apache-airflow-providers-google 16.0.0a1__py3-none-any.whl → 16.0.0rc1__py3-none-any.whl

airflow/providers/google/cloud/operators/bigquery.py

@@ -93,16 +93,32 @@ class IfExistAction(enum.Enum):
     SKIP = "skip"
 
 
+class _BigQueryHookWithFlexibleProjectId(BigQueryHook):
+    @property
+    def project_id(self) -> str:
+        _, project_id = self.get_credentials_and_project_id()
+        return project_id or PROVIDE_PROJECT_ID
+
+    @project_id.setter
+    def project_id(self, value: str) -> None:
+        cached_creds, _ = self.get_credentials_and_project_id()
+        self._cached_project_id = value or PROVIDE_PROJECT_ID
+        self._cached_credntials = cached_creds
+
+
 class _BigQueryDbHookMixin:
-    def get_db_hook(self: BigQueryCheckOperator) -> BigQueryHook:  # type:ignore[misc]
+    def get_db_hook(self: BigQueryCheckOperator) -> _BigQueryHookWithFlexibleProjectId:  # type:ignore[misc]
         """Get BigQuery DB Hook."""
-        return BigQueryHook(
+        hook = _BigQueryHookWithFlexibleProjectId(
             gcp_conn_id=self.gcp_conn_id,
             use_legacy_sql=self.use_legacy_sql,
             location=self.location,
             impersonation_chain=self.impersonation_chain,
             labels=self.labels,
         )
+        if self.project_id:
+            hook.project_id = self.project_id
+        return hook
 
 
 class _BigQueryOperatorsEncryptionConfigurationMixin:
@@ -190,6 +206,7 @@ class BigQueryCheckOperator(
         https://cloud.google.com/bigquery/docs/reference/rest/v2/jobs.
         For example, [{ 'name': 'corpus', 'parameterType': { 'type': 'STRING' },
         'parameterValue': { 'value': 'romeoandjuliet' } }]. (templated)
+    :param project_id: Google Cloud Project where the job is running
     """
 
     template_fields: Sequence[str] = (
@@ -208,6 +225,7 @@ class BigQueryCheckOperator(
         *,
         sql: str,
         gcp_conn_id: str = "google_cloud_default",
+        project_id: str = PROVIDE_PROJECT_ID,
         use_legacy_sql: bool = True,
         location: str | None = None,
         impersonation_chain: str | Sequence[str] | None = None,
@@ -228,6 +246,7 @@ class BigQueryCheckOperator(
         self.deferrable = deferrable
         self.poll_interval = poll_interval
         self.query_params = query_params
+        self.project_id = project_id
 
     def _submit_job(
         self,
@@ -243,7 +262,7 @@ class BigQueryCheckOperator(
 
         return hook.insert_job(
             configuration=configuration,
-            project_id=hook.project_id,
+            project_id=self.project_id,
             location=self.location,
             job_id=job_id,
             nowait=True,
@@ -257,6 +276,8 @@ class BigQueryCheckOperator(
                 gcp_conn_id=self.gcp_conn_id,
                 impersonation_chain=self.impersonation_chain,
             )
+            if self.project_id is None:
+                self.project_id = hook.project_id
             job = self._submit_job(hook, job_id="")
             context["ti"].xcom_push(key="job_id", value=job.job_id)
             if job.running():
@@ -265,7 +286,7 @@ class BigQueryCheckOperator(
                     trigger=BigQueryCheckTrigger(
                         conn_id=self.gcp_conn_id,
                         job_id=job.job_id,
-                        project_id=hook.project_id,
+                        project_id=self.project_id,
                         location=self.location or hook.location,
                         poll_interval=self.poll_interval,
                         impersonation_chain=self.impersonation_chain,
@@ -342,6 +363,7 @@ class BigQueryValueCheckOperator(
     :param deferrable: Run operator in the deferrable mode.
     :param poll_interval: (Deferrable mode only) polling period in seconds to
         check for the status of job.
+    :param project_id: Google Cloud Project where the job is running
     """
 
