-attribute 
output_enabled: bool | None = None

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.

type class-attribute instance-attribute 
type: GuardrailTopicType | None = None

Specifies to deny the topic.