SageMaker Inference Agent¶

This guide provides an overview of how to set up the SageMaker inference agent in your Flyte deployment.

Specify agent configuration¶

Edit the relevant YAML file to specify the agent.

kubectl edit configmap flyte-sandbox-config -n flyte

tasks:
  task-plugins:
    enabled-plugins:
      - container
      - sidecar
      - k8s-array
      - agent-service
    default-for-task-types:
      - container: container
      - container_array: k8s-array
      - boto: agent-service
      - sagemaker-endpoint: agent-service
plugins:
  agent-service:
    supportedTaskTypes:
    - boto
    - sagemaker-endpoint

Create a file named values-override.yaml and add the following configuration to it:

configmap:
  enabled_plugins:
    tasks:
      task-plugins:
        enabled-plugins:
          - container
          - sidecar
          - k8s-array
          - agent-service
        default-for-task-types:
          container: container
          sidecar: sidecar
          container_array: k8s-array
          boto: agent-service
          sagemaker-endpoint: agent-service
    plugins:
      agent-service:
        supportedTaskTypes:
        - boto
        - sagemaker-endpoint

AWS credentials¶

When running the code locally, you can set AWS credentials as environment variables. When running on a production AWS cluster, the IAM role is used by default. Ensure that it has the AmazonSageMakerFullAccess policy attached.

Upgrade the Flyte Helm release¶

helm upgrade <RELEASE_NAME> flyteorg/flyte-binary -n <YOUR_NAMESPACE> --values <YOUR_YAML_FILE>

Replace <RELEASE_NAME> with the name of your release (e.g., flyte-backend), <YOUR_NAMESPACE> with the name of your namespace (e.g., flyte), and <YOUR_YAML_FILE> with the name of your YAML file.

helm upgrade <RELEASE_NAME> flyte/flyte-core -n <YOUR_NAMESPACE> --values values-override.yaml

Replace <RELEASE_NAME> with the name of your release (e.g., flyte) and <YOUR_NAMESPACE> with the name of your namespace (e.g., flyte).

You can refer to the documentation here.