What's new in Document Intelligence - Foundry Tools (original) (raw)

This content applies to: v4.0 (GA) v3.1 (GA) v3.0 (retiring) v2.1 (retiring)

Document Intelligence service is updated on an ongoing basis. Bookmark this page to stay up to date with release notes, feature enhancements, and our newest documentation.

Important

• Document Intelligence REST API v2.1 reaches end of support on September 15, 2027.
• Document Intelligence REST API 2022-08-31 v3.0 reaches end of support on March 30, 2029.
• To avoid production disruption, migrate now to Azure Document Intelligence 2024-11-30 v4.0. For more information, see Document Intelligence migration guide.

March 2026

Updated prebuilt tax form models

Prebuilt models for US tax forms have been updated supporting 2025 tax forms including quality improvement to address multi-copy extraction (e.g., multiple W-2s or 1099s in one document). You can now extract data from multi-form filings in a single request and get more comprehensive field coverage.

June 2025

Document Intelligence v4.0 Read container is now available!
This container image includes highly requested Read features like searchable PDF! For more information, see:

• Install and run containers
• Container image tags

April 2025

Document Intelligence v4.0 Layout container is now available!
For more information, see:

• Install and run containers
• Container image tags

December 2024

Document Intelligence v4.0 programming language SDKs are now generally available (GA)!

The latest client libraries default to the 2024-11-30 REST API (GA) version of the service.

For more information, see client libraries for the following supported programming languages:

• .NET (C#)
• Java
• JavaScript
• Python

November 2024

Document Intelligence REST API v4.0: 2024-11-30 REST API (GA) is now generally available (GA)! The v4.0 REST API includes the following changes:

• Batch API
  • Batch API now supports all models, including all read, layout, prebuilt verticals, and custom models.
  • Batch API supports LIST function to allow users to list batch jobs within past seven days.
  • Batch API supports DELETE function to explicitly delete batch job for GDPR and privacy compliance.
  • GetAnalyzeBatchResult supports resultId in response to LIST all resultIds.
• Searchable PDF. The prebuilt read model now supports images formats (JPEG/JPG, PNG, BMP, TIFF, HEIF) and language expansion to include Chinese, Japanese, and Korean for PDF output.
• Custom classification model
  • Custom classification model supports incremental training. You can add new samples to existing classes or add new classes by referencing an existing classifier.
  • With v4.0, custom classification model doesn't split documents by default during analysis. You need to explicitly set 'splitMode' property to auto to preserve the older behavior.
  • Custom classification model now supports 25,000 pages as new training page limit.
• Custom Neural Model
  • Custom Neural model now supports signature detection.
  • Custom neural models support paid training for longer duration when you need to train model with a larger labeled dataset. The first 20 training runs in a calendar month continue to be free. Any training operations over 20 is on the paid tier. Learn more details on billing.
• US Bank statement model
  • US Bank Statement Model now supports check table extraction.
• Check model
  • Supports Payer's Signature extraction
• Mortgage documents model
  • Mortgage model now supports signature detection for forms 1003, 1004, 1005 and closing disclosure.
• Receipt Model
  • Receipt Model now supports more fields including ReceiptType, Tax rate, CountryRegion, net amount and description.
• US Tax model
  • New prebuilt tax models added for 1095A, 1095C, 1099SSA, and W4.
• Delete analyze response
  • Analyze response is stored for 24 hours from when the operation completes for retrieval. For scenarios where you want to delete the response sooner, use the delete analyze response API to delete the response.
• The v4.0 API includes cumulative updates from preview releases as listed:
  • August 2024
  • May 2024
  • Feb 2024

August 2024

The Document Intelligence 2024-07-31-preview REST API is now available. This preview API introduces new and updated capabilities:

• Public preview version 2024-07-31-preview is currently available only in the following Azure regions. The new document field extraction model in Microsoft Foundry portal is only available in North Central US region:
• East US
• West US2
• West Europe
• North Central US
• Model compose with custom classifiers
  • Document Intelligence now adds support for composing model with an explicit custom classification model. Learn more about the benefits of using the new compose capability.
• Custom classification model
  • Custom classification model now supports updating the model in-place as well.
  • Custom classification model adds support for model copy operation to enable backup and disaster recovery.
  • Custom classification model now supports explicitly specifying pages to be classified from an input document.
• Mortgage documents model
  • Extract information from Appraisal (Form 1004).
  • Extract information from Validation of Employment (Form 1005).
• Check model
  • Extract payee, amount, date, and other relevant information from checks.​
• Pay Stub model
  • New prebuilt to process pay stubs to extract wages, hours, deductions, net pay and more.​
• Bank statement model
  • New prebuilt to extract account information including beginning and ending balances, transaction details from bank statements.​
• US Tax model
  • New unified US tax model that can extract from forms such as W-2, 1098, 1099, and 1040.
• Searchable PDF. The prebuilt read model now supports PDF output to download PDFs with embedded text from extraction results, allowing for PDF to be utilized in scenarios such as search copy of contents.
• Layout model now supports improved figure detection where figures from documents can now be downloaded as an image file to be used for further figure understanding. The layout model also features improvements to the OCR model for scanned text targeting improvements for single characters, boxed text, and dense text documents.
• Batch API
  • Document Intelligence now adds support for batch analysis operation to support analyzing a set of documents to simplify developer experience and improve efficiency.
• Add-on capabilities
  • Query fields AI quality of extraction is improved with the latest model.

