googleapis · gcf-owl-bot · Jun 17, 2025 · Jun 18, 2025 · Jun 18, 2025 · Jun 18, 2025
diff --git a/docs/aiplatform_v1beta1/memory_bank_service.rst b/docs/aiplatform_v1beta1/memory_bank_service.rst
@@ -0,0 +1,10 @@
+MemoryBankService
+-----------------------------------
+
+.. automodule:: google.cloud.aiplatform_v1beta1.services.memory_bank_service
+    :members:
+    :inherited-members:
+
+.. automodule:: google.cloud.aiplatform_v1beta1.services.memory_bank_service.pagers
+    :members:
+    :inherited-members:
diff --git a/docs/aiplatform_v1beta1/services_.rst b/docs/aiplatform_v1beta1/services_.rst
@@ -22,6 +22,7 @@ Services for Google Cloud Aiplatform v1beta1 API
     job_service
     llm_utility_service
     match_service
+    memory_bank_service
     metadata_service
     migration_service
     model_garden_service

diff --git a/google/cloud/aiplatform_v1/__init__.py b/google/cloud/aiplatform_v1/__init__.py
@@ -203,6 +203,7 @@
 from .types.endpoint import DeployedModel
 from .types.endpoint import Endpoint
 from .types.endpoint import FasterDeploymentConfig
+from .types.endpoint import GenAiAdvancedFeaturesConfig
 from .types.endpoint import PredictRequestResponseLoggingConfig
 from .types.endpoint import PrivateEndpoints
 from .types.endpoint import SpeculativeDecodingSpec
@@ -680,6 +681,9 @@
 )
 from .types.model_evaluation import ModelEvaluation
 from .types.model_evaluation_slice import ModelEvaluationSlice
+from .types.model_garden_service import DeployOperationMetadata
+from .types.model_garden_service import DeployRequest
+from .types.model_garden_service import DeployResponse
 from .types.model_garden_service import GetPublisherModelRequest
 from .types.model_garden_service import PublisherModelView
 from .types.model_monitoring import ModelMonitoringAlertConfig
@@ -863,6 +867,7 @@
 from .types.service_networking import PscAutomatedEndpoints
 from .types.service_networking import PSCAutomationConfig
 from .types.service_networking import PscInterfaceConfig
+from .types.service_networking import PSCAutomationState
 from .types.specialist_pool import SpecialistPool
 from .types.specialist_pool_service import CreateSpecialistPoolOperationMetadata
 from .types.specialist_pool_service import CreateSpecialistPoolRequest
@@ -1302,6 +1307,9 @@
     "DeployModelOperationMetadata",
     "DeployModelRequest",
     "DeployModelResponse",
+    "DeployOperationMetadata",
+    "DeployRequest",
+    "DeployResponse",
     "DeployedIndex",
     "DeployedIndexAuthConfig",
     "DeployedIndexRef",
@@ -1409,6 +1417,7 @@
     "FunctionResponse",
     "GcsDestination",
     "GcsSource",
+    "GenAiAdvancedFeaturesConfig",
     "GenAiCacheServiceClient",
     "GenAiTuningServiceClient",
     "GenerateContentRequest",
@@ -1678,6 +1687,7 @@
     "NotebookServiceClient",
     "NotebookSoftwareConfig",
     "PSCAutomationConfig",
+    "PSCAutomationState",
     "PairwiseChoice",
     "PairwiseMetricInput",
     "PairwiseMetricInstance",

