GuardrailAutomatedReasoningPolicy¶
Structure Class¶
dataclass
¶
Represents the configuration of Automated Reasoning policies within a Amazon Bedrock Guardrail, including the policies to apply and confidence thresholds.
Attributes¶
class-attribute
instance-attribute
¶
confidence_threshold: float | None = None
The minimum confidence level required for Automated Reasoning policy violations to trigger guardrail actions. Values range from 0.0 to 1.0.
instance-attribute
¶
policies: list[str]
The list of Automated Reasoning policy ARNs that should be applied as part of this guardrail configuration.