Skip to content

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 JSON files in Cloud Storage, local JSON files, or output directly from the Document AI API.

License

Notifications You must be signed in to change notification settings

googleapis/python-documentai-toolbox

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Document AI Toolbox

experimental versions

Document AI Toolbox: Document AI Toolbox aims to reduce the friction of managing, manipulating, and extracting information from outputs of Document AI BatchProcessDocuments() (JSON files written to user-managed GCS buckets) and ProcessDocument() methods, programmatically.

Disclaimer

The Document AI Toolbox is in an experimental state. This library is a work-in-progress and is likely to have backwards-incompatible changes. Users of the toolbox might need to rewrite their code when upgrading the toolbox version.

Quick Start

In order to use this library, you first need to go through the following steps:

Enabling Document AI may not be technically required to use this library, unless ProcessDocument() is intended to be used. But you must enable the Storage API to access GCS buckets that contains the output of BatchProcessDocument(). You will need to enable the BigQuery API if you intend to use the BigQuery features.

  1. Select or create a Cloud Platform project.
  2. Enable billing for your project.
  3. Enable the Storage API.
  4. Enable the Document AI API.
  5. Enable the BigQuery API.
  6. Setup Authentication.

Installation

Install this library in a virtualenv using pip. virtualenv is a tool to create isolated Python environments. The basic problem it addresses is one of dependencies and versions, and indirectly permissions.

With virtualenv, it's possible to install this library without needing system install permissions, and without clashing with the installed system dependencies.

Code samples and snippets

Code samples and snippets live in the samples/ folder.

Supported Python Versions

Our client libraries are compatible with all current active and maintenance versions of Python.

Python >= 3.8

Unsupported Python Versions

Python <= 3.7

NOTE: Python 3.7 was marked as unsupported by the python community in June 2023. We recommend that all developers upgrade to Python 3.8 and newer as soon as they can. Support for Python 3.7 will be removed from all client libraries after January 1 2024. Client libraries that support Python 3.7 will continue to be available for download, but releases after January 1 2024 will only target Python 3.8 and newer.

If you are using an end-of-life version of Python, we recommend that you update as soon as possible to an actively supported version.

Mac/Linux

pip install virtualenv
virtualenv <your-env>
source <your-env>/bin/activate
<your-env>/bin/pip install google-cloud-documentai-toolbox

Windows

pip install virtualenv
virtualenv <your-env>
<your-env>\Scripts\activate
<your-env>\Scripts\pip.exe install google-cloud-documentai-toolbox

Next Steps

About

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 JSON files in Cloud Storage, local JSON files, or output directly from the Document AI API.

Topics

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Languages