Package software.amazon.awscdk.services.bedrockagentcore

Class EvaluatorInferenceConfig.Builder

java.lang.Object

software.amazon.awscdk.services.bedrockagentcore.EvaluatorInferenceConfig.Builder

All Implemented Interfaces:

software.amazon.jsii.Builder<EvaluatorInferenceConfig>

Enclosing interface:

EvaluatorInferenceConfig

@Stability(Stable)
public static final class EvaluatorInferenceConfig.Builder
extends Object
implements software.amazon.jsii.Builder<EvaluatorInferenceConfig>

A builder for EvaluatorInferenceConfig

Constructor Summary

Constructors

Constructor	Description
Builder()

Method Summary

Modifier and Type	Method	Description
EvaluatorInferenceConfig	build()	Builds the configured instance.
EvaluatorInferenceConfig.Builder	maxTokens(Number maxTokens)	Sets the value of EvaluatorInferenceConfig.getMaxTokens()
EvaluatorInferenceConfig.Builder	temperature(Number temperature)	Sets the value of EvaluatorInferenceConfig.getTemperature()
EvaluatorInferenceConfig.Builder	topP(Number topP)	Sets the value of EvaluatorInferenceConfig.getTopP()

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

Builder

public Builder()

Method Details

maxTokens

@Stability(Stable)
public EvaluatorInferenceConfig.Builder maxTokens(Number maxTokens)

Sets the value of EvaluatorInferenceConfig.getMaxTokens()

Parameters:

maxTokens - The maximum number of tokens to generate in the model response.

Returns:

this

temperature

@Stability(Stable)
public EvaluatorInferenceConfig.Builder temperature(Number temperature)

Sets the value of EvaluatorInferenceConfig.getTemperature()

Parameters:

temperature - The temperature value that controls randomness in the model's responses. Higher values produce more diverse outputs. Range: 0.0 to 1.0.

Returns:

this

topP

@Stability(Stable)
public EvaluatorInferenceConfig.Builder topP(Number topP)

Sets the value of EvaluatorInferenceConfig.getTopP()

Parameters:

topP - The top-p sampling parameter that controls the diversity of the model's responses. Range: 0.0 to 1.0.

Returns:

this

build

@Stability(Stable)
public EvaluatorInferenceConfig build()

Builds the configured instance.

Specified by:

build in interface software.amazon.jsii.Builder<EvaluatorInferenceConfig>

Returns:

a new instance of EvaluatorInferenceConfig

Throws:

NullPointerException - if any required attribute was not provided