Document Intelligence custom template model

Custom template (formerly custom form) is an easy-to-train document model that accurately extracts labeled key-value pairs, selection marks, tables, regions, and signatures from documents. Template models use layout cues to extract values from documents and are suitable to extract fields from highly structured documents with defined visual templates.

Model capabilities

Custom template models support key-value pairs, selection marks, tables, signature fields, and selected regions.

Dealing with variations

Template models rely on a defined visual template, changes to the template results in lower accuracy. In those instances, split your training dataset to include at least five samples of each template and train a model for each of the variations. You can then compose the models into a single endpoint. For subtle variations, like digital PDF documents and images, it's best to include at least five examples of each type in the same training dataset.

Input requirements

• For best results, provide one clear photo or high-quality scan per document.

• Supported file formats:

  Model	PDF	Image: JPEG/JPG, PNG, BMP, TIFF, HEIF	Microsoft Office: Word (DOCX), Excel (XLSX), PowerPoint (PPTX), and HTML
  Read	✔	✔	✔
  Layout	✔	✔	✔ (2024-02-29-preview, 2023-10-31-preview or later)
  General Document	✔	✔
  Prebuilt	✔	✔
  Custom	✔	✔

  ✱ Microsoft Office files are currently not supported for other models or versions.

• For PDF and TIFF, up to 2,000 pages can be processed (with a free tier subscription, only the first two pages are processed).

• The file size for analyzing documents is 500 MB for paid (S0) tier and 4 MB for free (F0) tier.

• Image dimensions must be between 50 x 50 pixels and 10,000 px x 10,000 pixels.

• If your PDFs are password-locked, you must remove the lock before submission.

• The minimum height of the text to be extracted is 12 pixels for a 1024 x 768 pixel image. This dimension corresponds to about 8-point text at 150 dots per inch (DPI).

• For custom model training, the maximum number of pages for training data is 500 for the custom template model and 50,000 for the custom neural model.

• For custom extraction model training, the total size of training data is 50 MB for template model and 1G-MB for the neural model.

• For custom classification model training, the total size of training data is 1GB with a maximum of 10,000 pages.

Training a model

https://{endpoint}/documentintelligence/documentModels:build?api-version=2024-07-31-preview


{
  "modelId": "string",
  "description": "string",
  "buildMode": "template",
  "azureBlobSource":
  {
    "containerUrl": "string",
    "prefix": "string"
  }
}

https://{endpoint}/formrecognizer/documentModels:build?api-version=2023-07-31

{
  "modelId": "string",
  "description": "string",
  "buildMode": "template",
  "azureBlobSource":
  {
    "containerUrl": "string",
    "prefix": "string"
  }
}

Supported languages and locales

See our Language Support—custom models page for a complete list of supported languages.

Next steps

Learn to create and compose custom models: