feat: add dedicated_resources to DeployedIndex in aiplatform v1beta1 index_endpoint.proto feat: add Scaling to OnlineServingConfig in aiplatform v1beta1 featurestore.proto chore: sort imports (#991)

* feat: add dedicated_resources to DeployedIndex in aiplatform v1beta1 index_endpoint.proto feat: add Scaling to OnlineServingConfig in aiplatform v1beta1 featurestore.proto chore: sort imports

PiperOrigin-RevId: 425395202

Source-Link: googleapis/googleapis@e3bcc1e

Source-Link: googleapis/googleapis-gen@62beef7
Copy-Tag: eyJwIjoiLmdpdGh1Yi8uT3dsQm90LnlhbWwiLCJoIjoiNjJiZWVmNzg1NTljOGJhYjQ3ZWNkMzZlZWQxYWE2YjY3OGRiNjA4OCJ9

* 🦉 Updates from OwlBot

See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md

Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
Co-authored-by: Yu-Han Liu <[email protected]>

Author: gcf-owl-bot[bot]

google/cloud/aiplatform_v1beta1/services/vizier_service/async_client.py

@@ -255,9 +255,7 @@ async def create_study(
 
         Returns:
             google.cloud.aiplatform_v1beta1.types.Study:
-                LINT.IfChange
                 A message representing a Study.
-
         """
         # Create or coerce a protobuf request object.
         # Quick check: If we got a request object, we should *not* have
@@ -328,9 +326,7 @@ async def get_study(
 
         Returns:
             google.cloud.aiplatform_v1beta1.types.Study:
-                LINT.IfChange
                 A message representing a Study.
-
         """
         # Create or coerce a protobuf request object.
         # Quick check: If we got a request object, we should *not* have
@@ -548,9 +544,7 @@ async def lookup_study(
 
         Returns:
             google.cloud.aiplatform_v1beta1.types.Study:
-                LINT.IfChange
                 A message representing a Study.
-
         """
         # Create or coerce a protobuf request object.
         # Quick check: If we got a request object, we should *not* have

google/cloud/aiplatform_v1beta1/services/vizier_service/client.py

@@ -478,9 +478,7 @@ def create_study(
 
         Returns:
             google.cloud.aiplatform_v1beta1.types.Study:
-                LINT.IfChange
                 A message representing a Study.
-
         """
         # Create or coerce a protobuf request object.
         # Quick check: If we got a request object, we should *not* have
@@ -551,9 +549,7 @@ def get_study(
 
         Returns:
             google.cloud.aiplatform_v1beta1.types.Study:
-                LINT.IfChange
                 A message representing a Study.
-
         """
         # Create or coerce a protobuf request object.
         # Quick check: If we got a request object, we should *not* have
@@ -771,9 +767,7 @@ def lookup_study(
 
         Returns:
             google.cloud.aiplatform_v1beta1.types.Study:
-                LINT.IfChange
                 A message representing a Study.
-
         """
         # Create or coerce a protobuf request object.
         # Quick check: If we got a request object, we should *not* have

google/cloud/aiplatform_v1beta1/types/custom_job.py

@@ -120,6 +120,7 @@ class CustomJob(proto.Message):
 
 class CustomJobSpec(proto.Message):
     r"""Represents the spec of a CustomJob.
+    Next Id: 14
 
     Attributes:
         worker_pool_specs (Sequence[google.cloud.aiplatform_v1beta1.types.WorkerPoolSpec]):

google/cloud/aiplatform_v1beta1/types/featurestore.py

@@ -81,13 +81,39 @@ class OnlineServingConfig(proto.Message):
 
         Attributes:
             fixed_node_count (int):
-                The number of nodes for each cluster. The
-                number of nodes will not scale automatically but
-                can be scaled manually by providing different
-                values when updating.
+                The number of nodes for each cluster. The number of nodes
+                will not scale automatically but can be scaled manually by
+                providing different values when updating. Only one of
+                ``fixed_node_count`` and ``scaling`` can be set. Setting one
+                will reset the other.
+            scaling (google.cloud.aiplatform_v1beta1.types.Featurestore.OnlineServingConfig.Scaling):
+                Online serving scaling configuration. Only one of
+                ``fixed_node_count`` and ``scaling`` can be set. Setting one
+                will reset the other.
         """
 
+        class Scaling(proto.Message):
+            r"""Online serving scaling configuration. If min_node_count and
+            max_node_count are set to the same value, the cluster will be
+            configured with the fixed number of node (no auto-scaling).
+
+            Attributes:
+                min_node_count (int):
+                    Required. The minimum number of nodes to
+                    scale down to. Must be greater than or equal to
+                    1.
+                max_node_count (int):
+                    The maximum number of nodes to scale up to. Must be greater
+                    or equal to min_node_count.
+            """
+
+            min_node_count = proto.Field(proto.INT32, number=1,)
+            max_node_count = proto.Field(proto.INT32, number=2,)
+
         fixed_node_count = proto.Field(proto.INT32, number=2,)
+        scaling = proto.Field(
+            proto.MESSAGE, number=4, message="Featurestore.OnlineServingConfig.Scaling",
+        )
 
     name = proto.Field(proto.STRING, number=1,)
     create_time = proto.Field(proto.MESSAGE, number=3, message=timestamp_pb2.Timestamp,)