     template_fields: Sequence[str] = (
@@ -363,6 +385,7 @@ class BigQueryValueCheckOperator(
         tolerance: Any = None,
         encryption_configuration: dict | None = None,
         gcp_conn_id: str = "google_cloud_default",
+        project_id: str = PROVIDE_PROJECT_ID,
         use_legacy_sql: bool = True,
         location: str | None = None,
         impersonation_chain: str | Sequence[str] | None = None,
@@ -380,6 +403,7 @@ class BigQueryValueCheckOperator(
         self.labels = labels
         self.deferrable = deferrable
         self.poll_interval = poll_interval
+        self.project_id = project_id
 
     def _submit_job(
         self,
@@ -398,7 +422,7 @@ class BigQueryValueCheckOperator(
 
         return hook.insert_job(
             configuration=configuration,
-            project_id=hook.project_id,
+            project_id=self.project_id,
             location=self.location,
             job_id=job_id,
             nowait=True,
@@ -409,7 +433,8 @@ class BigQueryValueCheckOperator(
             super().execute(context=context)
         else:
             hook = BigQueryHook(gcp_conn_id=self.gcp_conn_id, impersonation_chain=self.impersonation_chain)
-
+            if self.project_id is None:
+                self.project_id = hook.project_id
             job = self._submit_job(hook, job_id="")
             context["ti"].xcom_push(key="job_id", value=job.job_id)
             if job.running():
@@ -418,7 +443,7 @@ class BigQueryValueCheckOperator(
                     trigger=BigQueryValueCheckTrigger(
                         conn_id=self.gcp_conn_id,
                         job_id=job.job_id,
-                        project_id=hook.project_id,
+                        project_id=self.project_id,
                         location=self.location or hook.location,
                         sql=self.sql,
                         pass_value=self.pass_value,
@@ -575,6 +600,9 @@ class BigQueryIntervalCheckOperator(
             hook = BigQueryHook(gcp_conn_id=self.gcp_conn_id, impersonation_chain=self.impersonation_chain)
             self.log.info("Using ratio formula: %s", self.ratio_formula)
 
+            if self.project_id is None:
+                self.project_id = hook.project_id
+
             self.log.info("Executing SQL check: %s", self.sql1)
             job_1 = self._submit_job(hook, sql=self.sql1, job_id="")
             context["ti"].xcom_push(key="job_id", value=job_1.job_id)
@@ -587,7 +615,7 @@ class BigQueryIntervalCheckOperator(
                     conn_id=self.gcp_conn_id,
                     first_job_id=job_1.job_id,
                     second_job_id=job_2.job_id,
-                    project_id=hook.project_id,
+                    project_id=self.project_id,
                     table=self.table,
                     location=self.location or hook.location,
                     metrics_thresholds=self.metrics_thresholds,
@@ -654,6 +682,7 @@ class BigQueryColumnCheckOperator(
         Service Account Token Creator IAM role to the directly preceding identity, with first
         account from the list granting this role to the originating account (templated).
     :param labels: a dictionary containing labels for the table, passed to BigQuery
+    :param project_id: Google Cloud Project where the job is running
     """
 
     template_fields: Sequence[str] = tuple(set(SQLColumnCheckOperator.template_fields) | {"gcp_conn_id"})
@@ -670,6 +699,7 @@ class BigQueryColumnCheckOperator(
         accept_none: bool = True,
         encryption_configuration: dict | None = None,
         gcp_conn_id: str = "google_cloud_default",
+        project_id: str = PROVIDE_PROJECT_ID,
         use_legacy_sql: bool = True,
         location: str | None = None,
         impersonation_chain: str | Sequence[str] | None = None,
@@ -695,6 +725,7 @@ class BigQueryColumnCheckOperator(
         self.location = location
         self.impersonation_chain = impersonation_chain
         self.labels = labels
+        self.project_id = project_id
 
     def _submit_job(
         self,
@@ -706,7 +737,7 @@ class BigQueryColumnCheckOperator(
         self.include_encryption_configuration(configuration, "query")
         return hook.insert_job(
             configuration=configuration,
-            project_id=hook.project_id,
+            project_id=self.project_id,
             location=self.location,
             job_id=job_id,
             nowait=False,
@@ -715,6 +746,9 @@ class BigQueryColumnCheckOperator(
     def execute(self, context=None):
         """Perform checks on the given columns."""
         hook = self.get_db_hook()
+
+        if self.project_id is None:
+            self.project_id = hook.project_id
         failed_tests = []
 
         job = self._submit_job(hook, job_id="")
@@ -786,6 +820,7 @@ class BigQueryTableCheckOperator(
         account from the list granting this role to the originating account (templated).
     :param labels: a dictionary containing labels for the table, passed to BigQuery
     :param encryption_configuration: (Optional) Custom encryption configuration (e.g., Cloud KMS keys).
+    :param project_id: Google Cloud Project where the job is running
 
