apache-airflow-providers-google 14.0.0__py3-none-any.whl → 19.1.0rc1__py3-none-any.whl

airflow/providers/google/cloud/hooks/spanner.py

@@ -19,17 +19,19 @@
 
 from __future__ import annotations
 
-from collections.abc import Sequence
-from typing import TYPE_CHECKING, Callable, NamedTuple
+from collections import OrderedDict
+from collections.abc import Callable, Sequence
+from typing import TYPE_CHECKING, NamedTuple
 
+from google.api_core.exceptions import AlreadyExists, GoogleAPICallError
+from google.cloud.spanner_v1.client import Client
 from sqlalchemy import create_engine
 
 from airflow.exceptions import AirflowException
 from airflow.providers.common.sql.hooks.sql import DbApiHook
 from airflow.providers.google.common.consts import CLIENT_INFO
 from airflow.providers.google.common.hooks.base_google import GoogleBaseHook, get_field
-from google.api_core.exceptions import AlreadyExists, GoogleAPICallError
-from google.cloud.spanner_v1.client import Client
+from airflow.providers.openlineage.sqlparser import DatabaseInfo
 
 if TYPE_CHECKING:
     from google.cloud.spanner_v1.database import Database
@@ -37,6 +39,8 @@ if TYPE_CHECKING:
     from google.cloud.spanner_v1.transaction import Transaction
     from google.longrunning.operations_grpc_pb2 import Operation
 
+    from airflow.models.connection import Connection
+
 
 class SpannerConnectionParams(NamedTuple):
     """Information about Google Spanner connection parameters."""
@@ -388,7 +392,7 @@ class SpannerHook(GoogleBaseHook, DbApiHook):
         database_id: str,
         queries: list[str],
         project_id: str,
-    ) -> None:
+    ) -> list[int]:
         """
         Execute an arbitrary DML query (INSERT, UPDATE, DELETE).
 
@@ -398,12 +402,73 @@ class SpannerHook(GoogleBaseHook, DbApiHook):
         :param project_id: Optional, the ID of the Google Cloud project that owns the Cloud Spanner
             database. If set to None or missing, the default project_id from the Google Cloud connection
             is used.
+        :return: list of numbers of affected rows by DML query
         """
-        self._get_client(project_id=project_id).instance(instance_id=instance_id).database(
-            database_id=database_id
-        ).run_in_transaction(lambda transaction: self._execute_sql_in_transaction(transaction, queries))
+        db = (
+            self._get_client(project_id=project_id)
+            .instance(instance_id=instance_id)
+            .database(database_id=database_id)
+        )
+
+        def _tx_runner(tx: Transaction) -> dict[str, int]:
+            return self._execute_sql_in_transaction(tx, queries)
+
+        result = db.run_in_transaction(_tx_runner)
+
+        result_rows_count_per_query = []
+        for i, (sql, rc) in enumerate(result.items(), start=1):
+            if not sql.startswith("SELECT"):
+                preview = sql if len(sql) <= 300 else sql[:300] + "…"
+                self.log.info("[DML %d/%d] affected rows=%d | %s", i, len(result), rc, preview)
+                result_rows_count_per_query.append(rc)
+        return result_rows_count_per_query
 
