Oracle Cloud Infrastructure Documentation

Deactivating and Activating a Model Deployment

Activate a deactivated Data Science model deployment or deactivate an active one.

Deactivating a model deployment has the following effects:

  • The instances associated with the model deployment shut down.

  • Metering and billing of the model deployment instances and load balancer stop.

  • The deployment HTTP endpoint becomes unavailable.

  • The model deployment metadata is saved.

A deactivated model deployment can be reactivated. The same model HTTP endpoint is available upon reactivation, and requests can be made to that model endpoint.

When a model deployment is in the Inactive state, you can change all of the options at one time and save the changes. The same isn't true when a model deployment is Active. See editing a model deployment.

    1. Use the Console to sign in to a tenancy with the necessary policies.
    2. Open the navigation menu and click Analytics & AI. Under Machine Learning, click Data Science.
    3. Select the compartment that contains the project with the model deployments.

      All projects in the compartment are listed.

    4. Click the name of the project.

      The project details page opens and lists the notebook sessions.

    5. Under Resources, click Model deployments.

      A tabular list of model deployments in the project is displayed.

    6. Click the name of a model deployment.
    7. Click Deactivate or Activate.

  • Use the oci data-science model-deployment activate and oci data-science model-deployment deactivate commands and required parameters:

    oci data-science model-deployment activate --notebook-session-id  <model-deployment-id>.-c [<text>].. [OPTIONS]
    oci data-science model-deployment deactivate --notebook-session-id  <model-deployment-id>.-c [<text>].. [OPTIONS]

    For a complete list of flags and variable options for CLI commands, see the CLI Command Reference.

  • Use the ActivateModelDeployment and DeactivateModelDeployment operations to activate or deactivate a model deployment.