Cloudera Docs

Creating a Cloudera AI Inference service instance using the UI

You can create a Cloudera AI Inference service instance using the UI.

Cloudera AI Inference service requires a compute cluster enabled Cloudera Data Platform environment. You must either create the compute cluster enabled environment or convert your existing environment. For more information, see Prerequisites for setting up Cloudera AI Inference service.
  1. In the Cloudera Data Platform console, click the Cloudera AI tile.

    The Cloudera AI Workbenches page displays.

  2. Click AI Inference Services under ADMINISTRATION on the left navigation menu.
    The AI Inference Services page is displayed.
  3. Click the Create AI Inference Service button.
    The Create AI Inference Service page is displayed.
  4. In the Name textbox, enter a name for the Cloudera AI Inference service instance.
  5. In the Select Environment dropdown list, select your Cloudera environment within which you want to create the service.
  6. In the Select Compute Cluster dropdown list, select the compute cluster.
  7. In CPU Node Groups, select the CPU instance type and autoscale range. You can add more than one CPU node group by clicking the + button.
  8. In GPU Node Groups, select the GPU instance type and autoscale range. You can add more than one GPU node group by clicking the + button.
  9. In Network Settings, select the subnets for worker nodes and load balancer. You can select multiple subnets.
  10. In Load Balancer Source Ranges, specify the IP ranges that are allowed to access the load balancer.
  11. Select the Enable Public IP Address for Load Balancer checkbox to make Cloudera AI Inference service available on the public internet. When disabled, it is assumed that connectivity is achieved through a corporate Virtual Private Cloud (VPC).
  12. In Static Subdomain, specify the static domain for the AI Inference Service.
  13. Select the Skip Validation checkbox if you do not want to perform the validation checks before provisioning this AI Inference Service.
  14. In Tags, add any custom key and value pairs for your own use.
  15. Click Create.