1. Packages
  2. AWS Native
  3. API Docs
  4. bedrock
  5. Agent

AWS Native is in preview. AWS Classic is fully supported.

AWS Native v0.106.0 published on Monday, May 20, 2024 by Pulumi

aws-native.bedrock.Agent

Explore with Pulumi AI

aws-native logo

AWS Native is in preview. AWS Classic is fully supported.

AWS Native v0.106.0 published on Monday, May 20, 2024 by Pulumi

    Definition of AWS::Bedrock::Agent Resource Type

    Create Agent Resource

    Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

    Constructor syntax

    new Agent(name: string, args?: AgentArgs, opts?: CustomResourceOptions);
    @overload
    def Agent(resource_name: str,
              args: Optional[AgentArgs] = None,
              opts: Optional[ResourceOptions] = None)
    
    @overload
    def Agent(resource_name: str,
              opts: Optional[ResourceOptions] = None,
              action_groups: Optional[Sequence[AgentActionGroupArgs]] = None,
              agent_name: Optional[str] = None,
              agent_resource_role_arn: Optional[str] = None,
              auto_prepare: Optional[bool] = None,
              customer_encryption_key_arn: Optional[str] = None,
              description: Optional[str] = None,
              foundation_model: Optional[str] = None,
              idle_session_ttl_in_seconds: Optional[float] = None,
              instruction: Optional[str] = None,
              knowledge_bases: Optional[Sequence[AgentKnowledgeBaseArgs]] = None,
              prompt_override_configuration: Optional[AgentPromptOverrideConfigurationArgs] = None,
              skip_resource_in_use_check_on_delete: Optional[bool] = None,
              tags: Optional[Mapping[str, str]] = None,
              test_alias_tags: Optional[Mapping[str, str]] = None)
    func NewAgent(ctx *Context, name string, args *AgentArgs, opts ...ResourceOption) (*Agent, error)
    public Agent(string name, AgentArgs? args = null, CustomResourceOptions? opts = null)
    public Agent(String name, AgentArgs args)
    public Agent(String name, AgentArgs args, CustomResourceOptions options)
    
    type: aws-native:bedrock:Agent
    properties: # The arguments to resource properties.
    options: # Bag of options to control resource's behavior.
    
    

    Parameters

    name string
    The unique name of the resource.
    args AgentArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    resource_name str
    The unique name of the resource.
    args AgentArgs
    The arguments to resource properties.
    opts ResourceOptions
    Bag of options to control resource's behavior.
    ctx Context
    Context object for the current deployment.
    name string
    The unique name of the resource.
    args AgentArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args AgentArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args AgentArgs
    The arguments to resource properties.
    options CustomResourceOptions
    Bag of options to control resource's behavior.

    Example

    The following reference example uses placeholder values for all input properties.

    Coming soon!
    
    Coming soon!
    
    Coming soon!
    
    Coming soon!
    
    const agentResource = new aws_native.bedrock.Agent("agentResource", {
        actionGroups: [{
            actionGroupName: "string",
            actionGroupExecutor: {
                lambda: "string",
            },
            actionGroupState: aws_native.bedrock.AgentActionGroupState.Enabled,
            apiSchema: {
                s3: {
                    s3BucketName: "string",
                    s3ObjectKey: "string",
                },
            },
            description: "string",
            functionSchema: {
                functions: [{
                    name: "string",
                    description: "string",
                    parameters: {
                        string: {
                            type: aws_native.bedrock.AgentType.String,
                            description: "string",
                            required: false,
                        },
                    },
                }],
            },
            parentActionGroupSignature: aws_native.bedrock.AgentActionGroupSignature.AmazonUserInput,
            skipResourceInUseCheckOnDelete: false,
        }],
        agentName: "string",
        agentResourceRoleArn: "string",
        autoPrepare: false,
        customerEncryptionKeyArn: "string",
        description: "string",
        foundationModel: "string",
        idleSessionTtlInSeconds: 0,
        instruction: "string",
        knowledgeBases: [{
            description: "string",
            knowledgeBaseId: "string",
            knowledgeBaseState: aws_native.bedrock.AgentKnowledgeBaseState.Enabled,
        }],
        promptOverrideConfiguration: {
            promptConfigurations: [{
                basePromptTemplate: "string",
                inferenceConfiguration: {
                    maximumLength: 0,
                    stopSequences: ["string"],
                    temperature: 0,
                    topK: 0,
                    topP: 0,
                },
                parserMode: aws_native.bedrock.AgentCreationMode.Default,
                promptCreationMode: aws_native.bedrock.AgentCreationMode.Default,
                promptState: aws_native.bedrock.AgentPromptState.Enabled,
                promptType: aws_native.bedrock.AgentPromptType.PreProcessing,
            }],
            overrideLambda: "string",
        },
        skipResourceInUseCheckOnDelete: false,
        tags: {
            string: "string",
        },
        testAliasTags: {
            string: "string",
        },
    });
    
    Coming soon!
    

