fix: remove Optional type hint on deploy

Author: sasha-gitg

google/cloud/aiplatform/models.py

@@ -470,14 +470,13 @@ def deploy(
         self,
         model: "Model",
         deployed_model_display_name: Optional[str] = None,
-        traffic_percentage: int = 0,
+        traffic_percentage: Optional[int] = 0,
         traffic_split: Optional[Dict[str, int]] = None,
         machine_type: Optional[str] = None,
         min_replica_count: int = 1,
         max_replica_count: int = 1,
         accelerator_type: Optional[str] = None,
         accelerator_count: Optional[int] = None,
-        service_account: Optional[str] = None,
         explanation_metadata: Optional[explain.ExplanationMetadata] = None,
         explanation_parameters: Optional[explain.ExplanationParameters] = None,
         metadata: Optional[Sequence[Tuple[str, str]]] = (),
@@ -532,13 +531,6 @@ def deploy(
                 NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4, TPU_V2, TPU_V3
             accelerator_count (int):
                 Optional. The number of accelerators to attach to a worker replica.
-            service_account (str):
-                The service account that the DeployedModel's container runs as. Specify the
-                email address of the service account. If this service account is not
-                specified, the container runs as a service account that doesn't have access
-                to the resource project.
-                Users deploying the Model must have the `iam.serviceAccounts.actAs`
-                permission on this service account.
             explanation_metadata (explain.ExplanationMetadata):
                 Optional. Metadata describing the Model's input and output for explanation.
                 Both `explanation_metadata` and `explanation_parameters` must be
@@ -577,7 +569,6 @@ def deploy(
             max_replica_count=max_replica_count,
             accelerator_type=accelerator_type,
             accelerator_count=accelerator_count,
-            service_account=service_account,
             explanation_metadata=explanation_metadata,
             explanation_parameters=explanation_parameters,
             metadata=metadata,
@@ -592,11 +583,10 @@ def _deploy(
         traffic_percentage: Optional[int] = 0,
         traffic_split: Optional[Dict[str, int]] = None,
         machine_type: Optional[str] = None,
-        min_replica_count: Optional[int] = 1,
-        max_replica_count: Optional[int] = 1,
+        min_replica_count: int = 1,
+        max_replica_count: int = 1,
         accelerator_type: Optional[str] = None,
         accelerator_count: Optional[int] = None,
-        service_account: Optional[str] = None,
         explanation_metadata: Optional[explain.ExplanationMetadata] = None,
         explanation_parameters: Optional[explain.ExplanationParameters] = None,
         metadata: Optional[Sequence[Tuple[str, str]]] = (),
@@ -651,13 +641,6 @@ def _deploy(
                 NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4, TPU_V2, TPU_V3
             accelerator_count (int):
                 Optional. The number of accelerators to attach to a worker replica.
-            service_account (str):
-                The service account that the DeployedModel's container runs as. Specify the
-                email address of the service account. If this service account is not
-                specified, the container runs as a service account that doesn't have access
-                to the resource project.
-                Users deploying the Model must have the `iam.serviceAccounts.actAs`
-                permission on this service account.
             explanation_metadata (explain.ExplanationMetadata):
                 Optional. Metadata describing the Model's input and output for explanation.
                 Both `explanation_metadata` and `explanation_parameters` must be
@@ -694,7 +677,6 @@ def _deploy(
             max_replica_count=max_replica_count,
             accelerator_type=accelerator_type,
             accelerator_count=accelerator_count,
-            service_account=service_account,
             explanation_metadata=explanation_metadata,
             explanation_parameters=explanation_parameters,
             metadata=metadata,
@@ -715,11 +697,10 @@ def _deploy_call(
         traffic_percentage: Optional[int] = 0,
         traffic_split: Optional[Dict[str, int]] = None,
         machine_type: Optional[str] = None,
-        min_replica_count: Optional[int] = 1,
-        max_replica_count: Optional[int] = 1,
+        min_replica_count: int = 1,
+        max_replica_count: int = 1,
         accelerator_type: Optional[str] = None,
         accelerator_count: Optional[int] = None,
-        service_account: Optional[str] = None,
         explanation_metadata: Optional[explain.ExplanationMetadata] = None,
         explanation_parameters: Optional[explain.ExplanationParameters] = None,
         metadata: Optional[Sequence[Tuple[str, str]]] = (),
@@ -772,13 +753,6 @@ def _deploy_call(
                 is not provided, the larger value of min_replica_count or 1 will
                 be used. If value provided is smaller than min_replica_count, it
                 will automatically be increased to be min_replica_count.
-            service_account (str):
-                The service account that the DeployedModel's container runs as. Specify the
-                email address of the service account. If this service account is not
-                specified, the container runs as a service account that doesn't have access
-                to the resource project.
-                Users deploying the Model must have the `iam.serviceAccounts.actAs`
-                permission on this service account.
             explanation_metadata (explain.ExplanationMetadata):
                 Optional. Metadata describing the Model's input and output for explanation.
                 Both `explanation_metadata` and `explanation_parameters` must be
@@ -814,12 +788,6 @@ def _deploy_call(
             gca_endpoint = gca_endpoint_v1beta1
             gca_machine_resources = gca_machine_resources_v1beta1
 
