I’m trying to find how to set the temp and staging buckets at the DataprocOperator. I’ve searched for all the internet and didnt find a good awnser.

import pendulum
from datetime import timedelta

from airflow.operators.dummy import DummyOperator
from airflow.providers.google.cloud.operators.dataproc import DataprocCreateClusterOperator, 
    DataprocDeleteClusterOperator, DataprocSubmitJobOperator
from airflow.decorators import task, dag

# config = Variable.get("teste", deserialize_json=True)
config = {
    "cluster_name": 'teste',
    "region": 'us-central1',
    "project_id": 'test-dataproc'
}

default_args = {
    "owner": "Airflow",
    "start_date": pendulum.datetime(2024, 4, 26, tz="America/Sao_Paulo"),
    "retries": 0,
    'retry_delay': timedelta(minutes=3)
}

@dag(
    "teste_dataproc",
    default_args=default_args,
    schedule_interval='0 3 * * 1-5',
    params=config,
    catchup=False,
    tags=["TESTE"],
)
def teste_dataproc():

    CLUSTER_CONFIG = {
        "gce_cluster_config" : {
            "zone_uri": "us-central1-a",
            "internal_ip_only": False,
        },
        "master_config": {
            "num_instances": 1,
            "machine_type_uri": "n1-standard-2",
            "disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 25},
        },
        "worker_config": {
            "num_instances": 2,
            "machine_type_uri": "n1-standard-2",
            "disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 25},
        },
        "software_config": {
            "properties": {
                "spark:spark.executor.memory": "3g",  # Memory for each executor
                "spark:spark.executor.cores": "2",    # Number of cores per executor
                "spark:spark.executor.instances": "4"  # Number of executor instances
            }
        }
    }

    create_cluster = DataprocCreateClusterOperator(
        task_id="create_dataproc_cluster",
        project_id="{{ params.project_id }}",
        cluster_config=CLUSTER_CONFIG,
        region="{{ params.region }}",
        cluster_name="{{ params.cluster_name }}",
        staging_bucket="gs://teste/dataproc/staging",  # Staging bucket
        temp_bucket="gs://teste/dataproc/temp"  # Temp bucket
    )

    create_cluster

teste_dataproc()

I know that the staging_bucket and the temp_bucket params are not correct, so, if someone knows something, would be a good help.