    Agent Resource Properties

    To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

    Inputs

    The Agent resource accepts the following input properties:

    ActionGroups List<Pulumi.AwsNative.Bedrock.Inputs.AgentActionGroup>
    List of ActionGroups
    AgentName string
    Name for a resource.
    AgentResourceRoleArn string
    ARN of a IAM role.
    AutoPrepare bool
    Specifies whether to automatically prepare after creating or updating the agent.
    CustomerEncryptionKeyArn string
    A KMS key ARN
    Description string
    Description of the Resource.
    FoundationModel string
    ARN or name of a Bedrock model.
    IdleSessionTtlInSeconds double
    Max Session Time.
    Instruction string
    Instruction for the agent.
    KnowledgeBases List<Pulumi.AwsNative.Bedrock.Inputs.AgentKnowledgeBase>
    List of Agent Knowledge Bases
    PromptOverrideConfiguration Pulumi.AwsNative.Bedrock.Inputs.AgentPromptOverrideConfiguration
    Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
    SkipResourceInUseCheckOnDelete bool
    Specifies whether to allow deleting agent while it is in use.
    Tags Dictionary<string, string>
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    TestAliasTags Dictionary<string, string>
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    ActionGroups []AgentActionGroupArgs
    List of ActionGroups
    AgentName string
    Name for a resource.
    AgentResourceRoleArn string
    ARN of a IAM role.
    AutoPrepare bool
    Specifies whether to automatically prepare after creating or updating the agent.
    CustomerEncryptionKeyArn string
    A KMS key ARN
    Description string
    Description of the Resource.
    FoundationModel string
    ARN or name of a Bedrock model.
    IdleSessionTtlInSeconds float64
    Max Session Time.
    Instruction string
    Instruction for the agent.
    KnowledgeBases []AgentKnowledgeBaseArgs
    List of Agent Knowledge Bases
    PromptOverrideConfiguration AgentPromptOverrideConfigurationArgs
    Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
    SkipResourceInUseCheckOnDelete bool
    Specifies whether to allow deleting agent while it is in use.
    Tags map[string]string
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    TestAliasTags map[string]string
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    actionGroups List<AgentActionGroup>
    List of ActionGroups
    agentName String
    Name for a resource.
    agentResourceRoleArn String
    ARN of a IAM role.
    autoPrepare Boolean
    Specifies whether to automatically prepare after creating or updating the agent.
    customerEncryptionKeyArn String
    A KMS key ARN
    description String
    Description of the Resource.
    foundationModel String
    ARN or name of a Bedrock model.
    idleSessionTtlInSeconds Double
    Max Session Time.
    instruction String
    Instruction for the agent.
    knowledgeBases List<AgentKnowledgeBase>
    List of Agent Knowledge Bases
    promptOverrideConfiguration AgentPromptOverrideConfiguration
    Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
    skipResourceInUseCheckOnDelete Boolean
    Specifies whether to allow deleting agent while it is in use.
    tags Map<String,String>
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    testAliasTags Map<String,String>
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    actionGroups AgentActionGroup[]
    List of ActionGroups
    agentName string
    Name for a resource.
    agentResourceRoleArn string
    ARN of a IAM role.
    autoPrepare boolean
    Specifies whether to automatically prepare after creating or updating the agent.
    customerEncryptionKeyArn string
    A KMS key ARN
    description string
    Description of the Resource.
    foundationModel string
    ARN or name of a Bedrock model.
    idleSessionTtlInSeconds number
    Max Session Time.
    instruction string
    Instruction for the agent.
    knowledgeBases AgentKnowledgeBase[]
    List of Agent Knowledge Bases
    promptOverrideConfiguration AgentPromptOverrideConfiguration
    Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
    skipResourceInUseCheckOnDelete boolean
    Specifies whether to allow deleting agent while it is in use.
    tags {[key: string]: string}
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    testAliasTags {[key: string]: string}
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    action_groups Sequence[AgentActionGroupArgs]
    List of ActionGroups
    agent_name str
    Name for a resource.
    agent_resource_role_arn str
    ARN of a IAM role.
    auto_prepare bool
    Specifies whether to automatically prepare after creating or updating the agent.
    customer_encryption_key_arn str
    A KMS key ARN
    description str
    Description of the Resource.
    foundation_model str
    ARN or name of a Bedrock model.
    idle_session_ttl_in_seconds float
    Max Session Time.
    instruction str
    Instruction for the agent.
    knowledge_bases Sequence[AgentKnowledgeBaseArgs]
    List of Agent Knowledge Bases
    prompt_override_configuration AgentPromptOverrideConfigurationArgs
    Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
    skip_resource_in_use_check_on_delete bool
    Specifies whether to allow deleting agent while it is in use.
    tags Mapping[str, str]
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    test_alias_tags Mapping[str, str]
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    actionGroups List<Property Map>
    List of ActionGroups
    agentName String
    Name for a resource.
    agentResourceRoleArn String
    ARN of a IAM role.
    autoPrepare Boolean
    Specifies whether to automatically prepare after creating or updating the agent.
    customerEncryptionKeyArn String
    A KMS key ARN
    description String
    Description of the Resource.
    foundationModel String
    ARN or name of a Bedrock model.
    idleSessionTtlInSeconds Number
    Max Session Time.
    instruction String
    Instruction for the agent.
    knowledgeBases List<Property Map>
    List of Agent Knowledge Bases
    promptOverrideConfiguration Property Map
    Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts .
    skipResourceInUseCheckOnDelete Boolean
    Specifies whether to allow deleting agent while it is in use.
    tags Map<String>
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    testAliasTags Map<String>
    Metadata that you can assign to a resource as key-value pairs. For more information, see the following resources:

    Outputs

    All input properties are implicitly available as output properties. Additionally, the Agent resource produces the following output properties:

