Merge branch 'main' into fix--Fixed-getitng-project-ID-when-running-on-Vertex-AI

Author: Ark-kun

.github/CODEOWNERS

@@ -4,8 +4,8 @@
 # For syntax help see:
 # https://help.github.com/en/github/creating-cloning-and-archiving-repositories/about-code-owners#codeowners-syntax
 
-# yoshi-python is the default owner
-*                                      @googleapis/yoshi-python
+# @googleapis/cdpe-cloudai and yoshi-python are the default owners
+*                                      @googleapis/cdpe-cloudai @googleapis/yoshi-python
 
 # The AI Platform GAPIC libraries are owned by Cloud AI DPE
 /google/cloud/aiplatform_*/**          @googleapis/cdpe-cloudai

README.rst

@@ -111,7 +111,7 @@ Initialize the SDK to store common configurations that you use with the SDK.
         staging_bucket='gs://my_staging_bucket',
 
         # custom google.auth.credentials.Credentials
-        # environment default creds used if not set
+        # environment default credentials used if not set
         credentials=my_credentials,
 
         # customer managed encryption key resource name
@@ -188,7 +188,7 @@ Please visit `Using a managed dataset in a custom training application`_ for a d
 
 .. _Using a managed dataset in a custom training application: https://cloud.google.com/vertex-ai/docs/training/using-managed-datasets
 
-It must write the model artifact to the environment variable populated by the traing service:
+It must write the model artifact to the environment variable populated by the training service:
 
 .. code-block:: Python
 

google/cloud/aiplatform/base.py

@@ -98,7 +98,7 @@ def log_create_complete(
             cls (VertexAiResourceNoun):
                 Vertex AI Resource Noun class that is being created.
             resource (proto.Message):
-                Vertex AI Resourc proto.Message
+                Vertex AI Resource proto.Message
             variable_name (str): Name of variable to use for code snippet
         """
         self._logger.info(f"{cls.__name__} created. Resource name: {resource.name}")
@@ -121,7 +121,7 @@ def log_create_complete_with_getter(
             cls (VertexAiResourceNoun):
                 Vertex AI Resource Noun class that is being created.
             resource (proto.Message):
-                Vertex AI Resourc proto.Message
+                Vertex AI Resource proto.Message
             variable_name (str): Name of variable to use for code snippet
         """
         self._logger.info(f"{cls.__name__} created. Resource name: {resource.name}")
@@ -462,7 +462,7 @@ def __init__(
         Args:
             project(str): Project of the resource noun.
             location(str): The location of the resource noun.
-            credentials(google.auth.crendentials.Crendentials): Optional custom
+            credentials(google.auth.credentials.Credentials): Optional custom
                 credentials to use when accessing interacting with resource noun.
             resource_name(str): A fully-qualified resource name or ID.
         """
@@ -655,6 +655,15 @@ def gca_resource(self) -> proto.Message:
         self._assert_gca_resource_is_available()
         return self._gca_resource
 
+    @property
+    def _resource_is_available(self) -> bool:
+        """Returns True if GCA resource has been created and is available, otherwise False"""
+        try:
+            self._assert_gca_resource_is_available()
+            return True
+        except RuntimeError:
+            return False
+
     def _assert_gca_resource_is_available(self) -> None:
         """Helper method to raise when property is not accessible.
 
@@ -833,7 +842,7 @@ def __init__(
         Args:
             project (str): Optional. Project of the resource noun.
             location (str): Optional. The location of the resource noun.
-            credentials(google.auth.crendentials.Crendentials):
+            credentials(google.auth.credentials.Credentials):
                 Optional. custom credentials to use when accessing interacting with
                 resource noun.
             resource_name(str): A fully-qualified resource name or ID.
@@ -863,7 +872,7 @@ def _empty_constructor(
         Args:
             project (str): Optional. Project of the resource noun.
             location (str): Optional. The location of the resource noun.
-            credentials(google.auth.crendentials.Crendentials):
+            credentials(google.auth.credentials.Credentials):
                 Optional. custom credentials to use when accessing interacting with
                 resource noun.
             resource_name(str): A fully-qualified resource name or ID.
@@ -1153,7 +1162,7 @@ def delete(self, sync: bool = True) -> None:
         _LOGGER.log_action_completed_against_resource("deleted.", "", self)
 
     def __repr__(self) -> str:
-        if self._gca_resource:
+        if self._gca_resource and self._resource_is_available:
             return VertexAiResourceNoun.__repr__(self)
 
