Giter Site home page Giter Site logo

googlecloudplatform / documentai-notebooks Goto Github PK

View Code? Open in Web Editor NEW
77.0 11.0 36.0 82.41 MB

A centralized repository for AI Platform notebooks using the Google Cloud Document AI API.

License: Apache License 2.0

Jupyter Notebook 100.00%
ai-platform-notebooks notebook cloud gcs

documentai-notebooks's Introduction

Document AI Notebooks

This repository contains several Jupyter notebooks to be used with the Cloud Document AI Platform. Use the general notebooks to process any form type or the specialized notebooks for any of the solutions such as Procurement DocAI or Lending DocAI. These notebooks help you get started with extracting data from your documents whether you're bring your own form types or using one of our specialized parsers for invoices, receipts, tax forms and more.

gif

Prerequisites

You must have your own GCP project with billing enabled and have working knowledge of the following products:

Set Up Steps

  1. Set up your GCP project for Document AI following the Setup Guide.
  2. Enable the 'Document AI API' in your project in the Document AI Platform.
  3. Create or use an existing instance of AI Platform Notebook with Python 3 using the default configurations.
  4. In the notebook, go to Git > Clone a Repository and paste the repository URL.
  5. Install the required libraries in the notebook terminal python -m pip install -r requirements.txt

Please note Colab and Jupyter notebooks are also work with these samples. However, additional authentication will be required for service accounts.

Instructions

  1. Identify which form type or utility you would like to run through a processor.
  2. Create your processor using the instructions.
  3. Copy your processor id. processorId
  4. Update the PROCESSOR_ID, PROJECT_ID and REGION variables in the notebook.
PROJECT_ID = "YOUR_PROJECT_ID_HERE"
LOCATION = "LOCATION"  # Format is 'us' or 'eu'
PROCESSOR_ID = "PROCESSOR_ID"  # Create processor in Cloud Console

Please note, the location must match the one assigned to the processor.

  1. Run the notebook.

documentai-notebooks's People

Contributors

asrivas avatar asrivas-devrel avatar camushoilingma avatar holtskinner avatar marsbroshok avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

documentai-notebooks's Issues

Unable to get TextStyle from PDF OCR JSON result

Hi,

I've been working on a project and was wondering that in the document ai reference webpage they are showing us a response type with text style in JSON, and per the Documentation, I tried the same code provided on the main guidance webpage, in my JSON output the text style of font style was missing can anyone help me with this. I've been using a computer-generated pdf.

Thank you in advance

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.