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

TextAiPromptInferenceConfiguration

class TextAiPromptInferenceConfiguration

Inference configuration for text-based 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.

The top-K sampling parameter for token selection.

val topP: Float

The top-P sampling parameter for nucleus sampling.

Functions

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

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

open override fun hashCode(): Int

open override fun toString(): String