Get started with Azure AI Content Understanding

Create a content analyzer in Azure AI Foundry

This is where you start with a sample of the content you want to analyze. Upload your sample to Azure AI Foundry and the service will suggest templates from its own library based on your document. Select the most appropriate one and edit it to add your own fields and types. It’s a good idea to add descriptions to your edited schema to make debugging easier and to help other developers. Once you save your custom schema, you can test the analyzer using a selection of sample documents. Once saved, the Azure AI Foundry tool creates your ready-to-use analyzer. This will generate endpoint URLs that you can add to your code.

The sample templates are divided into four content categories: text, image, audio and video. Some of these, such as retail inventory management or media inventory management, are industry-specific, and Microsoft will likely add more as different use cases arise. If you have used any of the Azure Cognitive Services in the past, you will find that they are much easier to use and support more complex documents and other content.

Each analyzer is a self-contained pipeline that processes input, extracts content, and then provides insights and application-ready information. The process involves more than just simple recognition, and the additional tools for the document analyzer provide additional functionality, including the ability to recognize and process barcodes and mathematical formulas in documents. The service handles both handwritten content and fonts.