Create an entity reconciliation job

Creates a new entity reconciliation job.

Explore further

For detailed documentation that includes this code sample, see the following:

• Manage entity reconciliation jobs with the API

Code sample

Python

For more information, see the Enterprise Knowledge Graph Python API reference documentation.

To authenticate to Enterprise Knowledge Graph, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

from google.cloud import enterpriseknowledgegraph as ekg

# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_GRAPH_LOCATION'          # Values: 'global'
# input_dataset = 'YOUR_INPUT_DATASET'      # BigQuery Dataset Name
# input_table = 'YOUR_INPUT_TABLE'          # BigQuery Table Name
# mapping_file_uri = 'YOUR_MAPPING_FILE     # GCS Path. Example: gs://ekg-test-gcs/mapping.yml
# output_dataset = 'YOUR_OUTPUT_DATASET'    # BigQuery Dataset Name

# Refer to https://cloud.google.com/enterprise-knowledge-graph/docs/schema
# entity_type = ekg.InputConfig.EntityType.Person


def create_entity_reconciliation_job_sample(
    project_id: str,
    location: str,
    input_dataset: str,
    input_table: str,
    mapping_file_uri: str,
    entity_type: int,
    output_dataset: str,
) -> None:
    # Create a client
    client = ekg.EnterpriseKnowledgeGraphServiceClient()

    # The full resource name of the location
    # e.g. projects/{project_id}/locations/{location}
    parent = client.common_location_path(project=project_id, location=location)

    # Input Parameters
    input_config = ekg.InputConfig(
        bigquery_input_configs=[
            ekg.BigQueryInputConfig(
                bigquery_table=client.table_path(
                    project=project_id, dataset=input_dataset, table=input_table
                ),
                gcs_uri=mapping_file_uri,
            )
        ],
        entity_type=entity_type,
    )

    # Output Parameters
    output_config = ekg.OutputConfig(
        bigquery_dataset=client.dataset_path(project=project_id, dataset=output_dataset)
    )

    entity_reconciliation_job = ekg.EntityReconciliationJob(
        input_config=input_config, output_config=output_config
    )

    # Initialize request argument(s)
    request = ekg.CreateEntityReconciliationJobRequest(
        parent=parent, entity_reconciliation_job=entity_reconciliation_job
    )

    # Make the request
    response = client.create_entity_reconciliation_job(request=request)

    print(f"Job: {response.name}")
    print(
        f"Input Table: {response.input_config.bigquery_input_configs[0].bigquery_table}"
    )
    print(f"Output Dataset: {response.output_config.bigquery_dataset}")
    print(f"State: {response.state.name}")

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.