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/how-to-guides/create-document-intelligence-resource.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -40,7 +40,7 @@ Let's get started:
40
40
***Subscription**. Select your current subscription.
41
41
***Resource group**. The [Azure resource group](/azure/cloud-adoption-framework/govern/resource-consistency/resource-access-management#what-is-an-azure-resource-group) that contains your resource. You can create a new group or add it to an existing group.
42
42
***Region**. Select your local region.
43
-
***Name**. Enter a name for your resource. We recommend using a descriptive name, for example *YourNameFormRecognizer*.
43
+
***Name**. Enter a name for your resource. We recommend using a descriptive name, for example *YourNameDocumentIntelligence*.
44
44
***Pricing tier**. The cost of your resource depends on the pricing tier you choose and your usage. For more information, see [pricing details](https://azure.microsoft.com/pricing/details/cognitive-services/). You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/model-overview.md
+10-10Lines changed: 10 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-document-intelligence
8
8
ms.topic: conceptual
9
-
ms.date: 11/19/2024
9
+
ms.date: 03/14/2025
10
10
ms.author: lajanuar
11
11
---
12
12
@@ -36,7 +36,7 @@ ms.author: lajanuar
36
36
::: moniker-end
37
37
38
38
::: moniker range=">=doc-intel-2.1.0"
39
-
Azure AI Document Intelligence supports a wide variety of models that enable you to add intelligent document processing to your apps and flows. You can use a prebuilt domain-specific model or train a custom model tailored to your specific business need and use cases. Document Intelligence can be used with the REST API or Python, C#, Java, and JavaScript client libraries.
39
+
Azure AI Document Intelligence supports a wide variety of models that enable you to add intelligent document processing to your apps and flows. You can use a prebuilt domain-specific model or train a custom model tailored to your specific business needs and use cases. Document Intelligence can be used with the REST API or Python, C#, Java, and JavaScript client libraries.
40
40
::: moniker-end
41
41
42
42
> [!NOTE]
@@ -48,11 +48,11 @@ ms.author: lajanuar
48
48
49
49
The following table shows the available models for each stable API:
\*- Contains submodels. See the model specific information for supported variations and subtypes.</br>
86
-
\**- All the capabilites of General Document model are available in layout model. General model is no longer supported.
85
+
\* Contains submodels. See the model specific information for supported variations and subtypes.</br>
86
+
\** All the General Document model capabilities are available in layout model. General model is no longer supported.
87
87
88
88
### Latency
89
89
@@ -252,7 +252,7 @@ The US mortgage document models analyze and extract key fields including borrowe
252
252
253
253
The contract model analyzes and extracts key fields from check including check details, account details, amount, memo, is extracted from US bank checks.
254
254
255
-
***Sample bank check processed using [Document Intelligence Studio](https://documentintelligence.ai.azure.com/studio/prebuilt?formCategory=check.us)***:
255
+
***A bank check sample processed using [Document Intelligence Studio](https://documentintelligence.ai.azure.com/studio/prebuilt?formCategory=check.us)***:
256
256
257
257
:::image type="content" source="media/studio/analyze-bank-check.png" alt-text="Screenshot of bank check model extraction using Document Intelligence Studio.":::
258
258
@@ -263,7 +263,7 @@ The US mortgage document models analyze and extract key fields including borrowe
The bank statement model analyzes and extracts key fields and line items from US bank statements account number, bank details, statement details and transaction details.
266
+
The bank statement model analyzes and extracts key fields and line items from US bank statements account number, bank details, statement details, and transaction details.
267
267
268
268
***Sample bank statement processed using [Document Intelligence Studio](https://documentintelligence.ai.azure.com/studio/prebuilt?formCategory=bankStatement.us)***:
269
269
@@ -410,7 +410,7 @@ A composed model is created by taking a collection of custom models and assignin
> The [Sample Labeling tool](https://fott-2-1.azurewebsites.net/)does not support the BMP file format. This is a limitation of the tool not the Document Intelligence Service.
413
+
> The [Sample Labeling tool](https://fott-2-1.azurewebsites.net/)doesn't support the BMP file format. The limitation is derived from the tool not the Document Intelligence Service.
414
414
415
415
### Version migration
416
416
@@ -531,7 +531,7 @@ A composed model is created by taking a collection of custom models and assignin
> The [Sample Labeling tool](https://fott-2-1.azurewebsites.net/)does not support the BMP file format. This is a limitation of the tool not the Document Intelligence Service.
534
+
> The [Sample Labeling tool](https://fott-2-1.azurewebsites.net/)doesn't support the BMP file format. The limitation is derived from the tool not the Document Intelligence Service.
@@ -220,9 +220,9 @@ The new machine-learning based page object detection extracts logical roles like
220
220
221
221
### Text, lines, and words
222
222
223
-
The document layout model in Document Intelligence extracts print and handwritten style text as `lines` and `words`. The `styles` collection ../includes any handwritten style for lines if detected along with the spans pointing to the associated text. This feature applies to [supported handwritten languages](../language-support/prebuilt.md).
223
+
The document layout model in Document Intelligence extracts print and handwritten style text as `lines` and `words`. The `styles` collection includes any handwritten style for lines if detected along with the spans pointing to the associated text. This feature applies to [supported handwritten languages](../language-support/prebuilt.md).
