qconnect/aws.sdk.kotlin.services.qconnect.model/AiPromptInferenceConfiguration

AiPromptInferenceConfiguration

class AiPromptInferenceConfiguration

The configuration for inference parameters when using AI Prompts.

Types

object Companion

Properties

maxTokensToSample

val maxTokensToSample: Int?

The maximum number of tokens to generate in the response.

val temperature: Float?

The temperature setting for controlling randomness in the generated response.

val topK: Int?

The top-K sampling parameter for token selection.

val topP: Float?

The top-P sampling parameter for nucleus sampling.

Functions

inline fun copy(block: AiPromptInferenceConfiguration.Builder.() -> Unit = {}): AiPromptInferenceConfiguration

open operator override fun equals(other: Any?): Boolean

open override fun hashCode(): Int

open override fun toString(): String