Document AI Toolbox client libraries

This page shows how to get started with the Cloud Client Libraries for the Document AI Toolbox API. Read more about the client libraries for Cloud APIs, including the older Google API Client Libraries, in Client Libraries Explained.

Install the client library

Python

For more information, see Setting Up a Python Development Environment.

pip install --upgrade google-cloud-documentai-toolbox

Set up authentication

When you use client libraries, you use Application Default Credentials (ADC) to authenticate. For information about setting up ADC, see Provide credentials for Application Default Credentials. For information about using ADC with client libraries, see Authenticate using client libraries.

Use the client library

Document AI Toolbox is an SDK for Python that provides utility functions for managing, manipulating, and extracting information from the document response. It creates a "wrapped" document object from a processed document response from JSON files in Cloud Storage, local JSON files, or output directly from the process_document() method.

It can perform the following actions:

Code Samples

The following code samples demonstrate how to use Document AI Toolbox.

Quickstart


from google.cloud.documentai_toolbox import document
from google.cloud.documentai_toolbox import gcs_utilities

# TODO(developer): Uncomment these variables before running the sample.
# Given a document.proto or sharded document.proto in path gs://bucket/path/to/folder
# gcs_bucket_name = "bucket"
# gcs_prefix = "path/to/folder"


def quickstart_sample(gcs_bucket_name: str, gcs_prefix: str) -> None:
    print("Document structure in Cloud Storage")
    gcs_utilities.print_gcs_document_tree(
        gcs_bucket_name=gcs_bucket_name, gcs_prefix=gcs_prefix
    )

    wrapped_document = document.Document.from_gcs(
        gcs_bucket_name=gcs_bucket_name, gcs_prefix=gcs_prefix
    )

    print("Document Successfully Loaded!")
    print(f"\t Number of Pages: {len(wrapped_document.pages)}")
    print(f"\t Number of Entities: {len(wrapped_document.entities)}")

    for idx, page in enumerate(wrapped_document.pages):
        print(f"Page {idx}")
        for block in page.blocks:
            print(block.text)
        for paragraph in page.paragraphs:
            print(paragraph.text)

    for entity in wrapped_document.entities:
        print(f"{entity.type_} : {entity.mention_text}")

Tables


from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a local document.proto or sharded document.proto in path
# document_path = "path/to/local/document.json"
# output_file_prefix = "output/table"


def table_sample(document_path: str, output_file_prefix: str) -> None:
    wrapped_document = document.Document.from_document_path(document_path=document_path)

    print("Tables in Document")
    for page in wrapped_document.pages:
        for table_index, table in enumerate(page.tables):
            # Convert table to Pandas Dataframe
            # Refer to https://pandas.pydata.org/docs/reference/frame.html for all supported methods
            df = table.to_dataframe()
            print(df)

            output_filename = f"{output_file_prefix}-{page.page_number}-{table_index}"

            # Write Dataframe to CSV file
            df.to_csv(f"{output_filename}.csv", index=False)

            # Write Dataframe to HTML file
            df.to_html(f"{output_filename}.html", index=False)

            # Write Dataframe to Markdown file
            df.to_markdown(f"{output_filename}.md", index=False)

BigQuery export


from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a document.proto or sharded document.proto in path gs://bucket/path/to/folder
# gcs_bucket_name = "bucket"
# gcs_prefix = "path/to/folder"
# dataset_name = "test_dataset"
# table_name = "test_table"
# project_id = "YOUR_PROJECT_ID"


def entities_to_bigquery_sample(
    gcs_bucket_name: str,
    gcs_prefix: str,
    dataset_name: str,
    table_name: str,
    project_id: str,
) -> None:
    wrapped_document = document.Document.from_gcs(
        gcs_bucket_name=gcs_bucket_name, gcs_prefix=gcs_prefix
    )

    job = wrapped_document.entities_to_bigquery(
        dataset_name=dataset_name, table_name=table_name, project_id=project_id
    )

    # Also supported:
    # job = wrapped_document.form_fields_to_bigquery(
    #     dataset_name=dataset_name, table_name=table_name, project_id=project_id
    # )

    print("Document entities loaded into BigQuery")
    print(f"Job ID: {job.job_id}")
    print(f"Table: {job.destination.path}")

PDF split


from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a local document.proto or sharded document.proto from a splitter/classifier in path
# document_path = "path/to/local/document.json"
# pdf_path = "path/to/local/document.pdf"
# output_path = "resources/output/"


def split_pdf_sample(document_path: str, pdf_path: str, output_path: str) -> None:
    wrapped_document = document.Document.from_document_path(document_path=document_path)

    output_files = wrapped_document.split_pdf(
        pdf_path=pdf_path, output_path=output_path
    )

    print("Document Successfully Split")
    for output_file in output_files:
        print(output_file)

Image extraction


from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a local document.proto or sharded document.proto from an identity processor in path
# document_path = "path/to/local/document.json"
# output_path = "resources/output/"
# output_file_prefix = "exported_photo"
# output_file_extension = "png"


def export_images_sample(
    document_path: str,
    output_path: str,
    output_file_prefix: str,
    output_file_extension: str,
) -> None:
    wrapped_document = document.Document.from_document_path(document_path=document_path)

    output_files = wrapped_document.export_images(
        output_path=output_path,
        output_file_prefix=output_file_prefix,
        output_file_extension=output_file_extension,
    )
    print("Images Successfully Exported")
    for output_file in output_files:
        print(output_file)

