Guardrail
data class GuardrailContentFilterConfig(val inputAction: GuardrailContentFilterAction? = null, val inputEnabled: Boolean? = null, val inputModalities: List<GuardrailModality>? = null, val inputStrength: GuardrailFilterStrength, val outputAction: GuardrailContentFilterAction? = null, val outputEnabled: Boolean? = null, val outputModalities: List<GuardrailModality>? = null, val outputStrength: GuardrailFilterStrength, val type: GuardrailContentFilterType)
Content filter config in content policy.
Constructors
Link copied to clipboard
constructor(inputAction: GuardrailContentFilterAction? = null, inputEnabled: Boolean? = null, inputModalities: List<GuardrailModality>? = null, inputStrength: GuardrailFilterStrength, outputAction: GuardrailContentFilterAction? = null, outputEnabled: Boolean? = null, outputModalities: List<GuardrailModality>? = null, outputStrength: GuardrailFilterStrength, type: GuardrailContentFilterType)
Properties
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
List of modalities
Link copied to clipboard
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
Link copied to clipboard
Link copied to clipboard
Link copied to clipboard
List of modalities
Link copied to clipboard
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
Link copied to clipboard
The harmful category that the content filter is applied to.