Help Center/
DataArts Fabric/
User Guide/
Ray Scenario/
Managing Ray Services/
Running an Inference Service
Updated on 2025-07-08 GMT+08:00
Running an Inference Service
Prerequisites
- You have a valid Huawei Cloud account. For details, see Creating an IAM User and Assigning Permissions to Use DataArtsFabric and Configuring DataArtsFabric Service Agency Permissions.
- You have at least one workspace available. For details, see Creating a Workspace.
- You have at least one Ray service. For details, see Creating a Ray Service.
Running an Inference Service
- Log in to Workspace Management Console.
- Select the created workspace, click Access Workspace, and choose Resources and Assets > Ray Services.
- On the displayed page, obtain the inference address of the target Ray service from the Inference Address column.
- 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
- Log in to Workspace Management Console.
- Select the created workspace, click Access Workspace, and choose Resources and Assets > Ray Services.
- On the displayed page, click the target Ray service name.
- 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.
Parent topic: Managing Ray Services
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
The system is busy. Please try again later.
For any further questions, feel free to contact us through the chatbot.
Chatbot