Skip to content
v2.277.0

Experimental

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

AgentProps Struct ​

Properties for creating a CDK managed Bedrock Agent.

TODO: Knowledge bases configuration will be added in a future update TODO: Inference profile configuration will be added in a future update

Example ​

ts
const parserFunction = new lambda.Function(this, 'ParserFunction', {
  runtime: lambda.Runtime.PYTHON_3_10,
  handler: 'index.handler',
  code: lambda.Code.fromAsset('lambda'),
});

const agent = new bedrock.Agent(this, 'Agent', {
  foundationModel: bedrock.BedrockFoundationModel.AMAZON_NOVA_LITE_V1,
  instruction: 'You are a helpful assistant.',
  promptOverrideConfiguration: bedrock.PromptOverrideConfiguration.withCustomParser({
    parser: parserFunction,
    preProcessingStep: {
      stepType: bedrock.AgentStepType.PRE_PROCESSING,
      useCustomParser: true
    }
  })
});
python
parser_function = lambda_.Function(self, "ParserFunction",
    runtime=lambda_.Runtime.PYTHON_3_10,
    handler="index.handler",
    code=lambda_.Code.from_asset("lambda")
)

agent = bedrock.Agent(self, "Agent",
    foundation_model=bedrock.BedrockFoundationModel.AMAZON_NOVA_LITE_V1,
    instruction="You are a helpful assistant.",
    prompt_override_configuration=bedrock.PromptOverrideConfiguration.with_custom_parser(
        parser=parser_function,
        pre_processing_step=bedrock.PromptPreProcessingConfigCustomParser(
            step_type=bedrock.AgentStepType.PRE_PROCESSING,
            use_custom_parser=True
        )
    )
)
java
Function parserFunction = Function.Builder.create(this, "ParserFunction")
        .runtime(Runtime.PYTHON_3_10)
        .handler("index.handler")
        .code(Code.fromAsset("lambda"))
        .build();

Agent agent = Agent.Builder.create(this, "Agent")
        .foundationModel(BedrockFoundationModel.AMAZON_NOVA_LITE_V1)
        .instruction("You are a helpful assistant.")
        .promptOverrideConfiguration(PromptOverrideConfiguration.withCustomParser(CustomParserProps.builder()
                .parser(parserFunction)
                .preProcessingStep(PromptPreProcessingConfigCustomParser.builder()
                        .stepType(AgentStepType.PRE_PROCESSING)
                        .useCustomParser(true)
                        .build())
                .build()))
        .build();
csharp
// Install: dotnet add package Amazon.CDK.AWS.Bedrock.Alpha
var parserFunction = new Function(this, "ParserFunction", new FunctionProps {
    Runtime = Runtime.PYTHON_3_10,
    Handler = "index.handler",
    Code = Code.FromAsset("lambda")
});

var agent = new Agent(this, "Agent", new AgentProps {
    FoundationModel = BedrockFoundationModel.AMAZON_NOVA_LITE_V1,
    Instruction = "You are a helpful assistant.",
    PromptOverrideConfiguration = PromptOverrideConfiguration.WithCustomParser(new CustomParserProps {
        Parser = parserFunction,
        PreProcessingStep = new PromptPreProcessingConfigCustomParser {
            StepType = AgentStepType.PRE_PROCESSING,
            UseCustomParser = true
        }
    })
});
go
// Install: go get github.com/aws/aws-cdk-go/awsbedrockalpha/v2
parserFunction := lambda.NewFunction(this, jsii.String("ParserFunction"), &FunctionProps{
	Runtime: lambda.Runtime_PYTHON_3_10(),
	Handler: jsii.String("index.handler"),
	Code: lambda.Code_FromAsset(jsii.String("lambda")),
})

agent := bedrock.NewAgent(this, jsii.String("Agent"), &AgentProps{
	FoundationModel: bedrock.BedrockFoundationModel_AMAZON_NOVA_LITE_V1(),
	Instruction: jsii.String("You are a helpful assistant."),
	PromptOverrideConfiguration: bedrock.PromptOverrideConfiguration_WithCustomParser(&CustomParserProps{
		Parser: parserFunction,
		PreProcessingStep: &PromptPreProcessingConfigCustomParser{
			StepType: bedrock.AgentStepType_PRE_PROCESSING,
			UseCustomParser: jsii.Boolean(true),
		},
	}),
})

Properties ​

actionGroupsoptionalAgentActionGroup[]action_groupsoptionaltyping.List[AgentActionGroup]actionGroupsoptionalList<AgentActionGroup>ActionGroupsoptionalAgentActionGroup[]ActionGroupsoptional*[]AgentActionGroup #
The Action Groups associated with the agent.

Default: Only default action groups (UserInput and CodeInterpreter) are added

agentCollaborationoptionalAgentCollaborationagent_collaborationoptionalAgentCollaborationagentCollaborationoptionalAgentCollaborationAgentCollaborationoptionalAgentCollaborationAgentCollaborationoptionalAgentCollaboration #
Configuration for agent collaboration settings, including AgentCollaboratorType and AgentCollaborators.