    AgentArn string
    Arn representation of the Agent.
    AgentId string
    Identifier for a resource.
    AgentStatus Pulumi.AwsNative.Bedrock.AgentStatus
    The status of the agent and whether it is ready for use. The following statuses are possible:

    • CREATING – The agent is being created.
    • PREPARING – The agent is being prepared.
    • PREPARED – The agent is prepared and ready to be invoked.
    • NOT_PREPARED – The agent has been created but not yet prepared.
    • FAILED – The agent API operation failed.
    • UPDATING – The agent is being updated.
    • DELETING – The agent is being deleted.
    AgentVersion string
    Draft Agent Version.
    CreatedAt string
    Time Stamp.
    FailureReasons List<string>
    Failure Reasons for Error.
    Id string
    The provider-assigned unique ID for this managed resource.
    PreparedAt string
    Time Stamp.
    RecommendedActions List<string>
    The recommended actions users can take to resolve an error in failureReasons.
    UpdatedAt string
    Time Stamp.
    AgentArn string
    Arn representation of the Agent.
    AgentId string
    Identifier for a resource.
    AgentStatus AgentStatus
    The status of the agent and whether it is ready for use. The following statuses are possible:

    • CREATING – The agent is being created.
    • PREPARING – The agent is being prepared.
    • PREPARED – The agent is prepared and ready to be invoked.
    • NOT_PREPARED – The agent has been created but not yet prepared.
    • FAILED – The agent API operation failed.
    • UPDATING – The agent is being updated.
    • DELETING – The agent is being deleted.
    AgentVersion string
    Draft Agent Version.
    CreatedAt string
    Time Stamp.
    FailureReasons []string
    Failure Reasons for Error.
    Id string
    The provider-assigned unique ID for this managed resource.
    PreparedAt string
    Time Stamp.
    RecommendedActions []string
    The recommended actions users can take to resolve an error in failureReasons.
    UpdatedAt string
    Time Stamp.
    agentArn String
    Arn representation of the Agent.
    agentId String
    Identifier for a resource.
    agentStatus AgentStatus
    The status of the agent and whether it is ready for use. The following statuses are possible:

    • CREATING – The agent is being created.
    • PREPARING – The agent is being prepared.
    • PREPARED – The agent is prepared and ready to be invoked.
    • NOT_PREPARED – The agent has been created but not yet prepared.
    • FAILED – The agent API operation failed.
    • UPDATING – The agent is being updated.
    • DELETING – The agent is being deleted.
    agentVersion String
    Draft Agent Version.
    createdAt String
    Time Stamp.
    failureReasons List<String>
    Failure Reasons for Error.
    id String
    The provider-assigned unique ID for this managed resource.
    preparedAt String
    Time Stamp.
    recommendedActions List<String>
    The recommended actions users can take to resolve an error in failureReasons.
    updatedAt String
    Time Stamp.
    agentArn string
    Arn representation of the Agent.
    agentId string
    Identifier for a resource.
    agentStatus AgentStatus
    The status of the agent and whether it is ready for use. The following statuses are possible:

    • CREATING – The agent is being created.
    • PREPARING – The agent is being prepared.
    • PREPARED – The agent is prepared and ready to be invoked.
    • NOT_PREPARED – The agent has been created but not yet prepared.
    • FAILED – The agent API operation failed.
    • UPDATING – The agent is being updated.
    • DELETING – The agent is being deleted.
    agentVersion string
    Draft Agent Version.
    createdAt string
    Time Stamp.
    failureReasons string[]
    Failure Reasons for Error.
    id string
    The provider-assigned unique ID for this managed resource.
    preparedAt string
    Time Stamp.
    recommendedActions string[]
    The recommended actions users can take to resolve an error in failureReasons.
    updatedAt string
    Time Stamp.
    agent_arn str
    Arn representation of the Agent.
    agent_id str
    Identifier for a resource.
    agent_status AgentStatus
    The status of the agent and whether it is ready for use. The following statuses are possible:

    • CREATING – The agent is being created.
    • PREPARING – The agent is being prepared.
    • PREPARED – The agent is prepared and ready to be invoked.
    • NOT_PREPARED – The agent has been created but not yet prepared.
    • FAILED – The agent API operation failed.
    • UPDATING – The agent is being updated.
    • DELETING – The agent is being deleted.
    agent_version str
    Draft Agent Version.
    created_at str
    Time Stamp.
    failure_reasons Sequence[str]
    Failure Reasons for Error.
    id str
    The provider-assigned unique ID for this managed resource.
    prepared_at str
    Time Stamp.
    recommended_actions Sequence[str]
    The recommended actions users can take to resolve an error in failureReasons.
    updated_at str
    Time Stamp.
    agentArn String
    Arn representation of the Agent.
    agentId String
    Identifier for a resource.
    agentStatus "CREATING" | "PREPARING" | "PREPARED" | "NOT_PREPARED" | "DELETING" | "FAILED" | "VERSIONING" | "UPDATING"
    The status of the agent and whether it is ready for use. The following statuses are possible:

    • CREATING – The agent is being created.
    • PREPARING – The agent is being prepared.
    • PREPARED – The agent is prepared and ready to be invoked.
    • NOT_PREPARED – The agent has been created but not yet prepared.
    • FAILED – The agent API operation failed.
    • UPDATING – The agent is being updated.
    • DELETING – The agent is being deleted.
    agentVersion String
    Draft Agent Version.
    createdAt String
    Time Stamp.
    failureReasons List<String>
    Failure Reasons for Error.
    id String
    The provider-assigned unique ID for this managed resource.
    preparedAt String
    Time Stamp.
    recommendedActions List<String>
    The recommended actions users can take to resolve an error in failureReasons.
    updatedAt String
    Time Stamp.