-        deployed_model = gca_endpoint.DeployedModel(
-            model=model_resource_name,
-            display_name=deployed_model_display_name,
-            service_account=service_account,
-        )
-
         if machine_type:
             machine_spec = gca_machine_resources.MachineSpec(machine_type=machine_type)
 
@@ -828,17 +796,26 @@ def _deploy_call(
                 machine_spec.accelerator_type = accelerator_type
                 machine_spec.accelerator_count = accelerator_count
 
-            deployed_model.dedicated_resources = gca_machine_resources.DedicatedResources(
+            dedicated_resources = gca_machine_resources.DedicatedResources(
                 machine_spec=machine_spec,
                 min_replica_count=min_replica_count,
                 max_replica_count=max_replica_count,
             )
-
+            deployed_model = gca_endpoint.DeployedModel(
+                dedicated_resources=dedicated_resources,
+                model=model_resource_name,
+                display_name=deployed_model_display_name,
+            )
         else:
-            deployed_model.automatic_resources = gca_machine_resources.AutomaticResources(
+            automatic_resources = gca_machine_resources.AutomaticResources(
                 min_replica_count=min_replica_count,
                 max_replica_count=max_replica_count,
             )
+            deployed_model = gca_endpoint.DeployedModel(
+                automatic_resources=automatic_resources,
+                model=model_resource_name,
+                display_name=deployed_model_display_name,
+            )
 
         # Service will throw error if both metadata and parameters are not provided
         if explanation_metadata and explanation_parameters:
@@ -1512,11 +1489,10 @@ def deploy(
         traffic_percentage: Optional[int] = 0,
         traffic_split: Optional[Dict[str, int]] = None,
         machine_type: Optional[str] = None,
-        min_replica_count: Optional[int] = 1,
-        max_replica_count: Optional[int] = 1,
+        min_replica_count: int = 1,
+        max_replica_count: int = 1,
         accelerator_type: Optional[str] = None,
         accelerator_count: Optional[int] = None,
-        service_account: Optional[str] = None,
         explanation_metadata: Optional[explain.ExplanationMetadata] = None,
         explanation_parameters: Optional[explain.ExplanationParameters] = None,
         metadata: Optional[Sequence[Tuple[str, str]]] = (),
@@ -1572,13 +1548,6 @@ def deploy(
                 NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4, TPU_V2, TPU_V3
             accelerator_count (int):
                 Optional. The number of accelerators to attach to a worker replica.
-            service_account (str):
-                The service account that the DeployedModel's container runs as. Specify the
-                email address of the service account. If this service account is not
-                specified, the container runs as a service account that doesn't have access
-                to the resource project.
-                Users deploying the Model must have the `iam.serviceAccounts.actAs`
-                permission on this service account.
             explanation_metadata (explain.ExplanationMetadata):
                 Optional. Metadata describing the Model's input and output for explanation.
                 Both `explanation_metadata` and `explanation_parameters` must be
@@ -1632,7 +1601,6 @@ def deploy(
             max_replica_count=max_replica_count,
             accelerator_type=accelerator_type,
             accelerator_count=accelerator_count,
-            service_account=service_account,
             explanation_metadata=explanation_metadata,
             explanation_parameters=explanation_parameters,
             metadata=metadata,
@@ -1649,11 +1617,10 @@ def _deploy(
         traffic_percentage: Optional[int] = 0,
         traffic_split: Optional[Dict[str, int]] = None,
         machine_type: Optional[str] = None,
-        min_replica_count: Optional[int] = 1,
-        max_replica_count: Optional[int] = 1,
+        min_replica_count: int = 1,
+        max_replica_count: int = 1,
         accelerator_type: Optional[str] = None,
         accelerator_count: Optional[int] = None,
-        service_account: Optional[str] = None,
         explanation_metadata: Optional[explain.ExplanationMetadata] = None,
         explanation_parameters: Optional[explain.ExplanationParameters] = None,
         metadata: Optional[Sequence[Tuple[str, str]]] = (),
@@ -1709,13 +1676,6 @@ def _deploy(
                 NVIDIA_TESLA_V100, NVIDIA_TESLA_P4, NVIDIA_TESLA_T4, TPU_V2, TPU_V3
             accelerator_count (int):
                 Optional. The number of accelerators to attach to a worker replica.
-            service_account (str):
-                The service account that the DeployedModel's container runs as. Specify the
-                email address of the service account. If this service account is not
-                specified, the container runs as a service account that doesn't have access
-                to the resource project.
-                Users deploying the Model must have the `iam.serviceAccounts.actAs`
-                permission on this service account.
             explanation_metadata (explain.ExplanationMetadata):
                 Optional. Metadata describing the Model's input and output for explanation.
                 Both `explanation_metadata` and `explanation_parameters` must be
@@ -1772,7 +1732,6 @@ def _deploy(
             max_replica_count=max_replica_count,
             accelerator_type=accelerator_type,
             accelerator_count=accelerator_count,
-            service_account=service_account,
             explanation_metadata=explanation_metadata,
             explanation_parameters=explanation_parameters,
             metadata=metadata,