         .. code-block:: python
 
@@ -805,6 +840,7 @@ class BigQueryTableCheckOperator(
         checks: dict,
         partition_clause: str | None = None,
         gcp_conn_id: str = "google_cloud_default",
+        project_id: str = PROVIDE_PROJECT_ID,
         use_legacy_sql: bool = True,
         location: str | None = None,
         impersonation_chain: str | Sequence[str] | None = None,
@@ -819,6 +855,7 @@ class BigQueryTableCheckOperator(
         self.impersonation_chain = impersonation_chain
         self.labels = labels
         self.encryption_configuration = encryption_configuration
+        self.project_id = project_id
 
     def _submit_job(
         self,
@@ -832,7 +869,7 @@ class BigQueryTableCheckOperator(
 
         return hook.insert_job(
             configuration=configuration,
-            project_id=hook.project_id,
+            project_id=self.project_id,
             location=self.location,
             job_id=job_id,
             nowait=False,
@@ -841,6 +878,8 @@ class BigQueryTableCheckOperator(
     def execute(self, context=None):
         """Execute the given checks on the table."""
         hook = self.get_db_hook()
+        if self.project_id is None:
+            self.project_id = hook.project_id
         job = self._submit_job(hook, job_id="")
         context["ti"].xcom_push(key="job_id", value=job.job_id)
         records = job.result().to_dataframe()

airflow/providers/google/cloud/operators/cloud_run.py

@@ -27,6 +27,7 @@ from google.cloud.run_v2 import Job, Service
 from airflow.configuration import conf
 from airflow.exceptions import AirflowException
 from airflow.providers.google.cloud.hooks.cloud_run import CloudRunHook, CloudRunServiceHook
+from airflow.providers.google.cloud.links.cloud_run import CloudRunJobLoggingLink
 from airflow.providers.google.cloud.operators.cloud_base import GoogleCloudBaseOperator
 from airflow.providers.google.cloud.triggers.cloud_run import CloudRunJobFinishedTrigger, RunJobStatus
 
@@ -248,7 +249,7 @@ class CloudRunExecuteJobOperator(GoogleCloudBaseOperator):
 
     :param project_id: Required. The ID of the Google Cloud project that the service belongs to.
     :param region: Required. The ID of the Google Cloud region that the service belongs to.
-    :param job_name: Required. The name of the job to update.
+    :param job_name: Required. The name of the job to execute.
     :param overrides: Optional map of override values.
     :param gcp_conn_id: The connection ID used to connect to Google Cloud.
     :param polling_period_seconds: Optional. Control the rate of the poll for the result of deferrable run.
@@ -265,6 +266,7 @@ class CloudRunExecuteJobOperator(GoogleCloudBaseOperator):
     :param deferrable: Run the operator in deferrable mode.
     """
 
+    operator_extra_links = (CloudRunJobLoggingLink(),)
     template_fields = (
         "project_id",
         "region",
@@ -312,6 +314,13 @@ class CloudRunExecuteJobOperator(GoogleCloudBaseOperator):
         if self.operation is None:
             raise AirflowException("Operation is None")
 
