Creating a content parser in Azure AI Foundry
Here you start with a sample of the content you want to analyze. Upload your example to Azure AI Foundry and the service will suggest templates from its own library based on your document. Choose the most suitable one and edit it to add your own fields and types. It’s a good idea to add descriptions to your modified schema to aid debugging and support other developers. Once you have saved your custom schema, you can test the parser against a selection of sample documents. Once saved, the Azure AI Foundry tool creates your analyzer, ready to use. This will generate endpoint URLs to add to your code.
The sample templates are divided into four content categories: text, image, audio, and video. Some, like retail inventory management or media asset management, are industry specific, and Microsoft will likely add more as different use cases emerge. If you’ve used one of the Azure Cognitive Services before, you should find it much easier to use, with support for more complex documents and other content.
Each parser is a pipeline in its own right, processing inputs, extracting content, and then providing insights as well as application-ready information. The process is not limited to basic recognition, and the Document Analyzer’s add-on tools offer more functionality, including the ability to recognize and process barcodes and mathematical formulas in documents. The service will process handwritten content as well as type.