How-to Guides

Getting started

• Document AI Overview

  Guide to the fundamental concepts of using Document AI.

• Introduction videos & labs

  Videos and interactive labs that cover the fundamental concepts of Document AI.

• Setup the Document AI API

  Perform all steps to enable and use the Document AI API.

• Create and manage processors

  Create a specific type of processor to process your document.

• Sending a processing request

  Send a document processing request to your created processor.

• Handling the processing response

  Handle the processing response that the processor sent back to you.

Document AI Workbench

• Processor training and evaluation overview

  Document AI Workbench lets you train new processor versions using your own training data and evaluate the quality of your processor version against your own test data.

• Create dataset

  This page describes how to create a dataset, import documents, and define a schema.

• Label documents

  A labeled dataset of documents is required to train, uptrain, or evaluate a processor version. This page describes how to apply labels from your processor schema to imported documents in your dataset.

• Train processor

  This page shows you how to train a new processor version from scratch, or uptrain a new processor version based on an existing one.

• Evaluate the performance of processors

  Document AI generates evaluation metrics, such as precision and recall, to help you determine the predictive performance of your processors.

• Managing processor versions

  Choose a different version to process your documents.

Other functionality

• Multi-region support

  Specify continent-level data storage and document processing.

• Table parsing

  Parse the contents of a table in a document.