+        if self.operation.metadata.log_uri:
+            CloudRunJobLoggingLink.persist(
+                context=context,
+                task_instance=self,
+                log_uri=self.operation.metadata.log_uri,
+            )
+
         if not self.deferrable:
             result: Execution = self._wait_for_operation(self.operation)
             self._fail_if_execution_failed(result)

airflow/providers/google/cloud/operators/gcs.py

@@ -204,6 +204,7 @@ class GCSListObjectsOperator(GoogleCloudBaseOperator):
         "bucket",
         "prefix",
         "delimiter",
+        "match_glob",
         "impersonation_chain",
     )
 

airflow/providers/google/cloud/operators/kubernetes_engine.py

@@ -57,7 +57,6 @@ from airflow.providers.google.cloud.triggers.kubernetes_engine import (
     GKEOperationTrigger,
     GKEStartPodTrigger,
 )
-from airflow.providers.google.common.deprecated import deprecated
 from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID
 from airflow.providers_manager import ProvidersManager
 from airflow.utils.timezone import utcnow
@@ -222,7 +221,6 @@ class GKEDeleteClusterOperator(GKEOperatorMixin, GoogleCloudBaseOperator):
         If set as a sequence, the identities from the list must grant
         Service Account Token Creator IAM role to the directly preceding identity, with first
         account from the list granting this role to the originating account (templated).
-    :param name: (Deprecated) The name of the resource to delete, in this case cluster name
     :param api_version: The api version to use
     :param deferrable: Run operator in the deferrable mode.
     :param poll_interval: Interval size which defines how often operation status is checked.
@@ -241,7 +239,6 @@ class GKEDeleteClusterOperator(GKEOperatorMixin, GoogleCloudBaseOperator):
         gcp_conn_id: str = "google_cloud_default",
         impersonation_chain: str | Sequence[str] | None = None,
         cluster_name: str | None = None,
-        name: str | None = None,
         api_version: str = "v2",
         deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False),
         poll_interval: int = 10,
@@ -251,36 +248,17 @@ class GKEDeleteClusterOperator(GKEOperatorMixin, GoogleCloudBaseOperator):
         super().__init__(*args, **kwargs)
 
         self.location = location
-        self.cluster_name = cluster_name or name
+        self.cluster_name = cluster_name
         self.use_internal_ip = use_internal_ip
         self.use_dns_endpoint = use_dns_endpoint
         self.project_id = project_id
         self.gcp_conn_id = gcp_conn_id
         self.impersonation_chain = impersonation_chain
-        self._name = name
         self.api_version = api_version
         self.deferrable = deferrable
         self.poll_interval = poll_interval
         self._check_input()
 
-    @property
-    @deprecated(
-        planned_removal_date="May 01, 2025",
-        use_instead="cluster_name",
-        category=AirflowProviderDeprecationWarning,
-    )
-    def name(self) -> str | None:
-        return self._name
-
-    @name.setter
-    @deprecated(
-        planned_removal_date="May 01, 2025",
-        use_instead="cluster_name",
-        category=AirflowProviderDeprecationWarning,
-    )
-    def name(self, name: str) -> None:
-        self._name = name
-
     def _check_input(self) -> None:
         if not all([self.project_id, self.cluster_name, self.location]):
             self.log.error("One of (project_id, cluster_name, location) is missing or incorrect")
@@ -622,16 +600,10 @@ class GKEStartPodOperator(GKEOperatorMixin, KubernetesPodOperator):
         If set as a sequence, the identities from the list must grant
         Service Account Token Creator IAM role to the directly preceding identity, with first
         account from the list granting this role to the originating account (templated).
-    :param regional: (Deprecated) The location param is region name.
     :param on_finish_action: What to do when the pod reaches its final state, or the execution is interrupted.
         If "delete_pod", the pod will be deleted regardless its state; if "delete_succeeded_pod",
         only succeeded pod will be deleted. You can set to "keep_pod" to keep the pod.
         Current default is `keep_pod`, but this will be changed in the next major release of this provider.
-    :param is_delete_operator_pod: (Deprecated) What to do when the pod reaches its final
-        state, or the execution is interrupted. If True, delete the
-        pod; if False, leave the pod. Current default is False, but this will be
-        changed in the next major release of this provider.
-        Deprecated - use `on_finish_action` instead.
     :param deferrable: Run operator in the deferrable mode.
     """
 
