On the databricks notebook itself, I can see that databricks.automl supports using recall as a primary metric
Help on function classify in module databricks.automl:
:param primary_metric: primary metric to select the best model. Each trial will compute several metrics, but this one determines which model is selected from all the trials. One of "f1" (default), "log_loss", "accuracy", "precision", "recall", "roc_auc".
But this blog didn't state that in the list of primary metrics