Create a Model Serving platform

It’s time to repeat the same steps for the Time to Failure AI model. The steps will be quite similar, but make sure you specify the right path to our second model.

Time to Failure model

  1. Ensure you are in the Models tab inside our ai-edge-project project.

  2. Click on Deploy model.

  3. Complete again the following fields in the form:

    • Project: The ai-edge-project namespace should be already selected by default.

    • Model deployment name: Name for the Time to Failure model server.

    • Serving runtime: Choose OpenVINO Model Server runtime.

    • Model framework: Our model was saved in openvino_ir - opset13 format.

    • Model server replicas: Keep 1 for the number of pods.

    • Model server size: Assign Small to the server size.

    • Check the Existing data connection box.

    • Connection: Select again the s3-storage DataConnection.

    • Path: Our Time to Failure model was saved in models/time-to-failure/.

  4. Finally, click on Deploy.

Wait until you see a green checkmark in the Status column. Then, the Internal endpoint details will show the model inference API for our second AI model.

Time to Failure inference endpoint