     @staticmethod
-    def _execute_sql_in_transaction(transaction: Transaction, queries: list[str]):
+    def _execute_sql_in_transaction(transaction: Transaction, queries: list[str]) -> dict[str, int]:
+        counts: OrderedDict[str, int] = OrderedDict()
         for sql in queries:
-            transaction.execute_update(sql)
+            rc = transaction.execute_update(sql)
+            counts[sql] = rc
+        return counts
+
+    def _get_openlineage_authority_part(self, connection: Connection) -> str | None:
+        """Build Spanner-specific authority part for OpenLineage. Returns {project}/{instance}."""
+        extras = connection.extra_dejson
+        project_id = extras.get("project_id")
+        instance_id = extras.get("instance_id")
+
+        if not project_id or not instance_id:
+            return None
+
+        return f"{project_id}/{instance_id}"
+
+    def get_openlineage_database_dialect(self, connection: Connection) -> str:
+        """Return database dialect for OpenLineage."""
+        return "spanner"
+
+    def get_openlineage_database_info(self, connection: Connection) -> DatabaseInfo:
+        """Return Spanner specific information for OpenLineage."""
+        extras = connection.extra_dejson
+        database_id = extras.get("database_id")
+
+        return DatabaseInfo(
+            scheme=self.get_openlineage_database_dialect(connection),
+            authority=self._get_openlineage_authority_part(connection),
+            database=database_id,
+            information_schema_columns=[
+                "table_schema",
+                "table_name",
+                "column_name",
+                "ordinal_position",
+                "spanner_type",
+            ],
+        )
+
+    def get_openlineage_default_schema(self) -> str | None:
+        """
+        Spanner expose 'public' or '' schema depending on dialect(Postgres vs GoogleSQL).
+
+        SQLAlchemy dialect for Spanner does not expose default schema, so we return None
+        to follow the same approach.
+        """
+        return None

airflow/providers/google/cloud/hooks/speech_to_text.py

@@ -22,12 +22,13 @@ from __future__ import annotations
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.providers.google.common.consts import CLIENT_INFO
-from airflow.providers.google.common.hooks.base_google import GoogleBaseHook
 from google.api_core.gapic_v1.method import DEFAULT, _MethodDefault
 from google.cloud.speech_v1 import SpeechClient
 from google.cloud.speech_v1.types import RecognitionAudio, RecognitionConfig
 
+from airflow.providers.google.common.consts import CLIENT_INFO
+from airflow.providers.google.common.hooks.base_google import GoogleBaseHook
+
 if TYPE_CHECKING:
     from google.api_core.retry import Retry
 

airflow/providers/google/cloud/hooks/stackdriver.py

@@ -24,15 +24,15 @@ import json
 from collections.abc import Sequence
 from typing import TYPE_CHECKING, Any
 
-from googleapiclient.errors import HttpError
-
-from airflow.exceptions import AirflowException
-from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID, GoogleBaseHook
 from google.api_core.exceptions import InvalidArgument
 from google.api_core.gapic_v1.method import DEFAULT, _MethodDefault
 from google.cloud import monitoring_v3
 from google.cloud.monitoring_v3 import AlertPolicy, NotificationChannel
 from google.protobuf.field_mask_pb2 import FieldMask
+from googleapiclient.errors import HttpError
+
+from airflow.exceptions import AirflowException
+from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID, GoogleBaseHook
 
 if TYPE_CHECKING:
     from google.api_core.retry import Retry
@@ -121,10 +121,9 @@ class StackdriverHook(GoogleBaseHook):
         )
         if format_ == "dict":
             return [AlertPolicy.to_dict(policy) for policy in policies_]
-        elif format_ == "json":
+        if format_ == "json":
             return [AlertPolicy.to_jsoon(policy) for policy in policies_]
-        else:
-            return policies_
+        return policies_
 
     @GoogleBaseHook.fallback_to_default_project_id
     def _toggle_policy_status(
@@ -262,8 +261,9 @@ class StackdriverHook(GoogleBaseHook):
         channel_name_map = {}
 
         for channel in channels:
+            # This field is immutable, illegal to specifying non-default UNVERIFIED or VERIFIED, so setting default
             channel.verification_status = (
-                monitoring_v3.NotificationChannel.VerificationStatus.VERIFICATION_STATUS_UNSPECIFIED
+                monitoring_v3.NotificationChannel.VerificationStatus.VERIFICATION_STATUS_UNSPECIFIED  # type: ignore[assignment]
             )
 
             if channel.name in existing_channels:
@@ -275,7 +275,7 @@ class StackdriverHook(GoogleBaseHook):
                 )
             else:
                 old_name = channel.name
-                channel.name = None
+                del channel.name
                 new_channel = channel_client.create_notification_channel(
                     request={"name": f"projects/{project_id}", "notification_channel": channel},
                     retry=retry,
@@ -285,8 +285,8 @@ class StackdriverHook(GoogleBaseHook):
                 channel_name_map[old_name] = new_channel.name
 