@@ -651,30 +623,15 @@ class GKEStartPodOperator(GKEOperatorMixin, KubernetesPodOperator):
         project_id: str = PROVIDE_PROJECT_ID,
         gcp_conn_id: str = "google_cloud_default",
         impersonation_chain: str | Sequence[str] | None = None,
-        regional: bool | None = None,
         on_finish_action: str | None = None,
-        is_delete_operator_pod: bool | None = None,
         deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False),
         *args,
         **kwargs,
     ) -> None:
-        if is_delete_operator_pod is not None:
-            kwargs["on_finish_action"] = (
-                OnFinishAction.DELETE_POD if is_delete_operator_pod else OnFinishAction.KEEP_POD
-            )
-        elif on_finish_action is not None:
+        if on_finish_action is not None:
             kwargs["on_finish_action"] = OnFinishAction(on_finish_action)
         else:
-            warnings.warn(
-                f"You have not set parameter `on_finish_action` in class {self.__class__.__name__}. "
-                "Currently the default for this parameter is `keep_pod` but in a future release"
-                " the default will be changed to `delete_pod`. To ensure pods are not deleted in"
-                " the future you will need to set `on_finish_action=keep_pod` explicitly.",
-                AirflowProviderDeprecationWarning,
-                stacklevel=2,
-            )
-            kwargs["on_finish_action"] = OnFinishAction.KEEP_POD
-
+            kwargs["on_finish_action"] = OnFinishAction.DELETE_POD
         super().__init__(*args, **kwargs)
         self.project_id = project_id
         self.location = location
@@ -683,9 +640,6 @@ class GKEStartPodOperator(GKEOperatorMixin, KubernetesPodOperator):
         self.use_internal_ip = use_internal_ip
         self.use_dns_endpoint = use_dns_endpoint
         self.impersonation_chain = impersonation_chain
-        self._regional = regional
-        if is_delete_operator_pod is not None:
-            self.is_delete_operator_pod = is_delete_operator_pod
         self.deferrable = deferrable
 
         # There is no need to manage the kube_config file, as it will be generated automatically.
@@ -693,42 +647,6 @@ class GKEStartPodOperator(GKEOperatorMixin, KubernetesPodOperator):
         if self.config_file:
             raise AirflowException("config_file is not an allowed parameter for the GKEStartPodOperator.")
 
-    @property
-    @deprecated(
-        planned_removal_date="May 01, 2025",
-        use_instead="on_finish_action",
-        category=AirflowProviderDeprecationWarning,
-    )
-    def is_delete_operator_pod(self) -> bool | None:
-        return self._is_delete_operator_pod
-
-    @is_delete_operator_pod.setter
-    @deprecated(
-        planned_removal_date="May 01, 2025",
-        use_instead="on_finish_action",
-        category=AirflowProviderDeprecationWarning,
-    )
-    def is_delete_operator_pod(self, is_delete_operator_pod) -> None:
-        self._is_delete_operator_pod = is_delete_operator_pod
-
-    @property
-    @deprecated(
-        planned_removal_date="May 01, 2025",
-        reason="The parameter is not in actual use.",
-        category=AirflowProviderDeprecationWarning,
-    )
-    def regional(self) -> bool | None:
-        return self._regional
-
-    @regional.setter
-    @deprecated(
-        planned_removal_date="May 01, 2025",
-        reason="The parameter is not in actual use.",
-        category=AirflowProviderDeprecationWarning,
-    )
-    def regional(self, regional) -> None:
-        self._regional = regional
-
     def invoke_defer_method(self, last_log_time: DateTime | None = None):
         """Redefine triggers which are being used in child classes."""
         trigger_start_time = utcnow()

airflow/providers/google/cloud/operators/pubsub.py

@@ -40,6 +40,7 @@ from google.cloud.pubsub_v1.types import (
     SchemaSettings,
 )
 
+from airflow.configuration import conf
 from airflow.exceptions import AirflowException
 from airflow.providers.google.cloud.hooks.pubsub import PubSubHook
 from airflow.providers.google.cloud.links.pubsub import PubSubSubscriptionLink, PubSubTopicLink
@@ -770,7 +771,7 @@ class PubSubPullOperator(GoogleCloudBaseOperator):
         messages_callback: Callable[[list[ReceivedMessage], Context], Any] | None = None,
         gcp_conn_id: str = "google_cloud_default",
         impersonation_chain: str | Sequence[str] | None = None,
-        deferrable: bool = False,
+        deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False),
         poll_interval: int = 300,
         **kwargs,
     ) -> None:

