You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/whats-new.md
+22-18Lines changed: 22 additions & 18 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -25,44 +25,48 @@ ms.custom:
25
25
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.
26
26
27
27
> [!IMPORTANT]
28
-
> Preview API versions are retired once the GA API is released. The 2023-02-28-preview API version is being retired, if you are still using the preview API or the associated SDK versions, please update your code to target the latest API version 2023-07-31 (GA).
28
+
> Preview API versions are retired once the GA API is released. The 2023-02-28-preview API version is being retired, if you are still using the preview API or the associated SDK versions, please update your code to target the latest API version 2023-07-31 (GA). </br>
29
+
> Please note that [🆕 Document field extraction (custom generative) model](train/custom-generative-extraction.md) is under preview with improvements for runtime latency, table extraction, confidence scores, auto labeling and streamline training.
29
30
30
-
## November 2024
31
31
32
-
**Document Intelligence v4.0 (2024-11-30) is now generally available (GA)**!
32
+
## November 2024
33
33
34
-
*[🆕 Document field extraction (custom generative) model](train/custom-generative-extraction.md)
35
-
***Generative AI** model is available in preview with improvements for runtime latency, table extraction, confidence scores, auto labeling and streamline training.
34
+
**Document Intelligence v4.0 (2024-11-30) is now generally available (GA)**! The API version corresponds to 2024-11-30. The v4.0 API includes cumulative updates from preview releases as listed:
35
+
* August 2024 (release-ignite-document-intelligence-v4&tabs=csharp#august-2024)
36
+
* May 2024
37
+
* Feb 2024 (link to older release notes)
36
38
37
-
*[🆕 US Tax model](prebuilt/tax-document.md)
38
-
* New tax models added for 1095A, 1095C, 1099SSA, and W4.
39
-
* 🆕 Searchable PDF. The [prebuilt read](prebuilt/read.md) model now supports images formats (JPEG/JPG, PNG, BMP, TIFF, HEIF) and language expansion to include Chinese, Japanese, and Korean for [PDF output](prebuilt/read.md#searchable-pdf).
40
39
41
40
*[🆕 Batch API](concept-batch-analysis.md)
42
41
* Batch API now supports all the prebuilt models.
43
42
* Batch API supports LIST function to allow users to list batch jobs within past seven days.
44
43
* Batch API supports DELETE function to explicitly delete batch job for GDPR and privacy compliance.
45
-
* GetAnalyzeBatchResult supports resultId in response to LIST all resultIds.
46
-
47
-
*[Custom Neural Model](train/custom-neural.md)
48
-
* Custom Neural model now supports signature detection.
49
-
44
+
* GetAnalyzeBatchResult supports resultId in response to LIST all resultIds.
45
+
46
+
* 🆕 Searchable PDF. The [prebuilt read](prebuilt/read.md) model now supports images formats (JPEG/JPG, PNG, BMP, TIFF, HEIF) and language expansion to include Chinese, Japanese, and Korean for [PDF output](prebuilt/read.md#searchable-pdf).
* Custom classification model supports incremental training. You can add new samples to exisisting classes or add new classes by referencing an existing classifier.
52
50
* 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.
53
51
* Custom classification model now supports 25,000 pages as new training page limit.
0 commit comments