Vision conversion


from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a document.proto or sharded document.proto in path gs://bucket/path/to/folder
# gcs_bucket_name = "bucket"
# gcs_prefix = "path/to/folder"


def convert_document_to_vision_sample(
    gcs_bucket_name: str,
    gcs_prefix: str,
) -> None:
    wrapped_document = document.Document.from_gcs(
        gcs_bucket_name=gcs_bucket_name, gcs_prefix=gcs_prefix
    )

    # Converting wrapped_document to vision AnnotateFileResponse
    annotate_file_response = (
        wrapped_document.convert_document_to_annotate_file_response()
    )

    print("Document converted to AnnotateFileResponse!")
    print(
        f"Number of Pages : {len(annotate_file_response.responses[0].full_text_annotation.pages)}"
    )

hOCR conversion


from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a document.proto or sharded document.proto in path gs://bucket/path/to/folder
# document_path = "path/to/local/document.json"
# document_title = "your-document-title"


def convert_document_to_hocr_sample(document_path: str, document_title: str) -> str:
    wrapped_document = document.Document.from_document_path(document_path=document_path)

    # Converting wrapped_document to hOCR format
    hocr_string = wrapped_document.export_hocr_str(title=document_title)

    print("Document converted to hOCR!")
    return hocr_string

Third-party conversion


from google.cloud.documentai_toolbox import converter

# TODO(developer): Uncomment these variables before running the sample.
# This sample will convert external annotations to the Document.json format used by Document AI Workbench for training.
# To process this the external annotation must have these type of objects:
#       1) Type
#       2) Text
#       3) Bounding Box (bounding boxes must be 1 of the 3 optional types)
#
# This is the bare minimum requirement to convert the annotations but for better accuracy you will need to also have:
#       1) Document width & height
#
# Bounding Box Types:
#   Type 1:
#       bounding_box:[{"x":1,"y":2},{"x":2,"y":2},{"x":2,"y":3},{"x":1,"y":3}]
#   Type 2:
#       bounding_box:{ "Width": 1, "Height": 1, "Left": 1, "Top": 1}
#   Type 3:
#       bounding_box: [1,2,2,2,2,3,1,3]
#
#   Note: If these types are not sufficient you can propose a feature request or contribute the new type and conversion functionality.
#
# Given a folders in gcs_input_path with the following structure :
#
# gs://path/to/input/folder
#   ├──test_annotations.json
#   ├──test_config.json
#   └──test.pdf
#
# An example of the config is in sample-converter-configs/Azure/form-config.json
#
# location = "us",
# processor_id = "my_processor_id"
# gcs_input_path = "gs://path/to/input/folder"
# gcs_output_path = "gs://path/to/input/folder"


def convert_external_annotations_sample(
    location: str,
    processor_id: str,
    project_id: str,
    gcs_input_path: str,
    gcs_output_path: str,
) -> None:
    converter.convert_from_config(
        project_id=project_id,
        location=location,
        processor_id=processor_id,
        gcs_input_path=gcs_input_path,
        gcs_output_path=gcs_output_path,
    )

Document batches


from google.cloud import documentai
from google.cloud.documentai_toolbox import gcs_utilities

# TODO(developer): Uncomment these variables before running the sample.
# Given unprocessed documents in path gs://bucket/path/to/folder
# gcs_bucket_name = "bucket"
# gcs_prefix = "path/to/folder"
# batch_size = 50


def create_batches_sample(
    gcs_bucket_name: str,
    gcs_prefix: str,
    batch_size: int = 50,
) -> None:
    # Creating batches of documents for processing
    batches = gcs_utilities.create_batches(
        gcs_bucket_name=gcs_bucket_name, gcs_prefix=gcs_prefix, batch_size=batch_size
    )

    print(f"{len(batches)} batch(es) created.")
    for batch in batches:
        print(f"{len(batch.gcs_documents.documents)} files in batch.")
        print(batch.gcs_documents.documents)

        # Use as input for batch_process_documents()
        # Refer to https://cloud.google.com/document-ai/docs/send-request
        # for how to send a batch processing request
        request = documentai.BatchProcessRequest(
            name="processor_name", input_documents=batch
        )

Merge Document shards


from google.cloud import documentai
from google.cloud.documentai_toolbox import document

# TODO(developer): Uncomment these variables before running the sample.
# Given a document.proto or sharded document.proto in path gs://bucket/path/to/folder
# gcs_bucket_name = "bucket"
# gcs_prefix = "path/to/folder"
# output_file_name = "path/to/folder/file.json"


def merge_document_shards_sample(
    gcs_bucket_name: str, gcs_prefix: str, output_file_name: str
) -> None:
    wrapped_document = document.Document.from_gcs(
        gcs_bucket_name=gcs_bucket_name, gcs_prefix=gcs_prefix
    )

    merged_document = wrapped_document.to_merged_documentai_document()

    with open(output_file_name, "w") as f:
        f.write(documentai.Document.to_json(merged_document))

    print(f"Document with {len(wrapped_document.shards)} shards successfully merged.")

Additional resources