google/cloud/aiplatform_v1beta1/types/index_endpoint.py

@@ -171,6 +171,15 @@ class DeployedIndex(proto.Message):
             don't provide SLA when min_replica_count=1). If
             max_replica_count is not set, the default value is
             min_replica_count. The max allowed replica count is 1000.
+        dedicated_resources (google.cloud.aiplatform_v1beta1.types.DedicatedResources):
+            Optional. A description of resources that are dedicated to
+            the DeployedIndex, and that need a higher degree of manual
+            configuration. If min_replica_count is not set, the default
+            value is 2 (we don't provide SLA when min_replica_count=1).
+            If max_replica_count is not set, the default value is
+            min_replica_count. The max allowed replica count is 1000.
+
+            Available machine types: n1-standard-16 n1-standard-32
         enable_access_logging (bool):
             Optional. If true, private endpoint's access
             logs are sent to StackDriver Logging.
@@ -227,6 +236,9 @@ class DeployedIndex(proto.Message):
     automatic_resources = proto.Field(
         proto.MESSAGE, number=7, message=machine_resources.AutomaticResources,
     )
+    dedicated_resources = proto.Field(
+        proto.MESSAGE, number=16, message=machine_resources.DedicatedResources,
+    )
     enable_access_logging = proto.Field(proto.BOOL, number=8,)
     deployed_index_auth_config = proto.Field(
         proto.MESSAGE, number=9, message="DeployedIndexAuthConfig",

google/cloud/aiplatform_v1beta1/types/model.py

@@ -397,7 +397,7 @@ class ModelContainerSpec(proto.Message):
     r"""Specification of a container for serving predictions. Some fields in
     this message correspond to fields in the `Kubernetes Container v1
     core
-    specification <https://v1-18.docs.kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core>`__.
+    specification <https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core>`__.
 
     Attributes:
         image_uri (str):
@@ -463,7 +463,7 @@ class ModelContainerSpec(proto.Message):
             this syntax with ``$$``; for example: $$(VARIABLE_NAME) This
             field corresponds to the ``command`` field of the Kubernetes
             Containers `v1 core
-            API <https://v1-18.docs.kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core>`__.
+            API <https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core>`__.
         args (Sequence[str]):
             Immutable. Specifies arguments for the command that runs
             when the container starts. This overrides the container's
@@ -502,7 +502,7 @@ class ModelContainerSpec(proto.Message):
             this syntax with ``$$``; for example: $$(VARIABLE_NAME) This
             field corresponds to the ``args`` field of the Kubernetes
             Containers `v1 core
-            API <https://v1-18.docs.kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core>`__.
+            API <https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core>`__.
         env (Sequence[google.cloud.aiplatform_v1beta1.types.EnvVar]):
             Immutable. List of environment variables to set in the
             container. After the container starts running, code running
@@ -535,7 +535,7 @@ class ModelContainerSpec(proto.Message):
 
             This field corresponds to the ``env`` field of the
             Kubernetes Containers `v1 core
-            API <https://v1-18.docs.kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core>`__.
+            API <https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core>`__.
         ports (Sequence[google.cloud.aiplatform_v1beta1.types.Port]):
             Immutable. List of ports to expose from the container.
             Vertex AI sends any prediction requests that it receives to
@@ -558,7 +558,7 @@ class ModelContainerSpec(proto.Message):
             Vertex AI does not use ports other than the first one
             listed. This field corresponds to the ``ports`` field of the
             Kubernetes Containers `v1 core
-            API <https://v1-18.docs.kubernetes.io/docs/reference/generated/kubernetes-api/v1.18/#container-v1-core>`__.
+            API <https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#container-v1-core>`__.
         predict_route (str):
             Immutable. HTTP path on the container to send prediction
             requests to. Vertex AI forwards requests sent using

google/cloud/aiplatform_v1beta1/types/model_deployment_monitoring_job.py

@@ -284,9 +284,10 @@ class ModelDeploymentMonitoringScheduleConfig(proto.Message):
 
     Attributes:
         monitor_interval (google.protobuf.duration_pb2.Duration):
-            Required. The model monitoring job running
+            Required. The model monitoring job scheduling
             interval. It will be rounded up to next full
-            hour.
+            hour. This defines how often the monitoring jobs
+            are triggered.
     """
 
     monitor_interval = proto.Field(

google/cloud/aiplatform_v1beta1/types/study.py

@@ -27,8 +27,7 @@
 
 
 class Study(proto.Message):
-    r"""LINT.IfChange
-    A message representing a Study.
+    r"""A message representing a Study.
 
     Attributes:
         name (str):

tests/unit/gapic/aiplatform_v1beta1/test_index_endpoint_service.py

@@ -43,6 +43,7 @@
 )
 from google.cloud.aiplatform_v1beta1.services.index_endpoint_service import pagers
 from google.cloud.aiplatform_v1beta1.services.index_endpoint_service import transports
+from google.cloud.aiplatform_v1beta1.types import accelerator_type
 from google.cloud.aiplatform_v1beta1.types import index_endpoint
 from google.cloud.aiplatform_v1beta1.types import index_endpoint as gca_index_endpoint
 from google.cloud.aiplatform_v1beta1.types import index_endpoint_service