         for policy in policies_:
-            policy.creation_record = None
-            policy.mutation_record = None
+            del policy.creation_record
+            del policy.mutation_record
 
             for i, channel in enumerate(policy.notification_channels):
                 new_channel = channel_name_map.get(channel)
@@ -302,9 +302,9 @@ class StackdriverHook(GoogleBaseHook):
                         metadata=metadata,
                     )
             else:
-                policy.name = None
+                del policy.name
                 for condition in policy.conditions:
-                    condition.name = None
+                    del condition.name
                 policy_client.create_alert_policy(
                     request={"name": f"projects/{project_id}", "alert_policy": policy},
                     retry=retry,
@@ -395,10 +395,9 @@ class StackdriverHook(GoogleBaseHook):
         )
         if format_ == "dict":
             return [NotificationChannel.to_dict(channel) for channel in channels]
-        elif format_ == "json":
+        if format_ == "json":
             return [NotificationChannel.to_json(channel) for channel in channels]
-        else:
-            return channels
+        return channels
 
     @GoogleBaseHook.fallback_to_default_project_id
     def _toggle_channel_status(
@@ -533,8 +532,9 @@ class StackdriverHook(GoogleBaseHook):
             channels_list.append(NotificationChannel(**channel))
 
         for channel in channels_list:
+            # This field is immutable, illegal to specifying non-default UNVERIFIED or VERIFIED, so setting default
             channel.verification_status = (
-                monitoring_v3.NotificationChannel.VerificationStatus.VERIFICATION_STATUS_UNSPECIFIED
+                monitoring_v3.NotificationChannel.VerificationStatus.VERIFICATION_STATUS_UNSPECIFIED  # type: ignore[assignment]
             )
 
             if channel.name in existing_channels:
@@ -546,7 +546,7 @@ class StackdriverHook(GoogleBaseHook):
                 )
             else:
                 old_name = channel.name
-                channel.name = None
+                del channel.name
                 new_channel = channel_client.create_notification_channel(
                     request={"name": f"projects/{project_id}", "notification_channel": channel},
                     retry=retry,

airflow/providers/google/cloud/hooks/tasks.py

@@ -22,13 +22,14 @@ from __future__ import annotations
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.exceptions import AirflowException
-from airflow.providers.google.common.consts import CLIENT_INFO
-from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID, GoogleBaseHook
 from google.api_core.gapic_v1.method import DEFAULT, _MethodDefault
 from google.cloud.tasks_v2 import CloudTasksClient
 from google.cloud.tasks_v2.types import Queue, Task
 
+from airflow.exceptions import AirflowException
+from airflow.providers.google.common.consts import CLIENT_INFO
+from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID, GoogleBaseHook
+
 if TYPE_CHECKING:
     from google.api_core.retry import Retry
     from google.protobuf.field_mask_pb2 import FieldMask

airflow/providers/google/cloud/hooks/text_to_speech.py

@@ -22,8 +22,6 @@ from __future__ import annotations
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.providers.google.common.consts import CLIENT_INFO
-from airflow.providers.google.common.hooks.base_google import GoogleBaseHook
 from google.api_core.gapic_v1.method import DEFAULT, _MethodDefault
 from google.cloud.texttospeech_v1 import TextToSpeechClient
 from google.cloud.texttospeech_v1.types import (
@@ -33,6 +31,9 @@ from google.cloud.texttospeech_v1.types import (
     VoiceSelectionParams,
 )
 
+from airflow.providers.google.common.consts import CLIENT_INFO
+from airflow.providers.google.common.hooks.base_google import GoogleBaseHook
+
 if TYPE_CHECKING:
     from google.api_core.retry import Retry
 

airflow/providers/google/cloud/hooks/translate.py

@@ -25,9 +25,6 @@ from typing import (
     cast,
 )
 
