There are a lot of elements to
a real time service deployment. These can include the trained model,
the runtime environment configuration, the scoring script, the container image,
and the container host. Troubleshooting a failed deployment or an error when consuming a deployed
service can be complex. As an initial troubleshooting step,
you can check the status of a service by examining its state through the get
the deployed service method. It's important to note that to
view the state of a service, you must use the compute specific
service type, for example, a KS web service and
not a generic web service object. For an operational service,
the state should be healthy. If a service is not healthy or
you are experiencing errors when using it, you can review its logs. You can review these logs using a code,
the logs include detailed information about the provisioning of the service and
the requests it has processed. These can often provide an insight
into the cause of unexpected errors. Deployment and
runtime errors can be easier to diagnose, you can do this by deploying the service
as a container in a local docker instance. You can then test the locally
deployed service using the SDK. You can then troubleshoot runtime issues
by making changes to the scoring file that is referenced in
the inference configuration. Then reloading the service
without redeploying it, something you can only
do with a local service.