Interface OrchestrationTrace.Builder

All Superinterfaces:

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

Enclosing class:

OrchestrationTrace

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

Method Summary

Modifier and Type	Method	Description
default OrchestrationTrace.Builder	invocationInput(Consumer<InvocationInput.Builder> invocationInput)	Contains information pertaining to the action group or knowledge base that is being invoked.
OrchestrationTrace.Builder	invocationInput(InvocationInput invocationInput)	Contains information pertaining to the action group or knowledge base that is being invoked.
default OrchestrationTrace.Builder	modelInvocationInput(Consumer<ModelInvocationInput.Builder> modelInvocationInput)	The input for the orchestration step.
OrchestrationTrace.Builder	modelInvocationInput(ModelInvocationInput modelInvocationInput)	The input for the orchestration step.
default OrchestrationTrace.Builder	modelInvocationOutput(Consumer<OrchestrationModelInvocationOutput.Builder> modelInvocationOutput)	Contains information pertaining to the output from the foundation model that is being invoked.
OrchestrationTrace.Builder	modelInvocationOutput(OrchestrationModelInvocationOutput modelInvocationOutput)	Contains information pertaining to the output from the foundation model that is being invoked.
default OrchestrationTrace.Builder	observation(Consumer<Observation.Builder> observation)	Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.
OrchestrationTrace.Builder	observation(Observation observation)	Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.
default OrchestrationTrace.Builder	rationale(Consumer<Rationale.Builder> rationale)	Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.
OrchestrationTrace.Builder	rationale(Rationale rationale)	Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

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

invocationInput

OrchestrationTrace.Builder invocationInput(InvocationInput invocationInput)

Contains information pertaining to the action group or knowledge base that is being invoked.

Parameters:

invocationInput - Contains information pertaining to the action group or knowledge base that is being invoked.

Returns:

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

invocationInput

default OrchestrationTrace.Builder invocationInput(Consumer<InvocationInput.Builder> invocationInput)

Contains information pertaining to the action group or knowledge base that is being invoked.

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

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

Parameters:

invocationInput - a consumer that will call methods on InvocationInput.Builder

Returns:

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

See Also:

• invocationInput(InvocationInput)

modelInvocationInput

OrchestrationTrace.Builder modelInvocationInput(ModelInvocationInput modelInvocationInput)

The input for the orchestration step.

• The type is ORCHESTRATION.

• The text contains the prompt.

• The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

Parameters:

modelInvocationInput - The input for the orchestration step.

• The type is ORCHESTRATION.

• The text contains the prompt.

• The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

Returns:

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

modelInvocationInput

default OrchestrationTrace.Builder modelInvocationInput(Consumer<ModelInvocationInput.Builder> modelInvocationInput)

The input for the orchestration step.

• The type is ORCHESTRATION.

• The text contains the prompt.

• The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.

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

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

Parameters:

modelInvocationInput - a consumer that will call methods on ModelInvocationInput.Builder

Returns:

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

See Also:

• modelInvocationInput(ModelInvocationInput)

modelInvocationOutput

OrchestrationTrace.Builder modelInvocationOutput(OrchestrationModelInvocationOutput modelInvocationOutput)

Contains information pertaining to the output from the foundation model that is being invoked.

Parameters:

modelInvocationOutput - Contains information pertaining to the output from the foundation model that is being invoked.

Returns:

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

modelInvocationOutput

default OrchestrationTrace.Builder modelInvocationOutput(Consumer<OrchestrationModelInvocationOutput.Builder> modelInvocationOutput)

Contains information pertaining to the output from the foundation model that is being invoked.

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

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

Parameters:

modelInvocationOutput - a consumer that will call methods on OrchestrationModelInvocationOutput.Builder

Returns:

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

See Also:

• modelInvocationOutput(OrchestrationModelInvocationOutput)

observation

OrchestrationTrace.Builder observation(Observation observation)

Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.

Parameters:

observation - Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.

Returns:

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

observation

default OrchestrationTrace.Builder observation(Consumer<Observation.Builder> observation)

Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.

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

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

Parameters:

observation - a consumer that will call methods on Observation.Builder

Returns:

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

See Also:

• observation(Observation)

rationale

OrchestrationTrace.Builder rationale(Rationale rationale)

Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

Parameters:

rationale - Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

Returns:

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

rationale

default OrchestrationTrace.Builder rationale(Consumer<Rationale.Builder> rationale)

Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

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

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

Parameters:

rationale - a consumer that will call methods on Rationale.Builder

Returns:

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

See Also:

• rationale(Rationale)