Evaluate a processor version

Evaluate a processor version with a supplied dataset.

Explore further

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

• Evaluate performance

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 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_id = 'YOUR_PROCESSOR_VERSION_ID'
# gcs_input_uri = # Format: gs://bucket/directory/


def evaluate_processor_version_sample(
    project_id: str,
    location: str,
    processor_id: str,
    processor_version_id: str,
    gcs_input_uri: str,
) -> 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 version
    # e.g. `projects/{project_id}/locations/{location}/processors/{processor_id}/processorVersions/{processor_version_id}`
    name = client.processor_version_path(
        project_id, location, processor_id, processor_version_id
    )

    evaluation_documents = documentai.BatchDocumentsInputConfig(
        gcs_prefix=documentai.GcsPrefix(gcs_uri_prefix=gcs_input_uri)
    )

    # NOTE: Alternatively, specify a list of GCS Documents
    #
    # gcs_input_uri = "gs://bucket/directory/file.pdf"
    # input_mime_type = "application/pdf"
    #
    # gcs_document = documentai.GcsDocument(
    #     gcs_uri=gcs_input_uri, mime_type=input_mime_type
    # )
    # gcs_documents = [gcs_document]
    # evaluation_documents = documentai.BatchDocumentsInputConfig(
    #     gcs_documents=documentai.GcsDocuments(documents=gcs_documents)
    # )
    #

    request = documentai.EvaluateProcessorVersionRequest(
        processor_version=name,
        evaluation_documents=evaluation_documents,
    )

    # Make EvaluateProcessorVersion request
    # Continually polls the operation until it is complete.
    # This could take some time for larger files
    operation = client.evaluate_processor_version(request=request)
    # Print operation details
    # Format: projects/PROJECT_NUMBER/locations/LOCATION/operations/OPERATION_ID
    print(f"Waiting for operation {operation.operation.name} to complete...")
    # Wait for operation to complete
    response = documentai.EvaluateProcessorVersionResponse(operation.result())

    # After the operation is complete,
    # Print evaluation ID from operation response
    print(f"Evaluation Complete: {response.evaluation}")

What's next

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