Canary Promotion

Launch a SKLearn model and update model by canarying

Iris Model

iris

We will:

  • Deploy a pretrained sklearn iris model
  • Load test the model
  • View request payloads
  • Canary a new XGBoost model
  • Load test canary model
  • Promote the canary model

Deploy Model

Create the model using the wizard with a name of your choice and the model uri:

gs://seldon-models/sklearn/iris

All other defaults can be left as provided.

deploy1

Start Load Test

One the model is running start a load test with the following request payload:

Use the request.json file in this folder:

{
    "data": {
	"names": ["Sepal length","Sepal width","Petal length", "Petal Width"],
	"ndarray": [
	    [6.8,  2.8,  4.8,  1.4],
	    [6.1,  3.4,  4.5,  1.6]
	]
    }
}

load1

When running you should see metrics on dashboard. Enter the request logs screen to view requests. If this doesn’t work, consult the metrics or request logging docs section for debugging.

logs

You can also see core metrics from the dashboard.

metrics

Create Canary

Create an XGBoost canary model using the saved model at:

gs://seldon-models/xgboost/iris

canary

Rerun the load test and you should see metrics for both default and canary models.

canary-load

Promote the XGBoost Canary to be the main model.

promote

Last modified May 25, 2021