GuardrailAutomatedReasoningLogicWarning¶
Structure Class¶
dataclass
¶
Identifies logical issues in the translated statements that exist independent of any policy rules, such as statements that are always true or always false.
Attributes¶
class-attribute
instance-attribute
¶
claims: list[GuardrailAutomatedReasoningStatement] | None = None
The logical statements that are validated while assuming the policy and premises.
class-attribute
instance-attribute
¶
premises: list[GuardrailAutomatedReasoningStatement] | None = None
The logical statements that serve as premises under which the claims are validated.
class-attribute
instance-attribute
¶
type: GuardrailAutomatedReasoningLogicWarningType | None = None
The category of the detected logical issue, such as statements that are always true or always false.