Skip to content

Content Understanding 2025-11-01 GA #38821

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 9 commits into from
Nov 20, 2025
Merged

Content Understanding 2025-11-01 GA #38821

merged 9 commits into from
Nov 20, 2025

Conversation

@bojunehsu
Copy link
Member

@bojunehsu bojunehsu commented Nov 15, 2025 •
edited
Loading

Data Plane API Specification Update Pull Request

Content Understanding 2025-11-01 GA

API Info: The Basics

Is this review for (select one):

  • a private preview
  • a public preview
  • GA release

Change Scope

Breaking Changes from 2025-05-01-preview

  • Bring your own LLM capacity
    • No longer support managed capacity
  • Refined analyze result file access
  • New integrated segmentation design in analyzers
    • Replaces dedicated content classifiers
    • Replaces dedicated video segmentation design
  • Split :analyze and :analyzeBinary operations
  • Replace analyzer.{url,data} with analyzer.inputs
  • Merged analyzer trainingData into knowledgeSources

New Features

  • Field extraction
    • Field generation method is now optional
      • When not specified, service will automatically determine whether to extract or generate field value.
    • Generated fields now support grounding source and confidence
    • Allow grounding source and confidence to be configured per field
    • Increased field limit to 1000 fields
    • Relaxed field schema constraints
  • New prebuilt analyzers
    • prebuilt-{layout,read}
    • prebuilt-documentFieldSchema
    • prebuilt-documentFields
    • Prebuilt document analyzers for tax, procurement, ... industries
  • Document content analysis
    • Figure analysis (description, mermaid, chart.js, table)
    • Content annotations (underline, strikethrough, circle, ...)
    • Hyperlink extraction
    • Output table format selection
  • Analyzer copy
  • Allow new analyzers to replace existing analyzerId
  • Analyze partial content with input range
  • Delete temporary analyzer results
  • Customer managed keys, VNET, managed identity, private endpoint

Deprecated Features

  • Person directory, face APIs
  • Face integration with video analyzers
  • Pro mode
  • Dedicated content classifiers
  • Dedicated video segmentation design

Resources

@github-actions
Copy link

github-actions bot commented Nov 15, 2025 •
edited
Loading

Next Steps to Merge

✅ All automated merging requirements have been met! To get your PR merged, see aka.ms/azsdk/specreview/merge.

Comment generated by summarize-checks workflow run.

@github-actions github-actions bot added data-plane TypeSpec Authored with TypeSpec VersioningReviewRequired <valid label in PR review process>add this label when versioning review is required labels Nov 15, 2025
@github-actions
Copy link

github-actions bot commented Nov 15, 2025 •
edited
Loading

API Change Check

APIView identified API level changes in this PR and created the following API reviews

Language API Review for Package
TypeSpec ContentUnderstanding
Java com.azure:azure-ai-contentunderstanding

yungshinlintw and others added 4 commits November 18, 2025 15:13
@yungshinlintw
Migrate the client SDK changes from azure-rest-api-specs-pr (#38839)
063335d 
* MIGRATE SDK changes from azure-rest-api-specs-pr:

- Updated ContentUnderstandingClient interface to flatten operations and enhance naming conventions.
- Renamed ContentAnalyzer's status field to ResourceStatus for better clarity.
- Introduced StringEncoding union for encoding formats in AnalyzeParameters.
- Adjusted tspconfig.yaml to enable Java support and ensure proper emission of client libraries.

* PYTHON-SDK-FEEDBACK:
Add fieldType and inputRange renaming for clarity in ContentUnderstandingClient

* SDK-PYTHON: Hide string_encoding parameter in Python SDK and clarify string indexing behavior

* Move operation renames into interface definition

* PR Comments:
- Comment out emitters in emit to avoid dependency in this repo
- Move internal def of getRestul and getOperationStatus to client.tsp
- Merge operation rename in interface
- rename createAnalyzer

* Fix incorrect name in listAnalyzers renaming for .NET

* Fix typo in deleteAnalyzer method name in ContentUnderstandingClient interface
@bojunehsu
Remove preview versions. Add examples.
f1974c4
@bojunehsu
Fix PR checks
6faf668
@bojunehsu
Merge branch 'main' into paulhsu/ContentUnderstanding-2025-11-01
4f7837c
@bojunehsu bojunehsu requested a review from Copilot November 19, 2025 06:28
@bojunehsu bojunehsu marked this pull request as ready for review November 19, 2025 06:28
Copilot finished reviewing on behalf of bojunehsu November 19, 2025 06:30
Copilot AI reviewed Nov 19, 2025
View reviewed changes
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This pull request promotes the Content Understanding API from preview to general availability (GA) with version 2025-11-01. The changes introduce significant breaking changes and new features as part of the service evolution.