    Supporting Types

    AgentActionGroup, AgentActionGroupArgs

    ActionGroupName string
    Name of the action group
    ActionGroupExecutor Pulumi.AwsNative.Bedrock.Inputs.AgentActionGroupExecutor0Properties | Pulumi.AwsNative.Bedrock.Inputs.AgentActionGroupExecutor1Properties
    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.
    ActionGroupState Pulumi.AwsNative.Bedrock.AgentActionGroupState
    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
    ApiSchema Pulumi.AwsNative.Bedrock.Inputs.AgentApiSchema0Properties | Pulumi.AwsNative.Bedrock.Inputs.AgentApiSchema1Properties
    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas .
    Description string
    Description of action group
    FunctionSchema Pulumi.AwsNative.Bedrock.Inputs.AgentFunctionSchema
    Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
    ParentActionGroupSignature Pulumi.AwsNative.Bedrock.AgentActionGroupSignature

    If this field is set as AMAZON.UserInput , the agent can request the user for additional information when trying to complete a task. The description , apiSchema , and actionGroupExecutor fields must be blank for this action group.

    During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

    SkipResourceInUseCheckOnDelete bool
    Specifies whether to allow deleting action group while it is in use.
    ActionGroupName string
    Name of the action group
    ActionGroupExecutor AgentActionGroupExecutor0Properties | AgentActionGroupExecutor1Properties
    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.
    ActionGroupState AgentActionGroupState
    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
    ApiSchema AgentApiSchema0Properties | AgentApiSchema1Properties
    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas .
    Description string
    Description of action group
    FunctionSchema AgentFunctionSchema
    Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
    ParentActionGroupSignature AgentActionGroupSignature

    If this field is set as AMAZON.UserInput , the agent can request the user for additional information when trying to complete a task. The description , apiSchema , and actionGroupExecutor fields must be blank for this action group.

    During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

    SkipResourceInUseCheckOnDelete bool
    Specifies whether to allow deleting action group while it is in use.
    actionGroupName String
    Name of the action group
    actionGroupExecutor AgentActionGroupExecutor0Properties | AgentActionGroupExecutor1Properties
    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.
    actionGroupState AgentActionGroupState
    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
    apiSchema AgentApiSchema0Properties | AgentApiSchema1Properties
    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas .
    description String
    Description of action group
    functionSchema AgentFunctionSchema
    Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
    parentActionGroupSignature AgentActionGroupSignature

    If this field is set as AMAZON.UserInput , the agent can request the user for additional information when trying to complete a task. The description , apiSchema , and actionGroupExecutor fields must be blank for this action group.

    During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

    skipResourceInUseCheckOnDelete Boolean
    Specifies whether to allow deleting action group while it is in use.
    actionGroupName string
    Name of the action group
    actionGroupExecutor AgentActionGroupExecutor0Properties | AgentActionGroupExecutor1Properties
    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.
    actionGroupState AgentActionGroupState
    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
    apiSchema AgentApiSchema0Properties | AgentApiSchema1Properties
    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas .
    description string
    Description of action group
    functionSchema AgentFunctionSchema
    Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
    parentActionGroupSignature AgentActionGroupSignature

    If this field is set as AMAZON.UserInput , the agent can request the user for additional information when trying to complete a task. The description , apiSchema , and actionGroupExecutor fields must be blank for this action group.

    During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

    skipResourceInUseCheckOnDelete boolean
    Specifies whether to allow deleting action group while it is in use.
    action_group_name str
    Name of the action group
    action_group_executor AgentActionGroupExecutor0Properties | AgentActionGroupExecutor1Properties
    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.
    action_group_state AgentActionGroupState
    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
    api_schema AgentApiSchema0Properties | AgentApiSchema1Properties
    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas .
    description str
    Description of action group
    function_schema AgentFunctionSchema
    Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
    parent_action_group_signature AgentActionGroupSignature

    If this field is set as AMAZON.UserInput , the agent can request the user for additional information when trying to complete a task. The description , apiSchema , and actionGroupExecutor fields must be blank for this action group.

    During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

    skip_resource_in_use_check_on_delete bool
    Specifies whether to allow deleting action group while it is in use.
    actionGroupName String
    Name of the action group
    actionGroupExecutor Property Map | Property Map
    The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.
    actionGroupState "ENABLED" | "DISABLED"
    Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
    apiSchema Property Map | Property Map
    Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas .
    description String
    Description of action group
    functionSchema Property Map
    Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
    parentActionGroupSignature "AMAZON.UserInput"

    If this field is set as AMAZON.UserInput , the agent can request the user for additional information when trying to complete a task. The description , apiSchema , and actionGroupExecutor fields must be blank for this action group.

    During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.

    skipResourceInUseCheckOnDelete Boolean
    Specifies whether to allow deleting action group while it is in use.