         return FutureManager.__repr__(self)

google/cloud/aiplatform/datasets/dataset.py

@@ -164,7 +164,7 @@ def create(
                 be picked randomly. Two DataItems are considered identical
                 if their content bytes are identical (e.g. image bytes or
                 pdf bytes). These labels will be overridden by Annotation
-                labels specified inside index file refenced by
+                labels specified inside index file referenced by
                 ``import_schema_uri``,
                 e.g. jsonl file.
             project (str):
@@ -488,7 +488,7 @@ def import_data(
                 be picked randomly. Two DataItems are considered identical
                 if their content bytes are identical (e.g. image bytes or
                 pdf bytes). These labels will be overridden by Annotation
-                labels specified inside index file refenced by
+                labels specified inside index file referenced by
                 ``import_schema_uri``,
                 e.g. jsonl file.
             sync (bool):

google/cloud/aiplatform/datasets/image_dataset.py

@@ -82,7 +82,7 @@ def create(
                 be picked randomly. Two DataItems are considered identical
                 if their content bytes are identical (e.g. image bytes or
                 pdf bytes). These labels will be overridden by Annotation
-                labels specified inside index file refenced by
+                labels specified inside index file referenced by
                 ``import_schema_uri``,
                 e.g. jsonl file.
             project (str):

google/cloud/aiplatform/datasets/text_dataset.py

@@ -89,7 +89,7 @@ def create(
                 be picked randomly. Two DataItems are considered identical
                 if their content bytes are identical (e.g. image bytes or
                 pdf bytes). These labels will be overridden by Annotation
-                labels specified inside index file refenced by
+                labels specified inside index file referenced by
                 ``import_schema_uri``,
                 e.g. jsonl file.
             project (str):

google/cloud/aiplatform/datasets/video_dataset.py

@@ -82,7 +82,7 @@ def create(
                 be picked randomly. Two DataItems are considered identical
                 if their content bytes are identical (e.g. image bytes or
                 pdf bytes). These labels will be overridden by Annotation
-                labels specified inside index file refenced by
+                labels specified inside index file referenced by
                 ``import_schema_uri``,
                 e.g. jsonl file.
             project (str):

google/cloud/aiplatform/explain/lit.py

@@ -29,23 +29,23 @@
 except ImportError:
     raise ImportError(
         "LIT is not installed and is required to get Dataset as the return format. "
-        'Please install the SDK using "pip install python-aiplatform[lit]"'
+        'Please install the SDK using "pip install google-cloud-aiplatform[lit]"'
     )
 
 try:
     import tensorflow as tf
 except ImportError:
     raise ImportError(
         "Tensorflow is not installed and is required to load saved model. "
-        'Please install the SDK using "pip install pip install python-aiplatform[lit]"'
+        'Please install the SDK using "pip install google-cloud-aiplatform[lit]"'
     )
 
 try:
     import pandas as pd
 except ImportError:
     raise ImportError(
         "Pandas is not installed and is required to read the dataset. "
-        'Please install Pandas using "pip install python-aiplatform[lit]"'
+        'Please install Pandas using "pip install google-cloud-aiplatform[lit]"'
     )
 
 

google/cloud/aiplatform/jobs.py

@@ -325,7 +325,7 @@ def output_info(self,) -> Optional[aiplatform.gapic.BatchPredictionJob.OutputInf
         """Information describing the output of this job, including output location
         into which prediction output is written.
 
-        This is only available for batch predicition jobs that have run successfully.
+        This is only available for batch prediction jobs that have run successfully.
         """
         self._assert_gca_resource_is_available()
         return self._gca_resource.output_info
@@ -839,7 +839,7 @@ def __init__(
         Args:
             project(str): Project of the resource noun.
             location(str): The location of the resource noun.
-            credentials(google.auth.crendentials.Crendentials): Optional custom
+            credentials(google.auth.credentials.Credentials): Optional custom
                 credentials to use when accessing interacting with resource noun.
         """
 
@@ -1023,7 +1023,7 @@ def __init__(
         encryption_spec_key_name: Optional[str] = None,
         staging_bucket: Optional[str] = None,
     ):
-        """Cosntruct a Custom Job with Worker Pool Specs.
+        """Constructs a Custom Job with Worker Pool Specs.
 
