Class GuardrailAutomatedReasoningTranslation
Contains the logical translation of natural language input into formal logical statements, including premises, claims, and confidence scores.
Inherited Members
Namespace: Glitch9.AIDevKit.AmazonAws
Assembly: Glitch9.AIDevKit.Provider.AmazonAws.dll
Syntax
public class GuardrailAutomatedReasoningTranslationProperties
| Edit this page View SourceClaims
Optional. The logical statements that are being validated against the premises and policy rules.
Declaration
[JsonProperty("claims")]
public GuardrailAutomatedReasoningStatement[] Claims { get; set; }Property Value
| Type | Description |
|---|---|
| GuardrailAutomatedReasoningStatement[] |
Confidence
Optional. A confidence score between 0 and 1 indicating how certain the system is about the logical translation.
Declaration
[JsonProperty("confidence")]
public double? Confidence { get; set; }Property Value
| Type | Description |
|---|---|
| double? |
Premises
Optional. The logical statements that serve as the foundation or assumptions for the claims.
Declaration
[JsonProperty("premises")]
public GuardrailAutomatedReasoningStatement[] Premises { get; set; }Property Value
| Type | Description |
|---|---|
| GuardrailAutomatedReasoningStatement[] |
UntranslatedClaims
Optional. References to portions of the original input text that correspond to the claims but could not be fully translated.
Declaration
[JsonProperty("untranslatedClaims")]
public GuardrailAutomatedReasoningInputTextReference[] UntranslatedClaims { get; set; }Property Value
| Type | Description |
|---|---|
| GuardrailAutomatedReasoningInputTextReference[] |
UntranslatedPremises
Optional. References to portions of the original input text that correspond to the premises but could not be fully translated.
Declaration
[JsonProperty("untranslatedPremises")]
public GuardrailAutomatedReasoningInputTextReference[] UntranslatedPremises { get; set; }Property Value
| Type | Description |
|---|---|
| GuardrailAutomatedReasoningInputTextReference[] |