airflow/providers/google/cloud/operators/vertex_ai/generative_model.py

@@ -22,105 +22,13 @@ from __future__ import annotations
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.exceptions import AirflowProviderDeprecationWarning
 from airflow.providers.google.cloud.hooks.vertex_ai.generative_model import GenerativeModelHook
 from airflow.providers.google.cloud.operators.cloud_base import GoogleCloudBaseOperator
-from airflow.providers.google.common.deprecated import deprecated
 
 if TYPE_CHECKING:
     from airflow.utils.context import Context
 
 
-@deprecated(
-    planned_removal_date="April 09, 2025",
-    use_instead="GenerativeModelGenerateContentOperator",
-    category=AirflowProviderDeprecationWarning,
-)
-class TextGenerationModelPredictOperator(GoogleCloudBaseOperator):
-    """
-    Uses the Vertex AI PaLM API to generate natural language text.
-
-    :param project_id: Required. The ID of the Google Cloud project that the
-        service belongs to (templated).
-    :param location: Required. The ID of the Google Cloud location that the
-        service belongs to (templated).
-    :param prompt: Required. Inputs or queries that a user or a program gives
-        to the Vertex AI PaLM API, in order to elicit a specific response (templated).
-    :param pretrained_model: By default uses the pre-trained model `text-bison`,
-        optimized for performing natural language tasks such as classification,
-        summarization, extraction, content creation, and ideation.
-    :param temperature: Temperature controls the degree of randomness in token
-        selection. Defaults to 0.0.
-    :param max_output_tokens: Token limit determines the maximum amount of text
-        output. Defaults to 256.
-    :param top_p: Tokens are selected from most probable to least until the sum
-        of their probabilities equals the top_p value. Defaults to 0.8.
-    :param top_k: A top_k of 1 means the selected token is the most probable
-        among all tokens. Defaults to 0.4.
-    :param gcp_conn_id: The connection ID to use connecting to Google Cloud.
-    :param impersonation_chain: Optional service account to impersonate using short-term
-        credentials, or chained list of accounts required to get the access_token
-        of the last account in the list, which will be impersonated in the request.
-        If set as a string, the account must grant the originating account
-        the Service Account Token Creator IAM role.
-        If set as a sequence, the identities from the list must grant
-        Service Account Token Creator IAM role to the directly preceding identity, with first
-        account from the list granting this role to the originating account (templated).
-    """
-
-    template_fields = ("location", "project_id", "impersonation_chain", "prompt")
-
-    def __init__(
-        self,
-        *,
-        project_id: str,
-        location: str,
-        prompt: str,
-        pretrained_model: str = "text-bison",
-        temperature: float = 0.0,
-        max_output_tokens: int = 256,
-        top_p: float = 0.8,
-        top_k: int = 40,
-        gcp_conn_id: str = "google_cloud_default",
-        impersonation_chain: str | Sequence[str] | None = None,
-        **kwargs,
-    ) -> None:
-        super().__init__(**kwargs)
-        self.project_id = project_id
-        self.location = location
-        self.prompt = prompt
-        self.pretrained_model = pretrained_model
-        self.temperature = temperature
-        self.max_output_tokens = max_output_tokens
-        self.top_p = top_p
-        self.top_k = top_k
-        self.gcp_conn_id = gcp_conn_id
-        self.impersonation_chain = impersonation_chain
-
-    def execute(self, context: Context):
-        self.hook = GenerativeModelHook(
-            gcp_conn_id=self.gcp_conn_id,
-            impersonation_chain=self.impersonation_chain,
-        )
-
-        self.log.info("Submitting prompt")
-        response = self.hook.text_generation_model_predict(
-            project_id=self.project_id,
-            location=self.location,
-            prompt=self.prompt,
-            pretrained_model=self.pretrained_model,
-            temperature=self.temperature,
-            max_output_tokens=self.max_output_tokens,
-            top_p=self.top_p,
-            top_k=self.top_k,
-        )
-
-        self.log.info("Model response: %s", response)
-        self.xcom_push(context, key="model_response", value=response)
-
-        return response
-
-
 class TextEmbeddingModelGetEmbeddingsOperator(GoogleCloudBaseOperator):
     """
     Uses the Vertex AI Embeddings API to generate embeddings based on prompt.

