Request URI

A request URI of a service is the endpoint for calling an API. The endpoint is used to communicate and interact with the API.

To obtain the URI, perform the following steps:

1. Log in to ModelArts Studio.
2. Go to the target workspace.
3. Obtain the request URI.
   • Obtain the request URI of the model.
     • To call a deployed model, choose Model Development > Model Deployment in the navigation pane on the left. On the My Service tab page, click the model name in the model deployment list. On the Details tab page, obtain the request URI of the model.
       Figure 1 Calling a deployed model
       

       To call the NLP inference service you deployed, obtain the URL of the V1 API or the URI of the V2 API on the API Invoking page.

       Figure 2 Calling an NLP service
       
     • To call a preset model, choose Model Development > Model Deployment in the navigation pane on the left, click Call Path in the model list on the Preset service page, and obtain the request URI of the model.
       Figure 3 Calling a preset model