224
224
225
-
For Microsoft Word, Excel, PowerPoint, and HTML, Document Intelligence v4.0 2024-11-30 (GA) Layout model extract all embedded text as is. Texts are extracted as words and paragraphs. Embedded images aren't supported.
225
+
For Microsoft Word, Excel, PowerPoint, and HTML, Document Intelligence v4.0 `2024-11-30` (GA) Layout model extract all embedded text as is. Texts are extracted as words and paragraphs. Embedded images aren't supported.
226
226
227
227
#### [Sample code](#tab/sample-code)
228
228
@@ -343,8 +343,8 @@ Here are a few factors to consider when using the Document Intelligence bale ext
343
343
344
344
> [!NOTE]
345
345
>
346
-
> * Table analysis is not supported if the input file is XLSX.
347
-
> * For *2024-11-30 (GA)*, the bounding regions for figures and tables cover only the core content and exclude associated caption and footnotes.
346
+
> * Table analysis isn't supported if the input file is XLSX.
347
+
> * For `2024-11-30` (GA), the bounding regions for figures and tables cover only the core content and exclude associated caption and footnotes.
348
348
349
349
#### [Sample code](#tab/sample-code)
350
350
@@ -399,7 +399,8 @@ if result.tables:
399
399
The Layout API can output the extracted text in markdown format. Use the `outputContentFormat=markdown` to specify the output format in markdown. The markdown content is output as part of the `content` section.
400
400
401
401
> [!NOTE]
402
-
> For v4.0 *2024-11-30 (GA)*, the representation of tables is changed to HTML tables to enable rendering of merged cells, multi-row headers, etc. Another related change is to use Unicode checkbox characters ☒ and ☐ for selection marks instead of :selected: and :unselected:. Note that this means that the content of selection mark fields will contain :selected: even though their spans refer to Unicode characters in the top-level span.
402
+
>
403
+
> For v4.0 `2024-11-30` (GA), the representation of tables is changed to HTML tables to enable rendering of merged cells, multi-row headers, etc. Another related change is to use Unicode checkbox characters ☒ and ☐ for selection marks instead of `:selected:` and `:unselected:`. This update means that the content of selection mark fields contains `:selected:` even though their spans refer to Unicode characters in the top-level span.
403
404
404
405
#### [Sample code](#tab/sample-code)
405
406
@@ -472,7 +473,7 @@ When *output=figures* is specified during the initial analyze operation, the ser
472
473
`FigureId` is included in each figure object, following an undocumented convention of `{pageNumber}.{figureIndex}` where `figureIndex` resets to one per page.
473
474
474
475
> [!NOTE]
475
-
> For v4.0 *2024-11-30 (GA)*, the bounding regions for figures and tables cover only the core content and exclude associated caption and footnotes.
476
+
> For v4.0 `2024-11-30` (GA), the bounding regions for figures and tables cover only the core content and exclude associated caption and footnotes.
476
477
477
478
#### [Sample code](#tab/sample-code)
478
479
@@ -637,7 +638,7 @@ Supported file formats:
637
638
638
639
* For custom extraction model training, the total size of training data is 50 MB for template model and `1` GB for the neural model.
639
640
640
-
* For custom classification model training, the total size of training data is `1` GB with a maximum of 10,000 pages. For 2024-11-30 (GA), the total size of training data is `2` GB with a maximum of 10,000 pages.
641
+
* For custom classification model training, the total size of training data is `1` GB with a maximum of 10,000 pages. For `2024-11-30` (GA), the total size of training data is `2` GB with a maximum of 10,000 pages.
641
642
642
643
:::moniker-end
643
644
@@ -688,7 +689,7 @@ After you retrieve you key and endpoint, you can use the following development o
@@ -901,7 +902,7 @@ The new machine-learning based page object detection extracts logical roles like
901
902
902
903
The document layout model in Document Intelligence extracts print and handwritten style text as `lines` and `words`. The `styles` collection ../includes any handwritten style for lines if detected along with the spans pointing to the associated text. This feature applies to [supported handwritten languages](../language-support/prebuilt.md).
903
904
904
-
For Microsoft Word, Excel, PowerPoint, and HTML, Document Intelligence v4.0 2024-11-30 (GA) Layout model extract all embedded text as is. Texts are extracted as words and paragraphs. Embedded images aren't supported.
905
+
For Microsoft Word, Excel, PowerPoint, and HTML, Document Intelligence v4.0 `2024-11-30` (GA) Layout model extract all embedded text as is. Texts are extracted as words and paragraphs. Embedded images aren't supported.
905
906
906
907
:::moniker-end
907
908
@@ -1078,8 +1079,8 @@ Here are a few factors to consider when using the Document Intelligence bale ext
1078
1079
1079
1080
> [!NOTE]
1080
1081
>
1081
-
> * Table analysis is not supported if the input file is XLSX.
1082
-
> * Document Intelligence v4.0 2024-11-30 (GA) supports bounding regions for figures and tables that cover only the core content and exclude associated caption and footnotes.
1082
+
> * Table analysis isn't supported if the input file is XLSX.
1083
+
> * Document Intelligence v4.0 `2024-11-30` (GA) supports bounding regions for figures and tables that cover only the core content and exclude associated caption and footnotes.
0 commit comments