-from airflow.exceptions import AirflowException
-from airflow.providers.google.common.consts import CLIENT_INFO
-from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID, GoogleBaseHook
 from google.api_core.exceptions import GoogleAPICallError
 from google.api_core.gapic_v1.method import DEFAULT, _MethodDefault
 from google.api_core.retry import Retry
@@ -35,9 +32,12 @@ from google.cloud.translate_v2 import Client
 from google.cloud.translate_v3 import TranslationServiceClient
 from google.cloud.translate_v3.types.translation_service import GlossaryInputConfig
 
-if TYPE_CHECKING:
-    from proto import Message
+from airflow.exceptions import AirflowException
+from airflow.providers.google.common.consts import CLIENT_INFO
+from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID, GoogleBaseHook
+from airflow.providers.google.common.hooks.operation_helpers import OperationHelper
 
+if TYPE_CHECKING:
     from google.api_core.operation import Operation
     from google.cloud.translate_v3.services.translation_service import pagers
     from google.cloud.translate_v3.types import (
@@ -155,7 +155,7 @@ class CloudTranslateHook(GoogleBaseHook):
         )
 
 
-class TranslateHook(GoogleBaseHook):
+class TranslateHook(GoogleBaseHook, OperationHelper):
     """
     Hook for Google Cloud translation (Advanced) using client version V3.
 
@@ -221,15 +221,6 @@ class TranslateHook(GoogleBaseHook):
             error = operation.exception(timeout=timeout)
             raise AirflowException(error)
 
-    @staticmethod
-    def wait_for_operation_result(operation: Operation, timeout: int | None = None) -> Message:
-        """Wait for long-lasting operation to complete."""
-        try:
-            return operation.result(timeout=timeout)
-        except GoogleAPICallError:
-            error = operation.exception(timeout=timeout)
-            raise AirflowException(error)
-
     @staticmethod
     def extract_object_id(obj: dict) -> str:
         """Return unique id of the object."""
@@ -320,7 +311,7 @@ class TranslateHook(GoogleBaseHook):
             retry=retry,
             metadata=metadata,
         )
-        return cast(dict, type(result).to_dict(result))
+        return cast("dict", type(result).to_dict(result))
 
     def batch_translate_text(
         self,
@@ -438,7 +429,7 @@ class TranslateHook(GoogleBaseHook):
         project_id: str,
         location: str,
         retry: Retry | _MethodDefault = DEFAULT,
-        timeout: float | _MethodDefault = DEFAULT,
+        timeout: float | None | _MethodDefault = DEFAULT,
         metadata: Sequence[tuple[str, str]] = (),
     ) -> automl_translation.Dataset:
         """

airflow/providers/google/cloud/hooks/vertex_ai/auto_ml.py

@@ -23,9 +23,6 @@ import warnings
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.exceptions import AirflowException, AirflowProviderDeprecationWarning
-from airflow.providers.google.common.deprecated import deprecated
-from airflow.providers.google.common.hooks.base_google import GoogleBaseHook
 from google.api_core.client_options import ClientOptions
 from google.api_core.gapic_v1.method import DEFAULT, _MethodDefault
 from google.cloud.aiplatform import (
@@ -39,6 +36,11 @@ from google.cloud.aiplatform import (
 )
 from google.cloud.aiplatform_v1 import JobServiceClient, PipelineServiceClient
 
+from airflow.exceptions import AirflowException, AirflowProviderDeprecationWarning
+from airflow.providers.google.common.consts import CLIENT_INFO
+from airflow.providers.google.common.hooks.base_google import GoogleBaseHook
+from airflow.providers.google.common.hooks.operation_helpers import OperationHelper
+
 if TYPE_CHECKING:
     from google.api_core.operation import Operation
     from google.api_core.retry import Retry
@@ -46,7 +48,7 @@ if TYPE_CHECKING:
     from google.cloud.aiplatform_v1.types import TrainingPipeline
 
 
-class AutoMLHook(GoogleBaseHook):
+class AutoMLHook(GoogleBaseHook, OperationHelper):
     """Hook for Google Cloud Vertex AI Auto ML APIs."""
 
