mirror of
https://github.com/open-metadata/OpenMetadata.git
synced 2025-07-24 01:40:00 +00:00
96 lines
2.6 KiB
Markdown
96 lines
2.6 KiB
Markdown
---
|
|
description: >-
|
|
We highly recommend using Airflow or similar schedulers to run Metadata
|
|
Connectors.
|
|
---
|
|
|
|
# Example Metadata Ingestion
|
|
|
|
This is an example of how to create an Airflow DAG to ingest the sample data provided in the git [repository](https://github.com/open-metadata/OpenMetadata/tree/main/ingestion/examples/sample\_data).
|
|
|
|
## Airflow Example for Sample Data
|
|
|
|
```python
|
|
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
|
|
|
|
```python
|
|
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 that 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](https://github.com/open-metadata/OpenMetadata/tree/main/ingestion/examples/workflows) and refer to [Connectors](../connectors/).
|