diff --git a/google/cloud/aiplatform_v1/gapic_metadata.json b/google/cloud/aiplatform_v1/gapic_metadata.json
@@ -3097,6 +3097,11 @@
         "grpc": {
           "libraryClient": "ModelGardenServiceClient",
           "rpcs": {
+            "Deploy": {
+              "methods": [
+                "deploy"
+              ]
+            },
             "GetPublisherModel": {
               "methods": [
                 "get_publisher_model"
@@ -3107,6 +3112,11 @@
         "grpc-async": {
           "libraryClient": "ModelGardenServiceAsyncClient",
           "rpcs": {
+            "Deploy": {
+              "methods": [
+                "deploy"
+              ]
+            },
             "GetPublisherModel": {
               "methods": [
                 "get_publisher_model"
@@ -3117,6 +3127,11 @@
         "rest": {
           "libraryClient": "ModelGardenServiceClient",
           "rpcs": {
+            "Deploy": {
+              "methods": [
+                "deploy"
+              ]
+            },
             "GetPublisherModel": {
               "methods": [
                 "get_publisher_model"

diff --git a/google/cloud/aiplatform_v1/services/endpoint_service/async_client.py b/google/cloud/aiplatform_v1/services/endpoint_service/async_client.py
@@ -1151,7 +1151,6 @@ async def sample_deploy_model():
                 # Initialize request argument(s)
                 deployed_model = aiplatform_v1.DeployedModel()
                 deployed_model.dedicated_resources.min_replica_count = 1803
-                deployed_model.model = "model_value"
 
                 request = aiplatform_v1.DeployModelRe
F438
quest(
                     endpoint="endpoint_value",
@@ -1482,7 +1481,6 @@ async def sample_mutate_deployed_model():
                 # Initialize request argument(s)
                 deployed_model = aiplatform_v1.DeployedModel()
                 deployed_model.dedicated_resources.min_replica_count = 1803
-                deployed_model.model = "model_value"
 
                 request = aiplatform_v1.MutateDeployedModelRequest(
                     endpoint="endpoint_value",

diff --git a/google/cloud/aiplatform_v1/services/endpoint_service/client.py b/google/cloud/aiplatform_v1/services/endpoint_service/client.py
@@ -1685,7 +1685,6 @@ def sample_deploy_model():
                 # Initialize request argument(s)
                 deployed_model = aiplatform_v1.DeployedModel()
                 deployed_model.dedicated_resources.min_replica_count = 1803
-                deployed_model.model = "model_value"
 
                 request = aiplatform_v1.DeployModelRequest(
                     endpoint="endpoint_value",
@@ -2008,7 +2007,6 @@ def sample_mutate_deployed_model():
                 # Initialize request argument(s)
                 deployed_model = aiplatform_v1.DeployedModel()
                 deployed_model.dedicated_resources.min_replica_count = 1803
-                deployed_model.model = "model_value"
 
                 request = aiplatform_v1.MutateDeployedModelRequest(
                     endpoint="endpoint_value",

diff --git a/google/cloud/aiplatform_v1/services/model_garden_service/async_client.py b/google/cloud/aiplatform_v1/services/model_garden_service/async_client.py
@@ -45,6 +45,8 @@
 except AttributeError:  # pragma: NO COVER
     OptionalRetry = Union[retries.AsyncRetry, object, None]  # type: ignore
 
+from google.api_core import operation  # type: ignore
+from google.api_core import operation_async  # type: ignore
 from google.cloud.aiplatform_v1.types import model
 from google.cloud.aiplatform_v1.types import model_garden_service
 from google.cloud.aiplatform_v1.types import publisher_model
@@ -78,6 +80,10 @@ class ModelGardenServiceAsyncClient:
     _DEFAULT_ENDPOINT_TEMPLATE = ModelGardenServiceClient._DEFAULT_ENDPOINT_TEMPLATE
     _DEFAULT_UNIVERSE = ModelGardenServiceClient._DEFAULT_UNIVERSE
 
+    endpoint_path = staticmethod(ModelGardenServiceClient.endpoint_path)
+    parse_endpoint_path = staticmethod(ModelGardenServiceClient.parse_endpoint_path)
+    model_path = staticmethod(ModelGardenServiceClient.model_path)
+    parse_model_path = staticmethod(ModelGardenServiceClient.parse_model_path)
     publisher_model_path = staticmethod(ModelGardenServiceClient.publisher_model_path)
     parse_publisher_model_path = staticmethod(
         ModelGardenServiceClient.parse_publisher_model_path
@@ -414,6 +420,107 @@ async def sample_get_publisher_model():
         # Done; return the response.
         return response
 
