Interface OrchestrationConfiguration.Builder
- All Superinterfaces:
Buildable
,CopyableBuilder<OrchestrationConfiguration.Builder,
,OrchestrationConfiguration> SdkBuilder<OrchestrationConfiguration.Builder,
,OrchestrationConfiguration> SdkPojo
- Enclosing class:
OrchestrationConfiguration
-
Method Summary
Modifier and TypeMethodDescriptionadditionalModelRequestFields
(Map<String, Document> additionalModelRequestFields) Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base.inferenceConfig
(Consumer<InferenceConfig.Builder> inferenceConfig) Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.inferenceConfig
(InferenceConfig inferenceConfig) Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.performanceConfig
(Consumer<PerformanceConfiguration.Builder> performanceConfig) The latency configuration for the model.performanceConfig
(PerformanceConfiguration performanceConfig) The latency configuration for the model.promptTemplate
(Consumer<PromptTemplate.Builder> promptTemplate) Contains the template for the prompt that's sent to the model.promptTemplate
(PromptTemplate promptTemplate) Contains the template for the prompt that's sent to the model.queryTransformationConfiguration
(Consumer<QueryTransformationConfiguration.Builder> queryTransformationConfiguration) To split up the prompt and retrieve multiple sources, set the transformation type toQUERY_DECOMPOSITION
.queryTransformationConfiguration
(QueryTransformationConfiguration queryTransformationConfiguration) To split up the prompt and retrieve multiple sources, set the transformation type toQUERY_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 Details
-
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
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 theInferenceConfig.Builder
avoiding the need to create one manually viaInferenceConfig.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed toinferenceConfig(InferenceConfig)
.- Parameters:
inferenceConfig
- a consumer that will call methods onInferenceConfig.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-
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 thePerformanceConfiguration.Builder
avoiding the need to create one manually viaPerformanceConfiguration.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed toperformanceConfig(PerformanceConfiguration)
.- Parameters:
performanceConfig
- a consumer that will call methods onPerformanceConfiguration.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-
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
This is a convenience method that creates an instance of the$conversation_history$
and$output_format_instructions$
variables. For more information, see Use placeholder variables in the user guide.PromptTemplate.Builder
avoiding the need to create one manually viaPromptTemplate.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed topromptTemplate(PromptTemplate)
.- Parameters:
promptTemplate
- a consumer that will call methods onPromptTemplate.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-
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 toQUERY_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
This is a convenience method that creates an instance of theQUERY_DECOMPOSITION
.QueryTransformationConfiguration.Builder
avoiding the need to create one manually viaQueryTransformationConfiguration.builder()
.When the
Consumer
completes,SdkBuilder.build()
is called immediately and its result is passed toqueryTransformationConfiguration(QueryTransformationConfiguration)
.- Parameters:
queryTransformationConfiguration
- a consumer that will call methods onQueryTransformationConfiguration.Builder
- Returns:
- Returns a reference to this object so that method calls can be chained together.
- See Also:
-