         ```
         Example usage:
@@ -1569,7 +1569,7 @@ def __init__(
                 Required. Configured CustomJob. The worker pool spec from this custom job
                 applies to the CustomJobs created in all the trials.
             metric_spec: Dict[str, str]
-                Required. Dicionary representing metrics to optimize. The dictionary key is the metric_id,
+                Required. Dictionary representing metrics to optimize. The dictionary key is the metric_id,
                 which is reported by your training job, and the dictionary value is the
                 optimization goal of the metric('minimize' or 'maximize'). example:
 
@@ -1594,7 +1594,7 @@ def __init__(
                 DoubleParameterSpec, IntegerParameterSpec, CategoricalParameterSpace, DiscreteParameterSpec
 
             max_trial_count (int):
-                Reuired. The desired total number of Trials.
+                Required. The desired total number of Trials.
             parallel_trial_count (int):
                 Required. The desired number of Trials to run in parallel.
             max_failed_trial_count (int):

google/cloud/aiplatform/matching_engine/matching_engine_index_endpoint.py

@@ -535,6 +535,8 @@ def deploy_index(
             MatchingEngineIndexEndpoint - IndexEndpoint resource object
         """
 
+        self.wait()
+
         _LOGGER.log_action_start_against_resource(
             "Deploying index", "index_endpoint", self,
         )
@@ -591,6 +593,8 @@ def undeploy_index(
             MatchingEngineIndexEndpoint - IndexEndpoint resource object
         """
 
+        self.wait()
+
         _LOGGER.log_action_start_against_resource(
             "Undeploying index", "index_endpoint", self,
         )
@@ -652,6 +656,8 @@ def mutate_deployed_index(
                 Optional. Strings which should be sent along with the request as metadata.
         """
 
+        self.wait()
+
         _LOGGER.log_action_start_against_resource(
             "Mutating index", "index_endpoint", self,
         )
@@ -691,6 +697,7 @@ def deployed_indexes(
         Returns:
             List[gca_matching_engine_index_endpoint.DeployedIndex] - Deployed indexes
         """
+        self._assert_gca_resource_is_available()
         return self._gca_resource.deployed_indexes
 
     @base.optional_sync()

google/cloud/aiplatform/metadata/metadata.py

@@ -155,7 +155,7 @@ def log_metrics(self, metrics: Dict[str, Union[float, int]]):
 
         Args:
             metrics (Dict):
-                Required. Metrics key/value pairs. Only flot and int are supported format for value.
+                Required. Metrics key/value pairs. Only float and int are supported format for value.
         Raises:
             TypeError: If value contains unsupported types.
             ValueError: If Experiment or Run is not set.
@@ -263,7 +263,7 @@ def _validate_metrics_value_type(metrics: Dict[str, Union[float, int]]):
 
         Args:
             metrics (Dict):
-                Required. Metrics key/value pairs. Only flot and int are supported format for value.
+                Required. Metrics key/value pairs. Only float and int are supported format for value.
         Raises:
             TypeError: If value contains unsupported types.
         """

google/cloud/aiplatform/models.py

@@ -1575,6 +1575,8 @@ def update(
             ValueError: If `labels` is not the correct format.
         """
 
+        self.wait()
+
         current_model_proto = self.gca_resource
         copied_model_proto = current_model_proto.__class__(current_model_proto)
 
@@ -2496,6 +2498,8 @@ def export_model(
             ValueError: If invalid arguments or export formats are provided.
         """
 
+        self.wait()
+
         # Model does not support exporting
         if not self.supported_export_formats:
             raise ValueError(f"The model `{self.resource_name}` is not exportable.")

google/cloud/aiplatform/tensorboard/uploader_utils.py

@@ -377,7 +377,7 @@ def get_or_create(
 
         Returns:
             time_series (tensorboard_time_series.TensorboardTimeSeries):
-                A new or existing tensorboard_time_series.TensorbaordTimeSeries.
+                A new or existing tensorboard_time_series.TensorboardTimeSeries.
 
