Updated on 2025-07-08 GMT+08:00

Running an Inference Service

Prerequisites

Running an Inference Service

  1. Log in to Workspace Management Console.
  2. Select the created workspace, click Access Workspace, and choose Resources and Assets > Ray Services.
  3. On the displayed page, obtain the inference address of the target Ray service from the Inference Address column.
  4. Call the inference address using the API tool or other methods to query the inference result.

    You can use curl for inference as shown in the following:

    curl -s -k --location -X POST 'https://fabric-inference-url/v1/workspaces/{workSpaceId}/endpoints/{endPointId}/rayservice/fruit' --header "X-Auth-Token: $(cat test.json)" --header 'Content-Type: application/json' --data-raw '["MANGO", 3]'

    The inference result is 9.

Viewing the Ray Dashboard

  1. Log in to Workspace Management Console.
  2. Select the created workspace, click Access Workspace, and choose Resources and Assets > Ray Services.
  3. On the displayed page, click the target Ray service name.
  4. On the displayed details page, choose the Overview tab and click View Now on the right of Dashboard. The Ray dashboard is displayed, where you can view details about the inference service.