AgentPromptVariantInferenceConfigurationTextArgs

data class AgentPromptVariantInferenceConfigurationTextArgs(val maxTokens: Output<Int>? = null, val stopSequences: Output<List<String>>? = null, val temperature: Output<Double>? = null, val topP: Output<Double>? = null) : ConvertibleToJava<AgentPromptVariantInferenceConfigurationTextArgs>

Constructors

constructor(maxTokens: Output<Int>? = null, stopSequences: Output<List<String>>? = null, temperature: Output<Double>? = null, topP: Output<Double>? = null)

Properties

Link copied to clipboard
val maxTokens: Output<Int>? = null

Maximum number of tokens to return in the response.

Link copied to clipboard
val stopSequences: Output<List<String>>? = null

List of strings that define sequences after which the model will stop generating.

Link copied to clipboard
val temperature: Output<Double>? = null

Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.

Link copied to clipboard
val topP: Output<Double>? = null

Percentage of most-likely candidates that the model considers for the next token.

Functions

Link copied to clipboard
open override fun toJava(): AgentPromptVariantInferenceConfigurationTextArgs