         Raises:
             exceptions.InvalidArgument:

google/cloud/aiplatform/training_jobs.py

@@ -435,7 +435,7 @@ def _create_input_data_config(
                 -  AIP_TEST_DATA_URI = "bigquery_destination.dataset_*.test"
         Raises:
             ValueError: When more than 1 type of split configuration is passed or when
-                the split configuartion passed is incompatible with the dataset schema.
+                the split configuration passed is incompatible with the dataset schema.
         """
 
         input_data_config = None
@@ -5811,7 +5811,7 @@ def __init__(
                         multiple objects in shots and segments. You can use these
                         models to track objects in your videos according to your
                         own pre-defined, custom labels.
-                    "action_recognition" - A video action reconition model pinpoints
+                    "action_recognition" - A video action recognition model pinpoints
                         the location of actions with short temporal durations (~1 second).
             model_type: str = "CLOUD"
                 Required. One of the following:

google/cloud/aiplatform/utils/pipeline_utils.py

@@ -155,7 +155,7 @@ def _get_vertex_value(
           inputs, or value is none.
         """
         if value is None:
-            raise ValueError("None values should be filterd out.")
+            raise ValueError("None values should be filtered out.")
 
         if name not in self._parameter_types:
             raise ValueError(

google/cloud/aiplatform/utils/source_utils.py

@@ -71,7 +71,7 @@ class _TrainingScriptPythonPackager:
     packager = TrainingScriptPythonPackager('my_script.py', ['pandas', 'pytorch'])
     gcs_path = packager.package_and_copy_to_gcs(
         gcs_staging_dir='my-bucket',
-        project='my-prject')
+        project='my-project')
     module_name = packager.module_name
 
     The package after installed can be executed as:

google/cloud/aiplatform/utils/worker_spec_utils.py

@@ -186,7 +186,7 @@ def chief_worker_pool(
         reduction_server_replica_count: int = 0,
         reduction_server_machine_type: str = None,
     ) -> "_DistributedTrainingSpec":
-        """Parameterizes Config to support only chief with worker replicas.
+        """Parametrizes Config to support only chief with worker replicas.
 
         For replica is assigned to chief and the remainder to workers. All spec have the
         same machine type, accelerator count, and accelerator type.

google/cloud/aiplatform_v1/__init__.py

@@ -131,6 +131,7 @@
 from .types.feature_selector import FeatureSelector
 from .types.feature_selector import IdMatcher
 from .types.featurestore import Featurestore
+from .types.featurestore_monitoring import FeaturestoreMonitoringConfig
 from .types.featurestore_online_service import FeatureValue
 from .types.featurestore_online_service import FeatureValueList
 from .types.featurestore_online_service import ReadFeatureValuesRequest
@@ -672,6 +673,7 @@
     "FeatureValueDestination",
     "FeatureValueList",
     "Featurestore",
+    "FeaturestoreMonitoringConfig",
     "FeaturestoreOnlineServingServiceClient",
     "FeaturestoreServiceClient",
     "FilterSplit",

google/cloud/aiplatform_v1/services/featurestore_service/async_client.py

@@ -41,6 +41,7 @@
 from google.cloud.aiplatform_v1.types import feature as gca_feature
 from google.cloud.aiplatform_v1.types import featurestore
 from google.cloud.aiplatform_v1.types import featurestore as gca_featurestore
+from google.cloud.aiplatform_v1.types import featurestore_monitoring
 from google.cloud.aiplatform_v1.types import featurestore_service
 from google.cloud.aiplatform_v1.types import operation as gca_operation
 from google.protobuf import empty_pb2  # type: ignore
@@ -1202,7 +1203,12 @@ def sample_update_entity_type():
                 -  ``description``
                 -  ``labels``
                 -  ``monitoring_config.snapshot_analysis.disabled``
-                -  ``monitoring_config.snapshot_analysis.monitoring_interval``
+                -  ``monitoring_config.snapshot_analysis.monitoring_interval_days``
+                -  ``monitoring_config.snapshot_analysis.staleness_days``
+                -  ``monitoring_config.import_features_analysis.state``
+                -  ``monitoring_config.import_features_analysis.anomaly_detection_baseline``
+                -  ``monitoring_config.numerical_threshold_config.value``
+                -  ``monitoring_config.categorical_threshold_config.value``
 
                 This corresponds to the ``update_mask`` field
                 on the ``request`` instance; if ``request`` is provided, this
@@ -1912,8 +1918,7 @@ def sample_update_feature():
 
                 -  ``description``
                 -  ``labels``
-                -  ``monitoring_config.snapshot_analysis.disabled``
-                -  ``monitoring_config.snapshot_analysis.monitoring_interval``
+                -  ``disable_monitoring``
 
                 This corresponds to the ``update_mask`` field
                 on the ``request`` instance; if ``request`` is provided, this