Studio experience for Document Intelligence

This content applies to:checkmark v3.1 (GA) | Previous versions: blue-checkmark v3.0 (GA)

Azure AI Document Intelligence Studio is an online tool that you can use to visually explore, understand, train, and integrate features from Document Intelligence into your applications. The studio provides a platform for you to experiment with the different Document Intelligence models. You can also sample returned data in an interactive manner without the need to write code. You can use the studio experience to:

  • Learn more about the different capabilities in Document Intelligence.
  • Use your Document Intelligence resource to test models on sample documents or upload your own documents.
  • Experiment with different add-on and preview features to adapt the output to your needs.
  • Train custom classification models to classify documents.
  • Train custom extraction models to extract fields from documents.
  • Get sample code for the language-specific SDKs to integrate into your applications.

Important

Document Intelligence Studio has distinct URLs for sovereign cloud regions:

Document Intelligence Studio supports Document Intelligence v3.0 and later API versions for model analysis and custom model training. Previously trained v2.1 models with labeled data are supported, but not v2.1 model training. For information about migrating from v2.1 to v3.0, see the REST API migration guide.

Use the Document Intelligence Studio quickstart to start analyzing documents with document analysis or prebuilt models. Build custom models and reference the models in your applications by using one of the language-specific SDKs.

Document Intelligence model support

Use the help wizard, labeling interface, training step, and interactive visualizations to understand how each feature works.

  • Read: Try out the Document Intelligence Studio read feature with sample documents or your own documents. Extract text lines, words, detected languages, and handwritten style, if detected. To learn more, see Read overview.
  • Layout: Try out the Document Intelligence layout feature with sample documents or your own documents. Extract text, tables, selection marks, and structure information. To learn more, see Layout overview.
  • Prebuilt models: Use the Document Intelligence prebuilt models to add intelligent document processing to your apps and flows without having to train and build your own models. As an example, start with the Document Intelligence invoice feature. To learn more, see Models overview.
  • Custom extraction models: Use the Document Intelligence Studio custom models feature to extract fields and values from models that are trained with your data and tailored to your forms and documents. To extract data from multiple form types, create standalone custom models. You can also combine two or more custom models and create a composed model. Test the custom model with your sample documents and iterate to improve the model. To learn more, see Custom models overview.
  • Custom classification models: Document classification is a new scenario supported by Document Intelligence. The document classifier API supports classification and splitting scenarios. Train a classification model to identify the different types of documents that your application supports. The input file for the classification model can contain multiple documents and classifies each document within an associated page range. To learn more, see Custom classification models.
  • Add-on capabilities: Document Intelligence supports more sophisticated analysis capabilities. You can enable and disable these optional capabilities in the studio by using Analyze Options on each model page. Four add-on capabilities are available: highResolution, formula, font, and barcode extraction. To learn more, see Add-on capabilities.

Related content