bedrockagentruntime/aws.sdk.kotlin.services.bedrockagentruntime.model/OrchestrationConfiguration/Builder

Builder

Properties

var additionalModelRequestFields: Map<String, Document?>?

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.

inferenceConfig

var inferenceConfig: InferenceConfig?

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

performanceConfig

var performanceConfig: PerformanceConfiguration?

The latency configuration for the model.

promptTemplate

var 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.

queryTransformationConfiguration

var queryTransformationConfiguration: QueryTransformationConfiguration?

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

Functions

inferenceConfig

fun inferenceConfig(block: InferenceConfig.Builder.() -> Unit)

construct an aws.sdk.kotlin.services.bedrockagentruntime.model.InferenceConfig inside the given block

performanceConfig

fun performanceConfig(block: PerformanceConfiguration.Builder.() -> Unit)

construct an aws.sdk.kotlin.services.bedrockagentruntime.model.PerformanceConfiguration inside the given block

promptTemplate

fun promptTemplate(block: PromptTemplate.Builder.() -> Unit)

construct an aws.sdk.kotlin.services.bedrockagentruntime.model.PromptTemplate inside the given block

queryTransformationConfiguration

fun queryTransformationConfiguration(block: QueryTransformationConfiguration.Builder.() -> Unit)

construct an aws.sdk.kotlin.services.bedrockagentruntime.model.QueryTransformationConfiguration inside the given block