Skip to content

Bedrock  >  Operations  >  update_custom_model_deployment

update_custom_model_deployment

Operation

update_custom_model_deployment async 

update_custom_model_deployment(input: UpdateCustomModelDeploymentInput, plugins: list[Plugin] | None = None) -> UpdateCustomModelDeploymentOutput

Updates a custom model deployment with a new custom model. This allows you to deploy updated models without creating new deployment endpoints.

Parameters:

Name Type Description Default
input UpdateCustomModelDeploymentInput

An instance of UpdateCustomModelDeploymentInput.

 required
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

Returns:

Type Description
UpdateCustomModelDeploymentOutput

An instance of UpdateCustomModelDeploymentOutput.

Input

UpdateCustomModelDeploymentInput dataclass

Dataclass for UpdateCustomModelDeploymentInput structure.

Attributes

custom_model_deployment_identifier class-attribute instance-attribute 
custom_model_deployment_identifier: str | None = None

Identifier of the custom model deployment to update with the new custom model.

model_arn class-attribute instance-attribute 
model_arn: str | None = None

ARN of the new custom model to deploy. This replaces the currently deployed model.

Output

UpdateCustomModelDeploymentOutput dataclass

Dataclass for UpdateCustomModelDeploymentOutput structure.

Attributes

custom_model_deployment_arn instance-attribute 
custom_model_deployment_arn: str

ARN of the custom model deployment being updated.

response_metadata class-attribute instance-attribute 
response_metadata: ResponseMetadata = field(default=EMPTY_RESPONSE_METADATA, repr=False, compare=False)

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.