airflow/providers/google/cloud/operators/vertex_ai/pipeline_job.py

@@ -112,6 +112,10 @@ class RunPipelineJobOperator(GoogleCloudBaseOperator):
         "project_id",
         "input_artifacts",
         "impersonation_chain",
+        "template_path",
+        "pipeline_root",
+        "parameter_values",
+        "service_account",
     ]
     operator_extra_links = (VertexAIPipelineJobLink(),)
 

airflow/providers/google/cloud/transfers/bigquery_to_bigquery.py

@@ -25,6 +25,7 @@ from typing import TYPE_CHECKING
 from airflow.models import BaseOperator
 from airflow.providers.google.cloud.hooks.bigquery import BigQueryHook
 from airflow.providers.google.cloud.links.bigquery import BigQueryTableLink
+from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID
 
 if TYPE_CHECKING:
     from airflow.utils.context import Context
@@ -73,6 +74,7 @@ class BigQueryToBigQueryOperator(BaseOperator):
         If set as a sequence, the identities from the list must grant
         Service Account Token Creator IAM role to the directly preceding identity, with first
         account from the list granting this role to the originating account (templated).
+    :param project_id: Google Cloud Project where the job is running
     """
 
     template_fields: Sequence[str] = (
@@ -93,6 +95,7 @@ class BigQueryToBigQueryOperator(BaseOperator):
         write_disposition: str = "WRITE_EMPTY",
         create_disposition: str = "CREATE_IF_NEEDED",
         gcp_conn_id: str = "google_cloud_default",
+        project_id: str = PROVIDE_PROJECT_ID,
         labels: dict | None = None,
         encryption_configuration: dict | None = None,
         location: str | None = None,
@@ -112,6 +115,7 @@ class BigQueryToBigQueryOperator(BaseOperator):
         self.impersonation_chain = impersonation_chain
         self.hook: BigQueryHook | None = None
         self._job_conf: dict = {}
+        self.project_id = project_id
 
     def _prepare_job_configuration(self):
         self.source_project_dataset_tables = (
@@ -124,7 +128,7 @@ class BigQueryToBigQueryOperator(BaseOperator):
         for source_project_dataset_table in self.source_project_dataset_tables:
             source_project, source_dataset, source_table = self.hook.split_tablename(
                 table_input=source_project_dataset_table,
-                default_project_id=self.hook.project_id,
+                default_project_id=self.project_id,
                 var_name="source_project_dataset_table",
             )
             source_project_dataset_tables_fixup.append(
@@ -133,7 +137,7 @@ class BigQueryToBigQueryOperator(BaseOperator):
 
         destination_project, destination_dataset, destination_table = self.hook.split_tablename(
             table_input=self.destination_project_dataset_table,
-            default_project_id=self.hook.project_id,
+            default_project_id=self.project_id,
         )
         configuration = {
             "copy": {
@@ -168,12 +172,12 @@ class BigQueryToBigQueryOperator(BaseOperator):
             impersonation_chain=self.impersonation_chain,
         )
 
-        if not self.hook.project_id:
-            raise ValueError("The project_id should be set")
+        if not self.project_id:
+            self.project_id = self.hook.project_id
 
         configuration = self._prepare_job_configuration()
         self._job_conf = self.hook.insert_job(
-            configuration=configuration, project_id=self.hook.project_id
+            configuration=configuration, project_id=self.project_id
         ).to_api_repr()
 
         dest_table_info = self._job_conf["configuration"]["copy"]["destinationTable"]

airflow/providers/google/cloud/transfers/facebook_ads_to_gcs.py

@@ -208,7 +208,7 @@ class FacebookAdsReportToGcsOperator(BaseOperator):
 
     def _flush_rows(self, converted_rows: list[Any] | None, object_name: str):
         if converted_rows:
-            headers = converted_rows[0].keys()
+            headers = self.fields
             with tempfile.NamedTemporaryFile("w", suffix=".csv") as csvfile:
                 writer = csv.DictWriter(csvfile, fieldnames=headers)
                 writer.writeheader()