AWS SageMaker Inference Agent¶
The AWS SageMaker inference agent allows you to deploy models, and create and trigger inference endpoints. You can also fully remove the SageMaker deployment.
Installation¶
To use the AWS SageMaker inference agent, run the following command:
pip install flytekitplugins-awssagemaker
Example usage¶
For a usage example, see AWS SageMaker inference agent example usage.
Local testing¶
To test an agent locally, create a class for the agent task that inherits from SyncAgentExecutorMixin or AsyncAgentExecutorMixin. These mixins can handle synchronous and synchronous tasks, respectively, and allow flytekit to mimic FlytePropeller’s behavior in calling the agent. For more information, see “Testing agents locally”.
Flyte deployment configuration¶
Note
If you are using a managed deployment of Flyte, you will need to contact your deployment administrator to configure agents in your deployment.
To enable the AWS SageMaker inference agent in your Flyte deployment, refer to the AWS SageMaker inference agent setup guide.