+    async def deploy(
+        self,
+        request: Optional[Union[model_garden_service.DeployRequest, dict]] = None,
+        *,
+        retry: OptionalRetry = gapic_v1.method.DEFAULT,
+        timeout: Union[float, object] = gapic_v1.method.DEFAULT,
+        metadata: Sequence[Tuple[str, Union[str, bytes]]] = (),
+    ) -> operation_async.AsyncOperation:
+        r"""Deploys a model to a new endpoint.
+
+        .. code-block:: python
+
+            # This snippet has been automatically generated and should be regarded as a
+            # code template only.
+            # It will require modifications to work:
+            # - It may require correct/in-range values for request initialization.
+            # - It may require specifying regional endpoints when creating the service
+            #   client as shown in:
+            #   https://googleapis.dev/python/google-api-core/latest/client_options.html
+            from google.cloud import aiplatform_v1
+
+            async def sample_deploy():
+                # Create a client
+                client = aiplatform_v1.ModelGardenServiceAsyncClient()
+
+                # Initialize request argument(s)
+                request = aiplatform_v1.DeployRequest(
+                    publisher_model_name="publisher_model_name_value",
+                    destination="destination_value",
+                )
+
+                # Make the request
+                operation = client.deploy(request=request)
+
+                print("Waiting for operation to complete...")
+
+                response = (await operation).result()
+
+                # Handle the response
+                print(response)
+
+        Args:
+            request (Optional[Union[google.cloud.aiplatform_v1.types.DeployRequest, dict]]):
+                The request object. Request message for
+                [ModelGardenService.Deploy][google.cloud.aiplatform.v1.ModelGardenService.Deploy].
+            retry (google.api_core.retry_async.AsyncRetry): Designation of what errors, if any,
+                should be retried.
+            timeout (float): The timeout for this request.
+            metadata (Sequence[Tuple[str, Union[str, bytes]]]): Key/value pairs which should be
+                sent along with the request as metadata. Normally, each value must be of type `str`,
+                but for metadata keys ending with the suffix `-bin`, the corresponding values must
+                be of type `bytes`.
+
+        Returns:
+            google.api_core.operation_async.AsyncOperation:
+                An object representing a long-running operation.
+
+                The result type for the operation will be :class:`google.cloud.aiplatform_v1.types.DeployResponse` Response message for
+                   [ModelGardenService.Deploy][google.cloud.aiplatform.v1.ModelGardenService.Deploy].
+
+        """
+        # Create or coerce a protobuf request object.
+        # - Use the request object if provided (there's no risk of modifying the input as
+        #   there are no flattened fields), or create one.
+        if not isinstance(request, model_garden_service.DeployRequest):
+            request = model_garden_service.DeployRequest(request)
+
+        # Wrap the RPC method; this adds retry and timeout information,
+        # and friendly error handling.
+        rpc = self._client._transport._wrapped_methods[self._client._transport.deploy]
+
+        # Certain fields should be provided within the metadata header;
+        # add these here.
+        metadata = tuple(metadata) + (
+            gapic_v1.routing_header.to_grpc_metadata(
+                (("destination", request.destination),)
+            ),
+        )
+
+        # Validate the universe domain.
+        self._client._validate_universe_domain()
+
+        # Send the request.
+        response = await rpc(
+            request,
+            retry=retry,
+            timeout=timeout,
+            metadata=metadata,
+        )
+
+        # Wrap the response in an operation future.
+        response = operation_async.from_gapic(
+            response,
+            self._client._transport.operations_client,
+            model_garden_service.DeployResponse,
+            metadata_type=model_garden_service.DeployOperationMetadata,
+        )
+
+        # Done; return the response.
+        return response
+
     async def list_operations(
         self,
         request: Optional[operations_pb2.ListOperationsRequest] = None,