--- title: "Getting started with AI Document Processing" canonical_url: "https://www.nutrient.io/sdk/ai-document-processing/getting-started/" md_url: "https://www.nutrient.io/sdk/ai-document-processing/getting-started.md" last_updated: "2026-05-21T17:12:02.375Z" description: "Learn how to integrate AI Document Processing (formerly known as XtractFlow) into your application. Enable AI-powered data extraction using natural language instructions, eliminating the need for predefined rules or coding." --- # Getting started with AI Document Processing This guide explains how to integrate AI Document Processing (formerly known as XtractFlow) into your application. **Test without installing** You can test the SDK capabilities in our online demo. [Read more](http://demo.xtractflow.com/) ## What is AI Document Processing AI Document Processing is an intelligent document processing (IDP) SDK that extends our existing [key-value pair](https://www.nutrient.io/guides/dotnet/extraction/key-value-pairs/kvp-overview.md) (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](https://visualstudio.microsoft.com/downloads/). - 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](https://www.nutrient.io/contact-sales/) 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](https://platform.openai.com/signup) to obtain an [API key](https://platform.openai.com/account/api-keys). > The OpenAI API has attained **SOC 2 Type 2** compliance (see the [official announcement](https://trust.openai.com/?tcuUid=16a1f4e1-9120-45c1-96bd-5c1007f0f3d1)). ### Creating an Azure OpenAI account To create an Azure OpenAI account, follow the [quickstart](https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart?tabs=command-line&pivots=programming-language-studio) guide. For data processing, privacy, and security details, refer to the [Azure OpenAI Service](https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy) 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. - Name: `GdPicture.XtractFlow` - Target framework: NET 8.0 and higher - nuget.org link: [https://www.nuget.org/packages/GdPicture.XtractFlow/](https://www.nuget.org/packages/GdPicture.XtractFlow/) 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](https://www.gdpicture.com/download/xtractflow_dicts.zip), 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](https://www.nuget.org/packages/GdPicture.Resources) 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: - [Important concepts to understand](https://www.nutrient.io/guides/ai-document-processing/concepts.md) - [Classify and recognize documents](https://www.nutrient.io/guides/ai-document-processing/classify-documents.md) - [Recognize and process invoices](https://www.nutrient.io/guides/ai-document-processing/invoices.md) - [Build a custom data extraction template](https://www.nutrient.io/guides/ai-document-processing/custom-templates.md)