    AgentActionGroupExecutor0Properties, AgentActionGroupExecutor0PropertiesArgs

    Lambda string
    ARN of a Lambda.
    Lambda string
    ARN of a Lambda.
    lambda String
    ARN of a Lambda.
    lambda string
    ARN of a Lambda.
    lambda_ str
    ARN of a Lambda.
    lambda String
    ARN of a Lambda.

    AgentActionGroupExecutor1Properties, AgentActionGroupExecutor1PropertiesArgs

    AgentActionGroupSignature, AgentActionGroupSignatureArgs

    AmazonUserInput
    AMAZON.UserInput
    AgentActionGroupSignatureAmazonUserInput
    AMAZON.UserInput
    AmazonUserInput
    AMAZON.UserInput
    AmazonUserInput
    AMAZON.UserInput
    AMAZON_USER_INPUT
    AMAZON.UserInput
    "AMAZON.UserInput"
    AMAZON.UserInput

    AgentActionGroupState, AgentActionGroupStateArgs

    Enabled
    ENABLED
    Disabled
    DISABLED
    AgentActionGroupStateEnabled
    ENABLED
    AgentActionGroupStateDisabled
    DISABLED
    Enabled
    ENABLED
    Disabled
    DISABLED
    Enabled
    ENABLED
    Disabled
    DISABLED
    ENABLED
    ENABLED
    DISABLED
    DISABLED
    "ENABLED"
    ENABLED
    "DISABLED"
    DISABLED

    AgentApiSchema0Properties, AgentApiSchema0PropertiesArgs

    AgentApiSchema1Properties, AgentApiSchema1PropertiesArgs

    Payload string
    String OpenAPI Payload
    Payload string
    String OpenAPI Payload
    payload String
    String OpenAPI Payload
    payload string
    String OpenAPI Payload
    payload str
    String OpenAPI Payload
    payload String
    String OpenAPI Payload

    AgentCreationMode, AgentCreationModeArgs

    Default
    DEFAULT
    Overridden
    OVERRIDDEN
    AgentCreationModeDefault
    DEFAULT
    AgentCreationModeOverridden
    OVERRIDDEN
    Default
    DEFAULT
    Overridden
    OVERRIDDEN
    Default
    DEFAULT
    Overridden
    OVERRIDDEN
    DEFAULT
    DEFAULT
    OVERRIDDEN
    OVERRIDDEN
    "DEFAULT"
    DEFAULT
    "OVERRIDDEN"
    OVERRIDDEN

    AgentCustomControlMethod, AgentCustomControlMethodArgs

    ReturnControl
    RETURN_CONTROL
    AgentCustomControlMethodReturnControl
    RETURN_CONTROL
    ReturnControl
    RETURN_CONTROL
    ReturnControl
    RETURN_CONTROL
    RETURN_CONTROL
    RETURN_CONTROL
    "RETURN_CONTROL"
    RETURN_CONTROL

    AgentFunction, AgentFunctionArgs

    Name string
    Name for a resource.
    Description string
    Description of function
    Parameters Dictionary<string, Pulumi.AwsNative.Bedrock.Inputs.AgentParameterDetail>
    The parameters that the agent elicits from the user to fulfill the function.
    Name string
    Name for a resource.
    Description string
    Description of function
    Parameters map[string]AgentParameterDetail
    The parameters that the agent elicits from the user to fulfill the function.
    name String
    Name for a resource.
    description String
    Description of function
    parameters Map<String,AgentParameterDetail>
    The parameters that the agent elicits from the user to fulfill the function.
    name string
    Name for a resource.
    description string
    Description of function
    parameters {[key: string]: AgentParameterDetail}
    The parameters that the agent elicits from the user to fulfill the function.
    name str
    Name for a resource.
    description str
    Description of function
    parameters Mapping[str, AgentParameterDetail]
    The parameters that the agent elicits from the user to fulfill the function.
    name String
    Name for a resource.
    description String
    Description of function
    parameters Map<Property Map>
    The parameters that the agent elicits from the user to fulfill the function.

    AgentFunctionSchema, AgentFunctionSchemaArgs

    Functions []AgentFunction
    List of Function definitions
    functions List<AgentFunction>
    List of Function definitions
    functions AgentFunction[]
    List of Function definitions
    functions Sequence[AgentFunction]
    List of Function definitions
    functions List<Property Map>
    List of Function definitions

    AgentInferenceConfiguration, AgentInferenceConfigurationArgs

    MaximumLength double
    Maximum length of output
    StopSequences List<string>
    List of stop sequences
    Temperature double
    Controls randomness, higher values increase diversity
    TopK double
    Sample from the k most likely next tokens
    TopP double
    Cumulative probability cutoff for token selection
    MaximumLength float64
    Maximum length of output
    StopSequences []string
    List of stop sequences
    Temperature float64
    Controls randomness, higher values increase diversity
    TopK float64
    Sample from the k most likely next tokens
    TopP float64
    Cumulative probability cutoff for token selection
    maximumLength Double
    Maximum length of output
    stopSequences List<String>
    List of stop sequences
    temperature Double
    Controls randomness, higher values increase diversity
    topK Double
    Sample from the k most likely next tokens
    topP Double
    Cumulative probability cutoff for token selection
    maximumLength number
    Maximum length of output
    stopSequences string[]
    List of stop sequences
    temperature number
    Controls randomness, higher values increase diversity
    topK number
    Sample from the k most likely next tokens
    topP number
    Cumulative probability cutoff for token selection
    maximum_length float
    Maximum length of output
    stop_sequences Sequence[str]
    List of stop sequences
    temperature float
    Controls randomness, higher values increase diversity
    top_k float
    Sample from the k most likely next tokens
    top_p float
    Cumulative probability cutoff for token selection
    maximumLength Number
    Maximum length of output
    stopSequences List<String>
    List of stop sequences
    temperature Number
    Controls randomness, higher values increase diversity
    topK Number
    Sample from the k most likely next tokens
    topP Number
    Cumulative probability cutoff for token selection