     def __init__(
@@ -79,7 +81,7 @@ class AutoMLHook(GoogleBaseHook):
             client_options = ClientOptions()
 
         return PipelineServiceClient(
-            credentials=self.get_credentials(), client_info=self.client_info, client_options=client_options
+            credentials=self.get_credentials(), client_info=CLIENT_INFO, client_options=client_options
         )
 
     def get_job_service_client(
@@ -93,7 +95,7 @@ class AutoMLHook(GoogleBaseHook):
             client_options = ClientOptions()
 
         return JobServiceClient(
-            credentials=self.get_credentials(), client_info=self.client_info, client_options=client_options
+            credentials=self.get_credentials(), client_info=CLIENT_INFO, client_options=client_options
         )
 
     def get_auto_ml_tabular_training_job(
@@ -182,42 +184,6 @@ class AutoMLHook(GoogleBaseHook):
             model_encryption_spec_key_name=model_encryption_spec_key_name,
         )
 
-    @deprecated(
-        planned_removal_date="June 15, 2025",
-        category=AirflowProviderDeprecationWarning,
-        reason="Deprecation of AutoMLText API",
-    )
-    def get_auto_ml_text_training_job(
-        self,
-        display_name: str,
-        prediction_type: str,
-        multi_label: bool = False,
-        sentiment_max: int = 10,
-        project: str | None = None,
-        location: str | None = None,
-        labels: dict[str, str] | None = None,
-        training_encryption_spec_key_name: str | None = None,
-        model_encryption_spec_key_name: str | None = None,
-    ) -> AutoMLTextTrainingJob:
-        """
-        Return AutoMLTextTrainingJob object.
-
-        WARNING: Text creation API is deprecated since September 15, 2024
-        (https://cloud.google.com/vertex-ai/docs/tutorials/text-classification-automl/overview).
-        """
-        return AutoMLTextTrainingJob(
-            display_name=display_name,
-            prediction_type=prediction_type,
-            multi_label=multi_label,
-            sentiment_max=sentiment_max,
-            project=project,
-            location=location,
-            credentials=self.get_credentials(),
-            labels=labels,
-            training_encryption_spec_key_name=training_encryption_spec_key_name,
-            model_encryption_spec_key_name=model_encryption_spec_key_name,
-        )
-
     def get_auto_ml_video_training_job(
         self,
         display_name: str,
@@ -252,14 +218,6 @@ class AutoMLHook(GoogleBaseHook):
         """Return unique id of the Training pipeline."""
         return resource_name.rpartition("/")[-1]
 
-    def wait_for_operation(self, operation: Operation, timeout: float | None = None):
-        """Wait for long-lasting operation to complete."""
-        try:
-            return operation.result(timeout=timeout)
-        except Exception:
-            error = operation.exception(timeout=timeout)
-            raise AirflowException(error)
-
     def cancel_auto_ml_job(self) -> None:
         """Cancel Auto ML Job for training pipeline."""
         if self._job:
@@ -992,178 +950,6 @@ class AutoMLHook(GoogleBaseHook):
             )
         return model, training_id
 
