Bedrock Runtime  >  Structures  >  GuardrailAutomatedReasoningTranslation

GuardrailAutomatedReasoningTranslation

Structure Class

GuardrailAutomatedReasoningTranslation dataclass

Contains the logical translation of natural language input into formal logical statements, including premises, claims, and confidence scores.

Attributes

claims class-attribute instance-attribute

claims: list[GuardrailAutomatedReasoningStatement] | None = None

The logical statements that are being validated against the premises and policy rules.

confidence class-attribute instance-attribute

confidence: float | None = None

A confidence score between 0 and 1 indicating how certain the system is about the logical translation.

premises class-attribute instance-attribute

premises: list[GuardrailAutomatedReasoningStatement] | None = None

The logical statements that serve as the foundation or assumptions for the claims.

untranslated_claims class-attribute instance-attribute

untranslated_claims: list[GuardrailAutomatedReasoningInputTextReference] | None = None

References to portions of the original input text that correspond to the claims but could not be fully translated.

untranslated_premises class-attribute instance-attribute

untranslated_premises: list[GuardrailAutomatedReasoningInputTextReference] | None = None

References to portions of the original input text that correspond to the premises but could not be fully translated.