    AgentKnowledgeBase, AgentKnowledgeBaseArgs

    Description string
    Description of the Resource.
    KnowledgeBaseId string
    Identifier for a resource.
    KnowledgeBaseState Pulumi.AwsNative.Bedrock.AgentKnowledgeBaseState
    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
    Description string
    Description of the Resource.
    KnowledgeBaseId string
    Identifier for a resource.
    KnowledgeBaseState AgentKnowledgeBaseState
    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
    description String
    Description of the Resource.
    knowledgeBaseId String
    Identifier for a resource.
    knowledgeBaseState AgentKnowledgeBaseState
    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
    description string
    Description of the Resource.
    knowledgeBaseId string
    Identifier for a resource.
    knowledgeBaseState AgentKnowledgeBaseState
    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
    description str
    Description of the Resource.
    knowledge_base_id str
    Identifier for a resource.
    knowledge_base_state AgentKnowledgeBaseState
    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
    description String
    Description of the Resource.
    knowledgeBaseId String
    Identifier for a resource.
    knowledgeBaseState "ENABLED" | "DISABLED"
    Specifies whether to use the knowledge base or not when sending an InvokeAgent request.

    AgentKnowledgeBaseState, AgentKnowledgeBaseStateArgs

    Enabled
    ENABLED
    Disabled
    DISABLED
    AgentKnowledgeBaseStateEnabled
    ENABLED
    AgentKnowledgeBaseStateDisabled
    DISABLED
    Enabled
    ENABLED
    Disabled
    DISABLED
    Enabled
    ENABLED
    Disabled
    DISABLED
    ENABLED
    ENABLED
    DISABLED
    DISABLED
    "ENABLED"
    ENABLED
    "DISABLED"
    DISABLED

    AgentParameterDetail, AgentParameterDetailArgs

    Type Pulumi.AwsNative.Bedrock.AgentType
    The data type of the parameter.
    Description string
    Description of function parameter.
    Required bool
    Information about if a parameter is required for function call. Default to false.
    Type AgentType
    The data type of the parameter.
    Description string
    Description of function parameter.
    Required bool
    Information about if a parameter is required for function call. Default to false.
    type AgentType
    The data type of the parameter.
    description String
    Description of function parameter.
    required Boolean
    Information about if a parameter is required for function call. Default to false.
    type AgentType
    The data type of the parameter.
    description string
    Description of function parameter.
    required boolean
    Information about if a parameter is required for function call. Default to false.
    type AgentType
    The data type of the parameter.
    description str
    Description of function parameter.
    required bool
    Information about if a parameter is required for function call. Default to false.
    type "string" | "number" | "integer" | "boolean" | "array"
    The data type of the parameter.
    description String
    Description of function parameter.
    required Boolean
    Information about if a parameter is required for function call. Default to false.

    AgentPromptConfiguration, AgentPromptConfigurationArgs

    BasePromptTemplate string
    Base Prompt Template.
    InferenceConfiguration Pulumi.AwsNative.Bedrock.Inputs.AgentInferenceConfiguration
    Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType . For more information, see Inference parameters for foundation models .
    ParserMode Pulumi.AwsNative.Bedrock.AgentCreationMode
    Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType . If you set the field as OVERRIDEN , the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
    PromptCreationMode Pulumi.AwsNative.Bedrock.AgentCreationMode
    Specifies whether to override the default prompt template for this promptType . Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate . If you leave it as DEFAULT , the agent uses a default prompt template.
    PromptState Pulumi.AwsNative.Bedrock.AgentPromptState
    Specifies whether to allow the agent to carry out the step specified in the promptType . If you set this value to DISABLED , the agent skips that step. The default state for each promptType is as follows.

    • PRE_PROCESSINGENABLED
    • ORCHESTRATIONENABLED
    • KNOWLEDGE_BASE_RESPONSE_GENERATIONENABLED
    • POST_PROCESSINGDISABLED
    PromptType Pulumi.AwsNative.Bedrock.AgentPromptType
    The step in the agent sequence that this prompt configuration applies to.
    BasePromptTemplate string
    Base Prompt Template.
    InferenceConfiguration AgentInferenceConfiguration
    Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType . For more information, see Inference parameters for foundation models .
    ParserMode AgentCreationMode
    Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType . If you set the field as OVERRIDEN , the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
    PromptCreationMode AgentCreationMode
    Specifies whether to override the default prompt template for this promptType . Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate . If you leave it as DEFAULT , the agent uses a default prompt template.
    PromptState AgentPromptState
    Specifies whether to allow the agent to carry out the step specified in the promptType . If you set this value to DISABLED , the agent skips that step. The default state for each promptType is as follows.