-    @GoogleBaseHook.fallback_to_default_project_id
-    @deprecated(
-        planned_removal_date="September 15, 2025",
-        category=AirflowProviderDeprecationWarning,
-        reason="Deprecation of AutoMLText API",
-    )
-    def create_auto_ml_text_training_job(
-        self,
-        project_id: str,
-        region: str,
-        display_name: str,
-        dataset: datasets.TextDataset,
-        prediction_type: str,
-        multi_label: bool = False,
-        sentiment_max: int = 10,
-        labels: dict[str, str] | None = None,
-        training_encryption_spec_key_name: str | None = None,
-        model_encryption_spec_key_name: str | None = None,
-        training_fraction_split: float | None = None,
-        validation_fraction_split: float | None = None,
-        test_fraction_split: float | None = None,
-        training_filter_split: str | None = None,
-        validation_filter_split: str | None = None,
-        test_filter_split: str | None = None,
-        model_display_name: str | None = None,
-        model_labels: dict[str, str] | None = None,
-        sync: bool = True,
-        parent_model: str | None = None,
-        is_default_version: bool | None = None,
-        model_version_aliases: list[str] | None = None,
-        model_version_description: str | None = None,
-    ) -> tuple[models.Model | None, str]:
-        """
-        Create an AutoML Text Training Job.
-
-        WARNING: Text creation API is deprecated since September 15, 2024
-        (https://cloud.google.com/vertex-ai/docs/tutorials/text-classification-automl/overview).
-
-        :param project_id: Required. Project to run training in.
-        :param region: Required. Location to run training in.
-        :param display_name: Required. The user-defined name of this TrainingPipeline.
-        :param dataset: Required. The dataset within the same Project from which data will be used to train
-            the Model. The Dataset must use schema compatible with Model being trained, and what is
-            compatible should be described in the used TrainingPipeline's [training_task_definition]
-            [google.cloud.aiplatform.v1beta1.TrainingPipeline.training_task_definition].
-        :param prediction_type: The type of prediction the Model is to produce, one of:
-            "classification" - A classification model analyzes text data and returns a list of categories
-            that apply to the text found in the data. Vertex AI offers both single-label and multi-label text
-            classification models.
-            "extraction" - An entity extraction model inspects text data for known entities referenced in the
-            data and labels those entities in the text.
-            "sentiment" - A sentiment analysis model inspects text data and identifies the prevailing
-            emotional opinion within it, especially to determine a writer's attitude as positive, negative,
-            or neutral.
-        :param parent_model: Optional. The resource name or model ID of an existing model.
-            The new model uploaded by this job will be a version of `parent_model`.
-            Only set this field when training a new version of an existing model.
-        :param is_default_version: Optional. When set to True, the newly uploaded model version will
-            automatically have alias "default" included. Subsequent uses of
-            the model produced by this job without a version specified will
-            use this "default" version.
-            When set to False, the "default" alias will not be moved.
-            Actions targeting the model version produced by this job will need
-            to specifically reference this version by ID or alias.
-            New model uploads, i.e. version 1, will always be "default" aliased.
-        :param model_version_aliases: Optional. User provided version aliases so that the model version
-            uploaded by this job can be referenced via alias instead of
-            auto-generated version ID. A default version alias will be created
-            for the first version of the model.
-            The format is [a-z][a-zA-Z0-9-]{0,126}[a-z0-9]
-        :param model_version_description: Optional. The description of the model version
-            being uploaded by this job.
-        :param multi_label: Required and only applicable for text classification task. If false, a
-            single-label (multi-class) Model will be trained (i.e. assuming that for each text snippet just
-            up to one annotation may be applicable). If true, a multi-label Model will be trained (i.e.
-            assuming that for each text snippet multiple annotations may be applicable).
-        :param sentiment_max: Required and only applicable for sentiment task. A sentiment is expressed as an
-            integer ordinal, where higher value means a more positive sentiment. The range of sentiments that
-            will be used is between 0 and sentimentMax (inclusive on both ends), and all the values in the
-            range must be represented in the dataset before a model can be created. Only the Annotations with
-            this sentimentMax will be used for training. sentimentMax value must be between 1 and 10
-            (inclusive).
-        :param labels: Optional. The labels with user-defined metadata to organize TrainingPipelines. Label
-            keys and values can be no longer than 64 characters (Unicode codepoints), can only contain
-            lowercase letters, numeric characters, underscores and dashes. International characters are
-            allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
-        :param training_encryption_spec_key_name: Optional. The Cloud KMS resource identifier of the customer
