Train a processor version

Start a new training job for a processor

Explore further

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

Code sample

Python

For more information, see the Document AI Python API reference documentation.

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


from typing import Optional

from google.api_core.client_options import ClientOptions
from google.cloud import documentai  # type: ignore

# TODO(developer): Uncomment these variables before running the sample.
# project_id = 'YOUR_PROJECT_ID'
# location = 'YOUR_PROCESSOR_LOCATION' # Format is 'us' or 'eu'
# processor_id = 'YOUR_PROCESSOR_ID'
# processor_version_display_name = 'new-processor-version'
# train_data_uri = 'gs://bucket/directory/' # (Optional)
# test_data_uri = 'gs://bucket/directory/' # (Optional)


def train_processor_version_sample(
    project_id: str,
    location: str,
    processor_id: str,
    processor_version_display_name: str,
    train_data_uri: Optional[str] = None,
    test_data_uri: Optional[str] = None,
) -> None:
    # You must set the api_endpoint if you use a location other than 'us', e.g.:
    opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")

    client = documentai.DocumentProcessorServiceClient(client_options=opts)

    # The full resource name of the processor
    # e.g. `projects/{project_id}/locations/{location}/processors/{processor_id}
    parent = client.processor_path(project_id, location, processor_id)

    processor_version = documentai.ProcessorVersion(
        display_name=processor_version_display_name
    )

    # If train/test data is not supplied, the default sets in the Cloud Console will be used
    input_data = documentai.TrainProcessorVersionRequest.InputData(
        training_documents=documentai.BatchDocumentsInputConfig(
            gcs_prefix=documentai.GcsPrefix(gcs_uri_prefix=train_data_uri)
        ),
        test_documents=documentai.BatchDocumentsInputConfig(
            gcs_prefix=documentai.GcsPrefix(gcs_uri_prefix=test_data_uri)
        ),
    )

    request = documentai.TrainProcessorVersionRequest(
        parent=parent, processor_version=processor_version, input_data=input_data
    )

    operation = client.train_processor_version(request=request)
    # Print operation details
    print(operation.operation.name)
    # Wait for operation to complete
    response = documentai.TrainProcessorVersionResponse(operation.result())

    metadata = documentai.TrainProcessorVersionMetadata(operation.metadata)

    print(f"New Processor Version:{response.processor_version}")
    print(f"Training Set Validation: {metadata.training_dataset_validation}")
    print(f"Test Set Validation: {metadata.test_dataset_validation}")

What's next

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