Skip to content

update_agent

Operation

update_agent

update_agent(request: UpdateAgentInput | UpdateAgentInputDict | None = None, /, *, plugins: list[Plugin] | None = None, **kwargs: Unpack[UpdateAgentInputDict]) -> UpdateAgentOutput

Updates the configuration of an agent.

Parameters:

Name Type Description Default
request UpdateAgentInput | UpdateAgentInputDict | None

The input as a model or dictionary. Pass this or keyword arguments, not both.

None
plugins list[Plugin] | None

A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations.

None
**kwargs Unpack[UpdateAgentInputDict]

The input fields as keyword arguments.

{}

Returns:

Type Description
UpdateAgentOutput

An instance of UpdateAgentOutput.

update_agent async

update_agent(request: UpdateAgentInput | UpdateAgentInputDict | None = None, /, *, plugins: list[Plugin] | None = None, **kwargs: Unpack[UpdateAgentInputDict]) -> UpdateAgentOutput

Updates the configuration of an agent.

Parameters:

Name Type Description Default
request UpdateAgentInput | UpdateAgentInputDict | None

The input as a model or dictionary. Pass this or keyword arguments, not both.

None
plugins list[Plugin] | None

A list of callables that modify the configuration dynamically. Changes made by these plugins only apply for the duration of the operation execution and will not affect any other operation invocations.

None
**kwargs Unpack[UpdateAgentInputDict]

The input fields as keyword arguments.

{}

Returns:

Type Description
UpdateAgentOutput

An instance of UpdateAgentOutput.

Input

Pass the input as keyword arguments, a positional dictionary, or a positional model object. Pass plugins separately as a keyword argument.

UpdateAgentInputDict

Bases: TypedDict

Dictionary form of UpdateAgentInput.

Attributes

agent_collaboration instance-attribute
agent_collaboration: str | None

The agent's collaboration role.

agent_id instance-attribute
agent_id: Required[str]

The unique identifier of the agent.

agent_name instance-attribute
agent_name: Required[str]

Specifies a new name for the agent.

agent_resource_role_arn instance-attribute
agent_resource_role_arn: Required[str]

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

custom_orchestration instance-attribute
custom_orchestration: CustomOrchestration | CustomOrchestrationDict | None

Contains details of the custom orchestration configured for the agent.

customer_encryption_key_arn instance-attribute
customer_encryption_key_arn: str | None

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

description instance-attribute
description: str | None

Specifies a new description of the agent.

foundation_model instance-attribute
foundation_model: Required[str]

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: GuardrailConfiguration | GuardrailConfigurationDict | None

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

idle_session_ttl_in_seconds instance-attribute
idle_session_ttl_in_seconds: int | None

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: str | None

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

memory_configuration instance-attribute
memory_configuration: MemoryConfiguration | MemoryConfigurationDict | None

Specifies the new memory configuration for the agent.

orchestration_type instance-attribute
orchestration_type: str | None

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: PromptOverrideConfiguration | PromptOverrideConfigurationDict | None

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

UpdateAgentInput dataclass

Bases: _SerdeShape

Dataclass for UpdateAgentInput structure.

Attributes

agent_collaboration class-attribute instance-attribute
agent_collaboration: str | None = ...

The agent's collaboration role.

agent_id class-attribute instance-attribute
agent_id: str | None = ...

The unique identifier of the agent.

agent_name class-attribute instance-attribute
agent_name: str | None = ...

Specifies a new name for the agent.

agent_resource_role_arn class-attribute instance-attribute
agent_resource_role_arn: str | None = ...

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

custom_orchestration class-attribute instance-attribute
custom_orchestration: CustomOrchestration | None = ...

Contains details of the custom orchestration configured for the agent.

customer_encryption_key_arn class-attribute instance-attribute
customer_encryption_key_arn: str | None = ...

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

description class-attribute instance-attribute
description: str | None = ...

Specifies a new description of the agent.

foundation_model class-attribute instance-attribute
foundation_model: str | None = ...

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 class-attribute instance-attribute
guardrail_configuration: GuardrailConfiguration | None = ...

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

idle_session_ttl_in_seconds class-attribute instance-attribute
idle_session_ttl_in_seconds: int | None = ...

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 class-attribute instance-attribute
instruction: str | None = ...

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

memory_configuration class-attribute instance-attribute
memory_configuration: MemoryConfiguration | None = ...

Specifies the new memory configuration for the agent.

orchestration_type class-attribute instance-attribute
orchestration_type: str | None = ...

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

prompt_override_configuration class-attribute instance-attribute
prompt_override_configuration: PromptOverrideConfiguration | None = ...

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

Output

UpdateAgentOutput dataclass

Bases: _SerdeShape

Dataclass for UpdateAgentOutput structure.

Attributes

agent instance-attribute
agent: Agent

Contains details about the agent that was updated.

response_metadata class-attribute instance-attribute
response_metadata: ResponseMetadata = ...

Metadata about the response that produced this output. Use this to recover the request identifiers a service's support team needs in order to investigate a call. Members of the metadata are individually optional.