May 2024

The Document Intelligence Studio adds support for Microsoft Entra (formerly Azure Active Directory) authentication. For more information, see Authentication in Document Intelligence Studio.

February 2024

The Document Intelligence 2024-07-31-preview REST API is now available. This preview API introduces new and updated capabilities:

• Public preview version 2024-07-31-preview is currently available only in the following Azure regions:
  • East US
  • West US2
  • West Europe
• Layout model now supports figure detection and hierarchical document structure analysis (sections and subsections). The AI quality of reading order and logical roles detection is also improved.
• Custom extraction models
  • Custom extraction models now support cell, row, and table level confidence scores. Learn more about table, row, and cell confidence.
  • Custom extraction models have AI quality improvements for field extraction.
  • Custom template extraction model now supports extracting overlapping fields. Learn more about overlapping fields and how you use them.
• Custom classification model
  • Custom classification model now supported incremental training for scenarios where you need to update the classifier model with added samples or classes. Learn more about incremental training.
  • Custom classification model adds support for Office document types (.docx, .pptx, and .xls). Learn more about expanded document type support.
• Invoice model
  • Support for new locales:

    Locale	Code
    Arabic	(ar)
    Bulgarian	(bg)
    Greek	(el)
    Hebrew	(he)
    Macedonian	(mk)
    Russian (ru)	Serbian Cyrillic (sr-cyrl)
    Ukrainian	(uk)
    Thai	(th)
    Turkish	(tr)
    Vietnamese	(vi)

  • Support for new currency codes:

    Currency	Locale	Code
    BAM	Bosnian Convertible Mark	(ba)
    BGN	Bulgarian Lev	(bg)
    ILS	Israeli New Shekel	(il)
    MKD	Macedonian Denar	(mk)
    RUB	Russian Ruble	(ru)
    THB	Thai Baht	(th)
    TRY	Turkish Lira	(tr)
    UAH	Ukrainian Hryvnia	(ua)
    VND	Vietnamese Dong	(vn)

  • Tax items support expansion for Germany (de), Spain (es), Portugal (pt), English Canada en-CA.
• ID model
  • Expanded field support for European Union identification cards and driver licenses.
• Mortgage documents
  • Extract information from Uniform Residential Loan Application (Form 1003).
  • Extract information from Uniform Underwriting and Transmittal Summary or Form 1008.
  • Extract information from mortgage closing disclosure.
• Credit/Debit card model
  • Extract information from bank cards.
• Marriage certificate
  • New prebuilt to extract information from marriage certificates.

December 2023

The Document Intelligence client libraries targeting REST API 2023-10-31-preview are now available for use!

November 2023

The Document Intelligence 2023-10-31-preview REST API is now available. This preview API introduces new and updated capabilities:

• Public preview version 2023-10-31-preview is currently only available in the following Azure regions:
  • East US
  • West US2
  • West Europe
• Read model
  • Language Expansion for Handwriting: Russian(ru), Arabic(ar), Thai(th).
  • Cyber Executive Order (EO) compliance.
• Layout model
  • Support office and HTML files.
  • Markdown output support.
  • Table extraction, reading order, and section heading detection improvements.
  • With the Document Intelligence 2023-10-31-preview, the general document model (prebuilt-document) is deprecated. Going forward, to extract key-value pairs from documents, use theprebuilt-layout model with the optional query string parameter features=keyValuePairs enabled.
• Receipt model
  • Now extracts currency for all price-related fields.
• Health Insurance Card model
  • New field support for Medicare and Medicaid information.
• US Tax Document models
  • New 1099 tax model. Supports base 1099 form and the following variations: A, B, C, CAP, DIV, G, H, INT, K, LS, LTC, MISC, NEC, OID, PATR, Q, QA, R, S, SA, SB​.
• Invoice model
  • Support for KVK field.
  • Support for BPAY field.
  • Numerous field refinements.
• Custom Classification
  • Support for multi-language documents.
  • New page splitting options: autosplit, always split by page, no split.
• Add-on capabilities
  • Query fields are available with the 2023-10-31-preview release.
  • Add-on capabilities are available within all models excluding the Read model.

Note

With the 2022-08-31 API general availability (GA) release, the associated preview APIs are being deprecated. If you're using the 2021-09-30-preview, 2022-01-30-preview, or 2022-06-30-preview API versions, update your applications to target the 2022-08-31 API version. There are a few minor changes involved, for more information, see the migration guide.