Oracle Cloud Infrastructure Documentation

About AI Quick Actions

AI Quick Actions makes it easy for you to browse foundation models, and deploy, fine-tune, and evaluate them inside Data Science notebooks.

Supported Compute Shapes

AI Quick Actions support the use of ARM CPUs and the GPUs supported by Data Science.

Accessing AI Quick Actions

AI Quick Actions are available from active notebook sessions. Create a notebook session if you don't already have one.
Note

To access model deployments using private endpoints, create a notebook session with the network type set to custom networking. The custom egress must reside in the same VCN and subnet as the private endpoint resource.

See AI Quick Actions - Overview on GitHub for more information.

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

      All projects in the compartment are listed.

    4. Select the name of the project.

      The project details page opens and lists the notebook sessions.

    5. Select the name of the notebook session.

      The notebook session details page opens.

    6. Select Open.

      The Jupyter Notebook web-based environment opens.

      When you open a notebook session, the Launcher tab is open and contains the main actions.

    7. Under Extensions, select AI Quick Actions.
      The AI Quick Actions page is displayed. It contains three tabs, Models, Deployments, and Evaluations.

  • For a complete list of parameters and values for AI Quick Actions CLI commands, see AI Quick Actions CLI.

  • This task can't be performed using the API.