GuardrailPiiEntity¶
Structure Class¶
GuardrailPiiEntity
dataclass
¶
The PII entity configured for the guardrail.
Attributes¶
action
instance-attribute
¶
The configured guardrail action when PII entity is detected.
input_action
class-attribute
instance-attribute
¶
input_action: GuardrailSensitiveInformationAction | None = 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. -
ANONYMIZE-- Mask the content and replace it with identifier tags. -
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.
output_action
class-attribute
instance-attribute
¶
output_action: GuardrailSensitiveInformationAction | None = 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. -
ANONYMIZE-- Mask the content and replace it with identifier tags. -
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
instance-attribute
¶
type: GuardrailPiiEntityType
The type of PII entity. For example, Social Security Number.