Requests to Models

Requests can be made using the user interface via different options.

Make a prediction

The prediction can be made from the UI directly by pasting or uploading content. The response is then shown on the screen.

predict

Here the path to model is displayed and an option is provided to export a curl command for manual requests.

For manual requests from outside the cluster (i.e. not from UI), can be whitelisted for chosen paths using seldonctl whitelist. This sets the SKIP_AUTH_URI env var in the authservice component.

Load Test

This initiates a loadtest, which in the background is implemented using hey and exposes the same options as that tool

loadtest

The load test runs inside the cluster so can take time to be provisioned.