@aws-cdk/aws-bedrock-alpha.PromptOverrideConfiguration

Experimental

@aws-cdk/aws-bedrock-alpha is an experimental (alpha) package: its API may change in any release, without a major version bump.

PromptOverrideConfiguration Class

Configuration for overriding prompt templates and behaviors in different parts of an agent's sequence.

This allows customizing how the agent processes inputs, makes decisions, and generates responses.

Stability

Experimental

Source

bedrock/agents/prompt-override.ts

Example

const agent = new bedrock.Agent(this, 'Agent', {
  foundationModel: bedrock.BedrockFoundationModel.AMAZON_NOVA_LITE_V1,
  instruction: 'You are a helpful assistant.',
  promptOverrideConfiguration: bedrock.PromptOverrideConfiguration.fromSteps([
    {
      stepType: bedrock.AgentStepType.ROUTING_CLASSIFIER,
      stepEnabled: true,
      customPromptTemplate: 'Your routing template here',
      foundationModel: bedrock.BedrockFoundationModel.ANTHROPIC_CLAUDE_V2
    } as bedrock.PromptRoutingClassifierConfigCustomParser
  ])
});

Properties

knowledgeBaseResponseGenerationStep?may be undefinedPromptKnowledgeBaseResponseGenerationConfigCustomParserknowledge_base_response_generation_step?may be undefinedPromptKnowledgeBaseResponseGenerationConfigCustomParserknowledgeBaseResponseGenerationStep?may be undefinedPromptKnowledgeBaseResponseGenerationConfigCustomParserKnowledgeBaseResponseGenerationStep?may be undefinedPromptKnowledgeBaseResponseGenerationConfigCustomParserKnowledgeBaseResponseGenerationStep?may be undefinedPromptKnowledgeBaseResponseGenerationConfigCustomParser#

Configuration for the knowledge base response generation step.

memorySummarizationStep?may be undefinedPromptMemorySummarizationConfigCustomParsermemory_summarization_step?may be undefinedPromptMemorySummarizationConfigCustomParsermemorySummarizationStep?may be undefinedPromptMemorySummarizationConfigCustomParserMemorySummarizationStep?may be undefinedPromptMemorySummarizationConfigCustomParserMemorySummarizationStep?may be undefinedPromptMemorySummarizationConfigCustomParser#

Configuration for the memory summarization step.

orchestrationStep?may be undefinedPromptOrchestrationConfigCustomParserorchestration_step?may be undefinedPromptOrchestrationConfigCustomParserorchestrationStep?may be undefinedPromptOrchestrationConfigCustomParserOrchestrationStep?may be undefinedPromptOrchestrationConfigCustomParserOrchestrationStep?may be undefinedPromptOrchestrationConfigCustomParser#

Configuration for the orchestration step.

parser?may be undefinedIFunctionparser?may be undefinedIFunctionparser?may be undefinedIFunctionParser?may be undefinedIFunctionParser?may be undefinedIFunction#

The custom Lambda parser function to use.

notes

The Lambda parser processes and interprets the raw foundation model output. It receives an input event with:

• messageVersion: Version of message format (1.0)
• agent: Info about the agent (name, id, alias, version)
• invokeModelRawResponse: Raw model output to parse
• promptType: Type of prompt being parsed
• overrideType: Type of override (OUTPUT_PARSER)

The Lambda must return a response that the agent uses for next actions.

postProcessingStep?may be undefinedPromptPostProcessingConfigCustomParserpost_processing_step?may be undefinedPromptPostProcessingConfigCustomParserpostProcessingStep?may be undefinedPromptPostProcessingConfigCustomParserPostProcessingStep?may be undefinedPromptPostProcessingConfigCustomParserPostProcessingStep?may be undefinedPromptPostProcessingConfigCustomParser#

Configuration for the post-processing step.

preProcessingStep?may be undefinedPromptPreProcessingConfigCustomParserpre_processing_step?may be undefinedPromptPreProcessingConfigCustomParserpreProcessingStep?may be undefinedPromptPreProcessingConfigCustomParserPreProcessingStep?may be undefinedPromptPreProcessingConfigCustomParserPreProcessingStep?may be undefinedPromptPreProcessingConfigCustomParser#

Configuration for the pre-processing step.

routingClassifierStep?may be undefinedPromptRoutingClassifierConfigCustomParserrouting_classifier_step?may be undefinedPromptRoutingClassifierConfigCustomParserroutingClassifierStep?may be undefinedPromptRoutingClassifierConfigCustomParserRoutingClassifierStep?may be undefinedPromptRoutingClassifierConfigCustomParserRoutingClassifierStep?may be undefinedPromptRoutingClassifierConfigCustomParser#

Configuration for the routing classifier step.

Methods

fromSteps(steps: PromptStepConfigBase[]): PromptOverrideConfiguration // chainable@staticmethod def from_steps(steps: typing.List[PromptStepConfigBase]) -> PromptOverrideConfigurationpublic static PromptOverrideConfiguration fromSteps(List<PromptStepConfigBase> steps)public static PromptOverrideConfiguration FromSteps(PromptStepConfigBase[] steps)func FromSteps(Steps *[]PromptStepConfigBase) PromptOverrideConfigurationstatic#

Creates a PromptOverrideConfiguration from individual step configurations.

Use this method when you want to override prompts without using a custom parser.

1 parameter · returns

Parameters

• stepsstepsstepsstepsSteps — The step configurations to use.

Returns: A new PromptOverrideConfiguration instance

withCustomParser(props: CustomParserProps): PromptOverrideConfiguration // chainable@staticmethod def with_custom_parser(props: CustomParserProps) -> PromptOverrideConfigurationpublic static PromptOverrideConfiguration withCustomParser(CustomParserProps props)public static PromptOverrideConfiguration WithCustomParser(CustomParserProps props)func WithCustomParser(Props CustomParserProps) PromptOverrideConfigurationstatic#

Creates a PromptOverrideConfiguration with a custom Lambda parser function.

1 parameter

Parameters

• propspropspropspropsProps — Configuration including: - parser: Lambda function to use as custom parser - Individual step configurations.