Skip to content

UpdateAgentRequest

Source code in docs_src/capo_bedrock_agent/types/update_agent_request.py
class UpdateAgentRequest(TypedDict, closed=True):
    agent_id: "capo_bedrock_agent.types.id.Id"
    """<p>The unique identifier of the agent.</p>"""
    agent_name: "capo_bedrock_agent.types.name.Name"
    """<p>Specifies a new name for the agent.</p>"""
    instruction: NotRequired["capo_bedrock_agent.types.instruction.Instruction"]
    """<p>Specifies new instructions that tell the agent what it should do and how it should interact with users.</p>"""
    foundation_model: NotRequired[
        "capo_bedrock_agent.types.model_identifier.ModelIdentifier"
    ]
    """<p>The identifier for the model that you want to be used for orchestration by the agent you create.</p> <p>The <code>modelId</code> to provide depends on the type of model or throughput that you use:</p> <ul> <li> <p>If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns">Amazon Bedrock base model IDs (on-demand throughput)</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html">Supported Regions and models for cross-region inference</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/prov-thru-use.html">Run inference using a Provisioned Throughput</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-use.html">Use a custom model in Amazon Bedrock</a> in the Amazon Bedrock User Guide.</p> </li> <li> <p>If you use an <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-customization-import-model.html">imported model</a>, specify the ARN of the imported model. You can get the model ARN from a successful call to <a href="https://docs.aws.amazon.com/bedrock/latest/APIReference/API_CreateModelImportJob.html">CreateModelImportJob</a> or from the Imported models page in the Amazon Bedrock console.</p> </li> </ul>"""
    description: NotRequired["capo_bedrock_agent.types.description.Description"]
    """<p>Specifies a new description of the agent.</p>"""
    orchestration_type: NotRequired[
        "capo_bedrock_agent.types.orchestration_type.OrchestrationType"
    ]
    """<p> Specifies the type of orchestration strategy for the agent. This is set to <code>DEFAULT</code> orchestration type, by default. </p>"""
    custom_orchestration: NotRequired[
        "capo_bedrock_agent.types.custom_orchestration.CustomOrchestration"
    ]
    """<p> Contains details of the custom orchestration configured for the agent. </p>"""
    idle_session_ttl_in_seconds: NotRequired[
        "capo_bedrock_agent.types.session_ttl.SessionTTL"
    ]
    """<p>The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.</p> <p>A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.</p>"""
    agent_resource_role_arn: "capo_bedrock_agent.types.agent_role_arn.AgentRoleArn"
    """<p>The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.</p>"""
    customer_encryption_key_arn: NotRequired[
        "capo_bedrock_agent.types.kms_key_arn.KmsKeyArn"
    ]
    """<p>The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.</p>"""
    prompt_override_configuration: NotRequired[
        "capo_bedrock_agent.types.prompt_override_configuration.PromptOverrideConfiguration"
    ]
    """<p>Contains configurations to override prompts in different parts of an agent sequence. For more information, see <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/advanced-prompts.html">Advanced prompts</a>.</p>"""
    guardrail_configuration: NotRequired[
        "capo_bedrock_agent.types.guardrail_configuration.GuardrailConfiguration"
    ]
    """<p>The unique Guardrail configuration assigned to the agent when it is updated.</p>"""
    memory_configuration: NotRequired[
        "capo_bedrock_agent.types.memory_configuration.MemoryConfiguration"
    ]
    """<p>Specifies the new memory configuration for the agent. </p>"""
    agent_collaboration: NotRequired[
        "capo_bedrock_agent.types.agent_collaboration.AgentCollaboration"
    ]
    """<p>The agent's collaboration role.</p>"""

agent_collaboration instance-attribute

agent_collaboration: NotRequired[AgentCollaboration]

The agent's collaboration role.

agent_id instance-attribute

agent_id: Id

The unique identifier of the agent.

agent_name instance-attribute

agent_name: Name

Specifies a new name for the agent.

agent_resource_role_arn instance-attribute

agent_resource_role_arn: AgentRoleArn

The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.

custom_orchestration instance-attribute

custom_orchestration: NotRequired[CustomOrchestration]

Contains details of the custom orchestration configured for the agent.

customer_encryption_key_arn instance-attribute

customer_encryption_key_arn: NotRequired[KmsKeyArn]

The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.

description instance-attribute

description: NotRequired[Description]

Specifies a new description of the agent.

foundation_model instance-attribute

foundation_model: NotRequired[ModelIdentifier]

The identifier for the model that you want to be used for orchestration by the agent you create.

The modelId to provide depends on the type of model or throughput that you use:

guardrail_configuration instance-attribute

guardrail_configuration: NotRequired[GuardrailConfiguration]

The unique Guardrail configuration assigned to the agent when it is updated.

idle_session_ttl_in_seconds instance-attribute

idle_session_ttl_in_seconds: NotRequired[SessionTTL]

The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.

A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.

instruction instance-attribute

instruction: NotRequired[Instruction]

Specifies new instructions that tell the agent what it should do and how it should interact with users.

memory_configuration instance-attribute

memory_configuration: NotRequired[MemoryConfiguration]

Specifies the new memory configuration for the agent.

orchestration_type instance-attribute

orchestration_type: NotRequired[OrchestrationType]

Specifies the type of orchestration strategy for the agent. This is set to DEFAULT orchestration type, by default.

prompt_override_configuration instance-attribute

prompt_override_configuration: NotRequired[PromptOverrideConfiguration]

Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.