Getting started with AI Document Processing

This guide explains how to integrate AI Document Processing into your application.

Test without installing

What is AI Document Processing

AI Document Processing (formerly known as XtractFlow) is an intelligent document processing (IDP) SDK that extends our existing key-value pair (KVP) technology with large language models (LLMs) to deliver best-in-class extraction and classification accuracy.

This new paradigm breaks traditional data extraction barriers to achieve a higher degree of accuracy compared to pure AI/ML alternatives.

Our solution offers the versatility of being used both as a REST microservice, suitable for hosting in any global region, and as an integrated API within desktop or server applications.

The solution operates without the need for storing documents or any extracted content, thereby greatly enhancing alignment with a wide array of data processing and retention policies.

Prerequisites

Before you follow the procedure in this guide, ensure you have:

  • A development environment — A modern integrated development environment (IDE) is highly recommended for an optimal development experience. While not strictly a prerequisite, Visual Studio or Visual Studio Code are our recommended tools. If you don’t have them, download and install them from Visual Studio Downloads(opens in a new tab).
  • A GdPicture.NET license key. To try the product in demo mode, use an empty string as the license key (for example, licenseKey: ""). For production use, contact our Sales team to grab your license key.
  • An LLM provider API key. AI Document Processing currently supports OpenAI and Azure OpenAI (other LLMs will be supported soon).

Obtaining an LLM provider API key (optional)

Skip this step if you already have an API key from one of the supported LLM providers.

Creating an OpenAI account

To create an OpenAI account, sign up(opens in a new tab) to obtain an API key(opens in a new tab).

The OpenAI API has attained SOC 2 Type 2 compliance (see the official announcement(opens in a new tab)).

Creating an Azure OpenAI account

To create an Azure OpenAI account, follow the quickstart(opens in a new tab) guide. For data processing, privacy, and security details, refer to the Azure OpenAI Service(opens in a new tab) article.

Azure OpenAI Service can be used in a HIPAA-compliant manner.

Installing AI Document Processing

The AI Document Processing SDK (formerly known as XtractFlow) is delivered as a NuGet package.

To incorporate the NuGet reference into your application:

  1. Right-click the project name in Solution Explorer and click Manage Nuget Packages....
  2. Enter XtractFlow in the search bar. In the search results, choose GdPicture.XtractFlow and click Install.

Machine vision resources

Machine vision resources(opens in a new tab), such as OCR models and language packs, are required for certain functionalities. The most direct way to obtain these is by adding the GdPicture.Resources NuGet package(opens in a new tab) to your project.

Once this package is installed, the necessary resources are automatically handled, and you do not need to manually configure Configuration.ResourceFolder.

Next steps

After installation, take a look at our guides to see some examples of how to use AI Document Processing: