Help Center/ ModelArts/ FAQs/ Service Deployment/ Service Deployment/ Real-Time Services/ Can a New-Version AI Application Still Use the Original API?
Updated on 2024-06-15 GMT+08:00

Can a New-Version AI Application Still Use the Original API?

ModelArts supports multiple model versions and flexible traffic policies to smoothly gray upgrade model versions. After a service is modified to deploy a new-version model or its model version is upgraded, the original service prediction API remains unchanged.

To adjust a model version, perform the operations described in this section.

Prerequisites

Procedure

  1. Log in to the ModelArts management console. In the navigation pane on the left, choose Service Deployment > Real-Time Services. The Real-Time Services page is displayed.
  2. Locate the target service and click Modify in the Operation column. The Modify Service page is displayed.
  3. In the AI Application and Configuration area, click Add AI Application Version and Configuration to add a new version.
    Figure 1 Add AI Application Version and Configuration
  4. Set the traffic proportion of the two versions. Service calling requests are allocated based on the proportion. For details about other settings, see Parameters. After the setting, click Next.
  5. Confirm the information and click Submit.