Package software.amazon.awssdk.services.bedrockagentruntime.model

Interface OrchestrationConfiguration.Builder

All Superinterfaces:

Buildable, CopyableBuilder<OrchestrationConfiguration.Builder,OrchestrationConfiguration>, SdkBuilder<OrchestrationConfiguration.Builder,OrchestrationConfiguration>, SdkPojo

Enclosing class:

OrchestrationConfiguration

@Mutable
@NotThreadSafe
public static interface OrchestrationConfiguration.Builder
extends SdkPojo, CopyableBuilder<OrchestrationConfiguration.Builder,OrchestrationConfiguration>

Method Summary

Modifier and Type	Method	Description
OrchestrationConfiguration.Builder	additionalModelRequestFields(Map<String,Document> additionalModelRequestFields)	Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base.
default OrchestrationConfiguration.Builder	inferenceConfig(Consumer<InferenceConfig.Builder> inferenceConfig)	Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
OrchestrationConfiguration.Builder	inferenceConfig(InferenceConfig inferenceConfig)	Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
default OrchestrationConfiguration.Builder	performanceConfig(Consumer<PerformanceConfiguration.Builder> performanceConfig)	The latency configuration for the model.
OrchestrationConfiguration.Builder	performanceConfig(PerformanceConfiguration performanceConfig)	The latency configuration for the model.
default OrchestrationConfiguration.Builder	promptTemplate(Consumer<PromptTemplate.Builder> promptTemplate)	Contains the template for the prompt that's sent to the model.
OrchestrationConfiguration.Builder	promptTemplate(PromptTemplate promptTemplate)	Contains the template for the prompt that's sent to the model.
default OrchestrationConfiguration.Builder	queryTransformationConfiguration(Consumer<QueryTransformationConfiguration.Builder> queryTransformationConfiguration)	To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.
OrchestrationConfiguration.Builder	queryTransformationConfiguration(QueryTransformationConfiguration queryTransformationConfiguration)	To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.

Methods inherited from interface software.amazon.awssdk.utils.builder.CopyableBuilder

copy

Methods inherited from interface software.amazon.awssdk.utils.builder.SdkBuilder

applyMutation, build

Methods inherited from interface software.amazon.awssdk.core.SdkPojo

equalsBySdkFields, sdkFieldNameToField, sdkFields

Method Detail

additionalModelRequestFields

OrchestrationConfiguration.Builder additionalModelRequestFields(Map<String,Document> additionalModelRequestFields)

Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.

Parameters:

additionalModelRequestFields - Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.

Returns:

Returns a reference to this object so that method calls can be chained together.

inferenceConfig

OrchestrationConfiguration.Builder inferenceConfig(InferenceConfig inferenceConfig)

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

Parameters:

inferenceConfig - Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

Returns:

Returns a reference to this object so that method calls can be chained together.

inferenceConfig

default OrchestrationConfiguration.Builder inferenceConfig(Consumer<InferenceConfig.Builder> inferenceConfig)

Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.

This is a convenience method that creates an instance of the InferenceConfig.Builder avoiding the need to create one manually via InferenceConfig.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to inferenceConfig(InferenceConfig).

Parameters:

inferenceConfig - a consumer that will call methods on InferenceConfig.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

inferenceConfig(InferenceConfig)

performanceConfig

OrchestrationConfiguration.Builder performanceConfig(PerformanceConfiguration performanceConfig)

The latency configuration for the model.

Parameters:

performanceConfig - The latency configuration for the model.

Returns:

Returns a reference to this object so that method calls can be chained together.

performanceConfig

default OrchestrationConfiguration.Builder performanceConfig(Consumer<PerformanceConfiguration.Builder> performanceConfig)

The latency configuration for the model.

This is a convenience method that creates an instance of the PerformanceConfiguration.Builder avoiding the need to create one manually via PerformanceConfiguration.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to performanceConfig(PerformanceConfiguration).

Parameters:

performanceConfig - a consumer that will call methods on PerformanceConfiguration.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

performanceConfig(PerformanceConfiguration)

promptTemplate

OrchestrationConfiguration.Builder promptTemplate(PromptTemplate promptTemplate)

Contains the template for the prompt that's sent to the model. Orchestration prompts must include the $conversation_history$ and $output_format_instructions$ variables. For more information, see Use placeholder variables in the user guide.

Parameters:

promptTemplate - Contains the template for the prompt that's sent to the model. Orchestration prompts must include the $conversation_history$ and $output_format_instructions$ variables. For more information, see Use placeholder variables in the user guide.

Returns:

Returns a reference to this object so that method calls can be chained together.

promptTemplate

default OrchestrationConfiguration.Builder promptTemplate(Consumer<PromptTemplate.Builder> promptTemplate)

Contains the template for the prompt that's sent to the model. Orchestration prompts must include the $conversation_history$ and $output_format_instructions$ variables. For more information, see Use placeholder variables in the user guide.

This is a convenience method that creates an instance of the PromptTemplate.Builder avoiding the need to create one manually via PromptTemplate.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to promptTemplate(PromptTemplate).

Parameters:

promptTemplate - a consumer that will call methods on PromptTemplate.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

promptTemplate(PromptTemplate)

queryTransformationConfiguration

OrchestrationConfiguration.Builder queryTransformationConfiguration(QueryTransformationConfiguration queryTransformationConfiguration)

To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.

Parameters:

queryTransformationConfiguration - To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.

Returns:

Returns a reference to this object so that method calls can be chained together.

queryTransformationConfiguration

default OrchestrationConfiguration.Builder queryTransformationConfiguration(Consumer<QueryTransformationConfiguration.Builder> queryTransformationConfiguration)

To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.

This is a convenience method that creates an instance of the QueryTransformationConfiguration.Builder avoiding the need to create one manually via QueryTransformationConfiguration.builder().

When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to queryTransformationConfiguration(QueryTransformationConfiguration).

Parameters:

queryTransformationConfiguration - a consumer that will call methods on QueryTransformationConfiguration.Builder

Returns:

Returns a reference to this object so that method calls can be chained together.

See Also:

queryTransformationConfiguration(QueryTransformationConfiguration)