    • PRE_PROCESSINGENABLED
    • ORCHESTRATIONENABLED
    • KNOWLEDGE_BASE_RESPONSE_GENERATIONENABLED
    • POST_PROCESSINGDISABLED
    PromptType AgentPromptType
    The step in the agent sequence that this prompt configuration applies to.
    basePromptTemplate String
    Base Prompt Template.
    inferenceConfiguration AgentInferenceConfiguration
    Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType . For more information, see Inference parameters for foundation models .
    parserMode AgentCreationMode
    Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType . If you set the field as OVERRIDEN , the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
    promptCreationMode AgentCreationMode
    Specifies whether to override the default prompt template for this promptType . Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate . If you leave it as DEFAULT , the agent uses a default prompt template.
    promptState AgentPromptState
    Specifies whether to allow the agent to carry out the step specified in the promptType . If you set this value to DISABLED , the agent skips that step. The default state for each promptType is as follows.

    • PRE_PROCESSINGENABLED
    • ORCHESTRATIONENABLED
    • KNOWLEDGE_BASE_RESPONSE_GENERATIONENABLED
    • POST_PROCESSINGDISABLED
    promptType AgentPromptType
    The step in the agent sequence that this prompt configuration applies to.
    basePromptTemplate string
    Base Prompt Template.
    inferenceConfiguration AgentInferenceConfiguration
    Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType . For more information, see Inference parameters for foundation models .
    parserMode AgentCreationMode
    Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType . If you set the field as OVERRIDEN , the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
    promptCreationMode AgentCreationMode
    Specifies whether to override the default prompt template for this promptType . Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate . If you leave it as DEFAULT , the agent uses a default prompt template.
    promptState AgentPromptState
    Specifies whether to allow the agent to carry out the step specified in the promptType . If you set this value to DISABLED , the agent skips that step. The default state for each promptType is as follows.

    • PRE_PROCESSINGENABLED
    • ORCHESTRATIONENABLED
    • KNOWLEDGE_BASE_RESPONSE_GENERATIONENABLED
    • POST_PROCESSINGDISABLED
    promptType AgentPromptType
    The step in the agent sequence that this prompt configuration applies to.
    base_prompt_template str
    Base Prompt Template.
    inference_configuration AgentInferenceConfiguration
    Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType . For more information, see Inference parameters for foundation models .
    parser_mode AgentCreationMode
    Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType . If you set the field as OVERRIDEN , the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
    prompt_creation_mode AgentCreationMode
    Specifies whether to override the default prompt template for this promptType . Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate . If you leave it as DEFAULT , the agent uses a default prompt template.
    prompt_state AgentPromptState
    Specifies whether to allow the agent to carry out the step specified in the promptType . If you set this value to DISABLED , the agent skips that step. The default state for each promptType is as follows.

    • PRE_PROCESSINGENABLED
    • ORCHESTRATIONENABLED
    • KNOWLEDGE_BASE_RESPONSE_GENERATIONENABLED
    • POST_PROCESSINGDISABLED
    prompt_type AgentPromptType
    The step in the agent sequence that this prompt configuration applies to.
    basePromptTemplate String
    Base Prompt Template.
    inferenceConfiguration Property Map
    Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType . For more information, see Inference parameters for foundation models .
    parserMode "DEFAULT" | "OVERRIDDEN"
    Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType . If you set the field as OVERRIDEN , the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
    promptCreationMode "DEFAULT" | "OVERRIDDEN"
    Specifies whether to override the default prompt template for this promptType . Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate . If you leave it as DEFAULT , the agent uses a default prompt template.
    promptState "ENABLED" | "DISABLED"
    Specifies whether to allow the agent to carry out the step specified in the promptType . If you set this value to DISABLED , the agent skips that step. The default state for each promptType is as follows.

    • PRE_PROCESSINGENABLED
    • ORCHESTRATIONENABLED
    • KNOWLEDGE_BASE_RESPONSE_GENERATIONENABLED
    • POST_PROCESSINGDISABLED
    promptType "PRE_PROCESSING" | "ORCHESTRATION" | "POST_PROCESSING" | "KNOWLEDGE_BASE_RESPONSE_GENERATION"
    The step in the agent sequence that this prompt configuration applies to.

    AgentPromptOverrideConfiguration, AgentPromptOverrideConfigurationArgs

    PromptConfigurations []AgentPromptConfiguration
    List of BasePromptConfiguration
    OverrideLambda string
    ARN of a Lambda.
    promptConfigurations List<AgentPromptConfiguration>
    List of BasePromptConfiguration
    overrideLambda String
    ARN of a Lambda.
    promptConfigurations AgentPromptConfiguration[]
    List of BasePromptConfiguration
    overrideLambda string
    ARN of a Lambda.
    prompt_configurations Sequence[AgentPromptConfiguration]
    List of BasePromptConfiguration
    override_lambda str
    ARN of a Lambda.
    promptConfigurations List<Property Map>
    List of BasePromptConfiguration
    overrideLambda String
    ARN of a Lambda.

