OpenMetadata/docs/install/metadata-ingestion/airflow/run-metadata-ingestion.md

description
Below is the sample code example you can refer to integrate with Airflow

Run Metadata Ingestion

Airflow Example for Sample Data

import pathlib
import json
from datetime import timedelta
from airflow import DAG

try:
    from airflow.operators.python import PythonOperator
except ModuleNotFoundError:
    from airflow.operators.python_operator import PythonOperator

from metadata.config.common import load_config_file
from metadata.ingestion.api.workflow import Workflow
from airflow.utils.dates import days_ago

default_args = {
    "owner": "user_name",
    "email": ["username@org.com"],
    "email_on_failure": False,
    "retries": 3,
    "retry_delay": timedelta(minutes=5),
    "execution_timeout": timedelta(minutes=60)
}

config = """
{
  "source": {
    "type": "sample-data",
    "config": {
      "sample_data_folder": "./examples/sample_data"
    }
  },
  "sink": {
    "type": "metadata-rest",
    "config": {}
  },
  "metadata_server": {
    "type": "metadata-server",
    "config": {
      "api_endpoint": "http://localhost:8585/api",
      "auth_provider_type": "no-auth"
    }
  }
}
"""

def metadata_ingestion_workflow():
    workflow_config = json.loads(config)
    workflow = Workflow.create(workflow_config)
    workflow.execute()
    workflow.raise_from_status()
    workflow.print_status()
    workflow.stop()


with DAG(
    "sample_data",
    default_args=default_args,
    description="An example DAG which runs a OpenMetadata ingestion workflow",
    start_date=days_ago(1),
    is_paused_upon_creation=False,
    schedule_interval='*/5 * * * *', 
    catchup=False,
) as dag:
    ingest_task = PythonOperator(
        task_id="ingest_using_recipe",
        python_callable=metadata_ingestion_workflow,
    )

we are using a python method like below

def metadata_ingestion_workflow():
    workflow_config = json.loads(config)
    workflow = Workflow.create(workflow_config)
    workflow.execute()
    workflow.raise_from_status()
    workflow.print_status()
    workflow.stop

Create a Workflow instance and pass a sample-data configuration which will read metadata from Json files and ingest it into the OpenMetadata Server. You can customize this configuration or add different connectors please refer to our examples and refer to Connectors.