pulumi-aws-kotlin/com.pulumi.aws.bedrock.kotlin.outputs/AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration

AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration

data class AgentAgentPromptOverrideConfigurationPromptConfigurationInferenceConfiguration(val maxLength: Int, val stopSequences: List<String>, val temperature: Double, val topK: Int, val topP: Double)

Constructors

constructor(maxLength: Int, stopSequences: List<String>, temperature: Double, topK: Int, topP: Double)

Types

Companion

object Companion

Properties

maxLength

val maxLength: Int

Maximum number of tokens to allow in the generated response.

stopSequences

val stopSequences: List<String>

List of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

temperature

val temperature: Double

Likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

topK

val topK: Int

Number of top most-likely candidates, between 0 and 500, from which the model chooses the next token in the sequence.

topP

val topP: Double

Top percentage of the probability distribution of next tokens, between 0 and 1 (denoting 0% and 100%), from which the model chooses the next token in the sequence.