acryl-datahub

import os from datahub.emitter.rest_emitter import DatahubRestEmitter from datahub.emitter.mcp import MetadataChangeProposalWrapper from datahub.metadata.schema_classes import DatasetPropertiesClass # --- CLI Quickstart (run in your terminal) --- # 1. Install Docker and Docker Compose v2. # 2. Start a local DataHub instance: # datahub docker quickstart # (This command might take some time to download and start services) # # --- Python SDK Example (after DataHub is running) --- # For local quickstart, GMS server is typically http://localhost:8080 gms_server = os.environ.get("DATAHUB_GMS_SERVER", "http://localhost:8080") token = os.environ.get("DATAHUB_GMS_TOKEN", "") # For cloud/secured instances, provide a token # Initialize the REST emitter # Note: The 'token' parameter is available for direct use, not just extra_headers. emitter = DatahubRestEmitter(gms_server=gms_server, token=token) # Define a sample dataset URN dataset_urn = "urn:li:dataset:(urn:li:dataPlatform:hive,sample_dataset,PROD)" # Create a DatasetProperties aspect dataset_properties = DatasetPropertiesClass( description="This is a sample dataset emitted via the Python SDK quickstart.", customProperties={ "owner_team": "data_platform", "environment": "production_dev" } ) # Create a MetadataChangeProposalWrapper mcp = MetadataChangeProposalWrapper( entityUrn=dataset_urn, aspect=dataset_properties, ) # Emit the metadata change proposal try: emitter.emit(mcp) print(f"Successfully emitted properties for dataset: {dataset_urn}") except Exception as e: print(f"Failed to emit metadata: {e}") print("Ensure your DataHub instance is running and accessible at", gms_server)