-            managed encryption key used to protect the training pipeline. Has the form:
-            ``projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key``.
-            The key needs to be in the same region as where the compute resource is created.
-            If set, this TrainingPipeline will be secured by this key.
-            Note: Model trained by this TrainingPipeline is also secured by this key if ``model_to_upload``
-            is not set separately.
-        :param model_encryption_spec_key_name: Optional. The Cloud KMS resource identifier of the customer
-            managed encryption key used to protect the model. Has the form:
-            ``projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key``.
-            The key needs to be in the same region as where the compute resource is created.
-            If set, the trained Model will be secured by this key.
-        :param training_fraction_split: Optional. The fraction of the input data that is to be used to train
-            the Model. This is ignored if Dataset is not provided.
-        :param validation_fraction_split: Optional. The fraction of the input data that is to be used to
-            validate the Model. This is ignored if Dataset is not provided.
-        :param test_fraction_split: Optional. The fraction of the input data that is to be used to evaluate
-            the Model. This is ignored if Dataset is not provided.
-        :param training_filter_split: Optional. A filter on DataItems of the Dataset. DataItems that match
-            this filter are used to train the Model. A filter with same syntax as the one used in
-            DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the
-            FilterSplit filters, then it is assigned to the first set that applies to it in the training,
-            validation, test order. This is ignored if Dataset is not provided.
-        :param validation_filter_split: Optional. A filter on DataItems of the Dataset. DataItems that match
-            this filter are used to validate the Model. A filter with same syntax as the one used in
-            DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the
-            FilterSplit filters, then it is assigned to the first set that applies to it in the training,
-            validation, test order. This is ignored if Dataset is not provided.
-        :param test_filter_split: Optional. A filter on DataItems of the Dataset. DataItems that match this
-            filter are used to test the Model. A filter with same syntax as the one used in
-            DatasetService.ListDataItems may be used. If a single DataItem is matched by more than one of the
-            FilterSplit filters, then it is assigned to the first set that applies to it in the training,
-            validation, test order. This is ignored if Dataset is not provided.
-        :param model_display_name: Optional. The display name of the managed Vertex AI Model. The name can be
-            up to 128 characters long and can consist of any UTF-8 characters.
-            If not provided upon creation, the job's display_name is used.
-        :param model_labels: Optional. The labels with user-defined metadata to organize your Models. Label
-            keys and values can be no longer than 64 characters (Unicode codepoints), can only contain
-            lowercase letters, numeric characters, underscores and dashes. International characters are
-            allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
-        :param sync: Whether to execute this method synchronously. If False, this method will be executed in
-            concurrent Future and any downstream object will be immediately returned and synced when the
-            Future has completed.
-        """
-        self._job = AutoMLTextTrainingJob(
-            display_name=display_name,
-            prediction_type=prediction_type,
-            multi_label=multi_label,
-            sentiment_max=sentiment_max,
-            project=project_id,
-            location=region,
-            credentials=self.get_credentials(),
-            labels=labels,
-            training_encryption_spec_key_name=training_encryption_spec_key_name,
-            model_encryption_spec_key_name=model_encryption_spec_key_name,
-        )
-
-        if not self._job:
-            raise AirflowException("AutoMLTextTrainingJob was not created")
-
-        model = self._job.run(
-            dataset=dataset,  # type: ignore[arg-type]
-            training_fraction_split=training_fraction_split,  # type: ignore[call-arg]
-            validation_fraction_split=validation_fraction_split,  # type: ignore[call-arg]
-            test_fraction_split=test_fraction_split,
-            training_filter_split=training_filter_split,
-            validation_filter_split=validation_filter_split,
-            test_filter_split=test_filter_split,  # type: ignore[call-arg]
-            model_display_name=model_display_name,
-            model_labels=model_labels,
-            sync=sync,
-            parent_model=parent_model,
-            is_default_version=is_default_version,
-            model_version_aliases=model_version_aliases,
-            model_version_description=model_version_description,
-        )
-        training_id = self.extract_training_id(self._job.resource_name)
-        if model:
-            model.wait()
-        else:
-            self.log.warning(
-                "Training did not produce a Managed Model returning None. AutoML Text Training "
-                "Pipeline is not configured to upload a Model."
-            )
-        return model, training_id
-
     @GoogleBaseHook.fallback_to_default_project_id
     def create_auto_ml_video_training_job(
         self,