Package software.amazon.awscdk.services.bedrock.alpha

Interface PromptInferenceConfigurationProps

All Superinterfaces:

software.amazon.jsii.JsiiSerializable

All Known Implementing Classes:

PromptInferenceConfigurationProps.Jsii$Proxy

@Generated(value="jsii-pacmak/1.119.0 (build 1634eac)",
           date="2025-11-17T14:41:04.518Z")
@Stability(Experimental)
public interface PromptInferenceConfigurationProps
extends software.amazon.jsii.JsiiSerializable

(experimental) Properties for creating a prompt inference configuration.

Example:

 Key cmk = Key.Builder.create(this, "cmk").build();
 BedrockFoundationModel claudeModel = BedrockFoundationModel.ANTHROPIC_CLAUDE_SONNET_V1_0;
 IPromptVariant variant1 = PromptVariant.text(TextPromptVariantProps.builder()
         .variantName("variant1")
         .model(claudeModel)
         .promptVariables(List.of("topic"))
         .promptText("This is my first text prompt. Please summarize our conversation on: {{topic}}.")
         .inferenceConfiguration(PromptInferenceConfiguration.text(PromptInferenceConfigurationProps.builder()
                 .temperature(1)
                 .topP(0.999)
                 .maxTokens(2000)
                 .build()))
         .build());
 Prompt prompt1 = Prompt.Builder.create(this, "prompt1")
         .promptName("prompt1")
         .description("my first prompt")
         .defaultVariant(variant1)
         .variants(List.of(variant1))
         .kmsKey(cmk)
         .build();
 

Nested Class Summary

Nested Classes

Modifier and Type	Interface	Description
static final class	PromptInferenceConfigurationProps.Builder	A builder for PromptInferenceConfigurationProps
static final class	PromptInferenceConfigurationProps.Jsii$Proxy	An implementation for PromptInferenceConfigurationProps

Method Summary

Modifier and Type	Method	Description
static PromptInferenceConfigurationProps.Builder	builder()
default Number	getMaxTokens()	(experimental) The maximum number of tokens to return in the response.
default List<String>	getStopSequences()	(experimental) A list of strings that define sequences after which the model will stop generating.
default Number	getTemperature()	(experimental) Controls the randomness of the response.
default Number	getTopP()	(experimental) The percentage of most-likely candidates that the model considers for the next token.

Methods inherited from interface software.amazon.jsii.JsiiSerializable

$jsii$toJson

Method Details

getMaxTokens

@Stability(Experimental)
@Nullable
default Number getMaxTokens()

(experimental) The maximum number of tokens to return in the response.

Default: - No limit specified

getStopSequences

@Stability(Experimental)
@Nullable
default List<String> getStopSequences()

(experimental) A list of strings that define sequences after which the model will stop generating.

Default: - No stop sequences

getTemperature

@Stability(Experimental)
@Nullable
default Number getTemperature()

(experimental) Controls the randomness of the response.

Higher values make output more random, lower values more deterministic. Valid range is 0.0 to 1.0.

Default: - Model default temperature

getTopP

@Stability(Experimental)
@Nullable
default Number getTopP()

(experimental) The percentage of most-likely candidates that the model considers for the next token.

Valid range is 0.0 to 1.0.

Default: - Model default topP

builder

@Stability(Experimental)
static PromptInferenceConfigurationProps.Builder builder()

Returns:

a PromptInferenceConfigurationProps.Builder of PromptInferenceConfigurationProps