Oracle Cloud Infrastructure Documentation

Creating a Model Endpoint

To access a model in Language, create an endpoint for the model. You can run inferences on a trained model with the endpoint in Language.

    1. Open the navigation menu and select Analytics & AI. Under AI Services, select Language.
    2. In the left-side navigation menu, select Projects.
      The projects list page opens. All projects in the selected compartment are displayed in a table.
    3. On the Projects list page, select the name of the project.

      The project details page opens.

    4. Under Resources, select Model endpoints.

      The model endpoints list page opens. All model endpoints are displayed in a table.

    5. Click Create model endpoint.
    6. (Optional) Enter a unique name (255 character limit) for the resource.

      If you don't provide a name, one is automatically generated. For example, ailanguage<resource>20230825155844.

    7. (Optional) Enter a description (400 character limit) for the resource.
    8. Select a model to associate the model endpoint with.
    9. (Optional) Enter an Inference unit count. The maximum is 10.

      Inference units are Compute resources dedicated to the endpoint. You must have at least one inference unit allocated to an endpoint to perform inferences on it. You're charged for the number of hours each inference unit is associated with the endpoint.

    10. (Optional) Select Show advanced options to assign tags to the job. Tags help you to easily find and track resources by selecting a tag namespace, and then entering the key and value.

      To add more than one tag, select Add tag.

      Tagging describes the various tags that you can use organize and find resources including cost-tracking tags.

    11. (Optional) To use a different endpoint for the project, enter a unique alias name.
    12. (Optional) Select View detail page on clicking create to go directly to the resource details page after creation.
    13. Click Create model endpoint.
    The model endpoint is created. The create process can take a couple of minutes. When the model endpoint is created successfully, the model endpoint is in an ACTIVE state and can be used.

  • Use the oci ai language endpoint create command and required parameters to create a model endpoint:

    oci ai language endpoint create --compartment-id <compartment-id> -c [<name>]... [OPTIONS]

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

  • Run the CreateEndpoint operation to create model endpoints.