    AgentPromptState, AgentPromptStateArgs

    Enabled
    ENABLED
    Disabled
    DISABLED
    AgentPromptStateEnabled
    ENABLED
    AgentPromptStateDisabled
    DISABLED
    Enabled
    ENABLED
    Disabled
    DISABLED
    Enabled
    ENABLED
    Disabled
    DISABLED
    ENABLED
    ENABLED
    DISABLED
    DISABLED
    "ENABLED"
    ENABLED
    "DISABLED"
    DISABLED

    AgentPromptType, AgentPromptTypeArgs

    PreProcessing
    PRE_PROCESSING
    Orchestration
    ORCHESTRATION
    PostProcessing
    POST_PROCESSING
    KnowledgeBaseResponseGeneration
    KNOWLEDGE_BASE_RESPONSE_GENERATION
    AgentPromptTypePreProcessing
    PRE_PROCESSING
    AgentPromptTypeOrchestration
    ORCHESTRATION
    AgentPromptTypePostProcessing
    POST_PROCESSING
    AgentPromptTypeKnowledgeBaseResponseGeneration
    KNOWLEDGE_BASE_RESPONSE_GENERATION
    PreProcessing
    PRE_PROCESSING
    Orchestration
    ORCHESTRATION
    PostProcessing
    POST_PROCESSING
    KnowledgeBaseResponseGeneration
    KNOWLEDGE_BASE_RESPONSE_GENERATION
    PreProcessing
    PRE_PROCESSING
    Orchestration
    ORCHESTRATION
    PostProcessing
    POST_PROCESSING
    KnowledgeBaseResponseGeneration
    KNOWLEDGE_BASE_RESPONSE_GENERATION
    PRE_PROCESSING
    PRE_PROCESSING
    ORCHESTRATION
    ORCHESTRATION
    POST_PROCESSING
    POST_PROCESSING
    KNOWLEDGE_BASE_RESPONSE_GENERATION
    KNOWLEDGE_BASE_RESPONSE_GENERATION
    "PRE_PROCESSING"
    PRE_PROCESSING
    "ORCHESTRATION"
    ORCHESTRATION
    "POST_PROCESSING"
    POST_PROCESSING
    "KNOWLEDGE_BASE_RESPONSE_GENERATION"
    KNOWLEDGE_BASE_RESPONSE_GENERATION

    AgentS3Identifier, AgentS3IdentifierArgs

    S3BucketName string
    A bucket in S3.
    S3ObjectKey string
    A object key in S3.
    S3BucketName string
    A bucket in S3.
    S3ObjectKey string
    A object key in S3.
    s3BucketName String
    A bucket in S3.
    s3ObjectKey String
    A object key in S3.
    s3BucketName string
    A bucket in S3.
    s3ObjectKey string
    A object key in S3.
    s3_bucket_name str
    A bucket in S3.
    s3_object_key str
    A object key in S3.
    s3BucketName String
    A bucket in S3.
    s3ObjectKey String
    A object key in S3.

    AgentStatus, AgentStatusArgs

    Creating
    CREATING
    Preparing
    PREPARING
    Prepared
    PREPARED
    NotPrepared
    NOT_PREPARED
    Deleting
    DELETING
    Failed
    FAILED
    Versioning
    VERSIONING
    Updating
    UPDATING
    AgentStatusCreating
    CREATING
    AgentStatusPreparing
    PREPARING
    AgentStatusPrepared
    PREPARED
    AgentStatusNotPrepared
    NOT_PREPARED
    AgentStatusDeleting
    DELETING
    AgentStatusFailed
    FAILED
    AgentStatusVersioning
    VERSIONING
    AgentStatusUpdating
    UPDATING
    Creating
    CREATING
    Preparing
    PREPARING
    Prepared
    PREPARED
    NotPrepared
    NOT_PREPARED
    Deleting
    DELETING
    Failed
    FAILED
    Versioning
    VERSIONING
    Updating
    UPDATING
    Creating
    CREATING
    Preparing
    PREPARING
    Prepared
    PREPARED
    NotPrepared
    NOT_PREPARED
    Deleting
    DELETING
    Failed
    FAILED
    Versioning
    VERSIONING
    Updating
    UPDATING
    CREATING
    CREATING
    PREPARING
    PREPARING
    PREPARED
    PREPARED
    NOT_PREPARED
    NOT_PREPARED
    DELETING
    DELETING
    FAILED
    FAILED
    VERSIONING
    VERSIONING
    UPDATING
    UPDATING
    "CREATING"
    CREATING
    "PREPARING"
    PREPARING
    "PREPARED"
    PREPARED
    "NOT_PREPARED"
    NOT_PREPARED
    "DELETING"
    DELETING
    "FAILED"
    FAILED
    "VERSIONING"
    VERSIONING
    "UPDATING"
    UPDATING

    AgentType, AgentTypeArgs

    String
    string
    Number
    number
    Integer
    integer
    Boolean
    boolean
    Array
    array
    AgentTypeString
    string
    AgentTypeNumber
    number
    AgentTypeInteger
    integer
    AgentTypeBoolean
    boolean
    AgentTypeArray
    array
    String
    string
    Number
    number
    Integer
    integer
    Boolean
    boolean
    Array
    array
    String
    string
    Number
    number
    Integer
    integer
    Boolean
    boolean
    Array
    array
    STRING
    string
    NUMBER
    number
    INTEGER
    integer
    BOOLEAN
    boolean
    ARRAY
    array
    "string"
    string
    "number"
    number
    "integer"
    integer
    "boolean"
    boolean
    "array"
    array

    Package Details

    Repository
    AWS Native pulumi/pulumi-aws-native
    License
    Apache-2.0
    aws-native logo

    AWS Native is in preview. AWS Classic is fully supported.

    AWS Native v0.106.0 published on Monday, May 20, 2024 by Pulumi