Key changes include:

  • Removal of deprecated features (person directory, face APIs, dedicated content classifiers)
  • New analyzer copy functionality with authorization
  • Integrated segmentation design replacing dedicated classifiers
  • Field extraction enhancements with optional generation methods
  • New defaults endpoint for model deployment configuration

Reviewed Changes

Copilot reviewed 73 out of 74 changed files in this pull request and generated 1 comment.

Show a summary per file
File Description
stable/2025-11-01/ContentUnderstanding.json Main OpenAPI specification for GA version with new endpoints and models
stable/2025-11-01/examples/*.json Example files updated with new API version and structure
main.tsp Updated service version from preview to GA
models.tsp Major model changes including new knowledge sources, field types, and usage tracking
routes.tsp New routes for copy operations and defaults management
documentContent.tsp Enhanced with annotations, hyperlinks, and segmentation support
audioVisualContent.tsp Updated segmentation model for audio/visual content
client.tsp Client customizations for SDK generation
tspconfig.yaml Configuration updates for multiple language emitters
readme.md Documentation updated to reference GA version
personDirectoryRoutes.tsp Commented out (deprecated features)
classifierRoutes.tsp Removed (deprecated features)

Copilot AI mentioned this pull request Nov 19, 2025
Merged
3 tasks
Copy link
Contributor

Copilot AI commented Nov 19, 2025

@bojunehsu I've opened a new pull request, #38877, to work on those changes. Once the pull request is ready, I'll request review from you.

@bojunehsu
Fix example title in ContentAnalyzers_DeleteResult.json (#38877)
b8cd664 
* Initial plan

* Fix example title: Change "Delete Analyzer" to "Delete Analysis Result"

Co-authored-by: bojunehsu <1988517+bojunehsu@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: bojunehsu <1988517+bojunehsu@users.noreply.github.com>
@mikekistler mikekistler added the Versioning-Approved-Retired https://github.com/Azure/azure-rest-api-specs/issues/30652 label Nov 19, 2025
mikekistler
mikekistler approved these changes Nov 20, 2025
View reviewed changes
Copy link
Member

@mikekistler mikekistler left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks good to me. 👍

I noted a few minor improvements that I hope you consider, but none are serious and I think all could be fixed in the next version.

@bojunehsu bojunehsu enabled auto-merge (squash) November 20, 2025 19:49
mikekistler
mikekistler approved these changes Nov 20, 2025
View reviewed changes
Copy link
Member

@mikekistler mikekistler left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the fixes!

@bojunehsu bojunehsu added the PublishToCustomers Acknowledgement the changes will be published to Azure customers. label Nov 20, 2025
@bojunehsu bojunehsu merged commit 5e429f4 into main Nov 20, 2025
47 of 49 checks passed
@bojunehsu bojunehsu deleted the paulhsu/ContentUnderstanding-2025-11-01 branch November 20, 2025 22:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Copilot code review Copilot Copilot left review comments

@mikekistler mikekistler mikekistler approved these changes

@yungshinlintw yungshinlintw Awaiting requested review from yungshinlintw

@johanste johanste Awaiting requested review from johanste

@weidongxu-microsoft weidongxu-microsoft Awaiting requested review from weidongxu-microsoft

Assignees

No one assigned

Labels

data-plane PublishToCustomers Acknowledgement the changes will be published to Azure customers. TypeSpec Authored with TypeSpec Versioning-Approved-Retired https://github.com/Azure/azure-rest-api-specs/issues/30652 VersioningReviewRequired <valid label in PR review process>add this label when versioning review is required

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@bojunehsu @mikekistler @yungshinlintw