Default: No agent collaboration configuration.

This property allows you to define how the agent collaborates with other agents and what collaborators it can work with.

agentNameoptionalstringagent_nameoptionalstragentNameoptionalStringAgentNameoptionalstringAgentNameoptional*string #
The name of the agent.

Default: A name is generated by CDK. Supported pattern : ^([0-9a-zA-Z][_-]?){1,100}$

This will be used as the physical name of the agent.

codeInterpreterEnabledoptionalbooleancode_interpreter_enabledoptionalboolcodeInterpreterEnabledoptionalBooleanCodeInterpreterEnabledoptionalboolCodeInterpreterEnabledoptional*bool = false #
Select whether the agent can generate, run, and troubleshoot code when trying to complete a task.
customOrchestrationExecutoroptionalCustomOrchestrationExecutorcustom_orchestration_executoroptionalCustomOrchestrationExecutorcustomOrchestrationExecutoroptionalCustomOrchestrationExecutorCustomOrchestrationExecutoroptionalCustomOrchestrationExecutorCustomOrchestrationExecutoroptionalCustomOrchestrationExecutor #
The Lambda function to use for custom orchestration.

Default: Default orchestration

If provided, custom orchestration will be used. If not provided, default orchestration will be used.

descriptionoptionalstringdescriptionoptionalstrdescriptionoptionalStringDescriptionoptionalstringDescriptionoptional*string #
A description of the agent.

Default: No description is provided.

existingRoleoptionalIRoleexisting_roleoptionalIRoleexistingRoleoptionalIRoleExistingRoleoptionalIRoleExistingRoleoptionalIRole #
An existing IAM Role to associate with this agent.

Default: A new role is created for you.

Use this property when you want to reuse an existing IAM role rather than create a new one. The role must have a trust policy that allows the Bedrock service to assume it.

forceDeleteoptionalbooleanforce_deleteoptionalboolforceDeleteoptionalBooleanForceDeleteoptionalboolForceDeleteoptional*bool = false #
Whether to delete the resource even if it's in use.
foundationModelIBedrockInvokablefoundation_modelIBedrockInvokablefoundationModelIBedrockInvokableFoundationModelIBedrockInvokableFoundationModelIBedrockInvokable required #
The foundation model used for orchestration by the agent.
guardrailoptionalIGuardrailguardrailoptionalIGuardrailguardrailoptionalIGuardrailGuardrailoptionalIGuardrailGuardrailoptionalIGuardrail #
The guardrail that will be associated with the agent.

Default: No guardrail is provided.

idleSessionTTLoptionalDurationidle_session_ttloptionalDurationidleSessionTTLoptionalDurationIdleSessionTTLoptionalDurationIdleSessionTTLoptionalDuration #
How long sessions should be kept open for the agent.

Default: 10 minutes

If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.

instructionstringinstructionstrinstructionStringInstructionstringInstruction*string required #
The instruction used by the agent.

This determines how the agent will perform his task. This instruction must have a minimum of 40 characters.

kmsKeyoptionalIKeykms_keyoptionalIKeykmsKeyoptionalIKeyKmsKeyoptionalIKeyKmsKeyoptionalIKey #
The KMS key of the agent if custom encryption is configured.

Default: An AWS managed key is used.

memoryoptionalMemorymemoryoptionalMemorymemoryoptionalMemoryMemoryoptionalMemoryMemoryoptionalMemory #
The type and configuration of the memory to maintain context across multiple sessions and recall past interactions.

Default: No memory will be used. Agents will retain context from the current session only.

This can be useful for maintaining continuity in multi-turn conversations and recalling user preferences or past interactions.

promptOverrideConfigurationoptionalPromptOverrideConfigurationprompt_override_configurationoptionalPromptOverrideConfigurationpromptOverrideConfigurationoptionalPromptOverrideConfigurationPromptOverrideConfigurationoptionalPromptOverrideConfigurationPromptOverrideConfigurationoptionalPromptOverrideConfiguration #
Overrides some prompt templates in different parts of an agent sequence configuration.

Default: No overrides are provided.

shouldPrepareAgentoptionalbooleanshould_prepare_agentoptionalboolshouldPrepareAgentoptionalBooleanShouldPrepareAgentoptionalboolShouldPrepareAgentoptional*bool = false #
Specifies whether to automatically update the `DRAFT` version of the agent after making changes to the agent.

The DRAFT version can be continually iterated upon during internal development.

userInputEnabledoptionalbooleanuser_input_enabledoptionalbooluserInputEnabledoptionalBooleanUserInputEnabledoptionalboolUserInputEnabledoptional*bool = false #
Select whether the agent can prompt additional information from the user when it does not have enough information to respond to an utterance.