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/build-a-custom-model.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
@@ -49,7 +49,7 @@ Once you gather a set of forms or documents for training, you need to upload it
49
49
50
50
The Document Intelligence Studio provides and orchestrates all the API calls required to complete your dataset and train your model.
51
51
52
-
1. Start by navigating to the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio). The first time you use the Studio, you need to [initialize your subscription, resource group, and resource](../studio-overview.md). Then, follow the [prerequisites for custom projects](../quickstarts/studio-custom-project.md#prerequisites-for-custom-projects) to configure the Studio to access your training dataset.
52
+
1. Start by navigating to the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio). The first time you use the Studio, you need to [initialize your subscription, resource group, and resource](../studio-overview.md). Then, follow the [prerequisites for custom projects](../quickstarts/studio-custom-project.md#prerequisites) to configure the Studio to access your training dataset.
53
53
54
54
1. In the Studio, select the **Custom extraction model** tile and select the **Create a project** button.
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/how-to-guides/create-document-intelligence-resource.md
+26-29Lines changed: 26 additions & 29 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,5 @@
1
1
---
2
-
title: Create a Document Intelligence resource
2
+
title: Create a Document Intelligence Resource
3
3
titleSuffix: Azure AI services
4
4
description: Create a Document Intelligence resource in the Azure portal.
5
5
author: laujan
@@ -17,59 +17,56 @@ ms.author: lajanuar
17
17
[!INCLUDE [applies to v4.0 v3.1 v3.0 v2.1](../includes/applies-to-v40-v31-v30-v21.md)]
18
18
::: moniker-end
19
19
20
-
Azure AI Document Intelligence is a cloud-based [Azure AI service](../../../ai-services/index.yml) that uses machine-learning models to extract key-value pairs, text, and tables from your documents. In this article, learn how to create a Document Intelligence resource in the Azure portal.
20
+
Azure AI Document Intelligence is a cloud-based [Azure AI service](../../../ai-services/index.yml) that uses machine-learning models to extract key/value pairs, text, and tables from your documents. In this article, learn how to create a Document Intelligence resource in the Azure portal.
21
21
22
22
## Visit the Azure portal
23
23
24
-
The Azure portal is a single platform you can use to create and manage Azure services.
24
+
The Azure portal is a single platform that you can use to create and manage Azure services.
25
25
26
-
Let's get started:
26
+
To get started:
27
27
28
28
1. Sign in to the [Azure portal](https://portal.azure.com).
29
29
30
-
1.Select **Create a resource** from the Azure home page.
30
+
1.On the Azure home page, select **Create a resource**.
31
31
32
-
1.Search for and choose **Document Intelligence** from the search bar.
32
+
1.In the search bar, search for and choose **Document Intelligence**.
33
33
34
-
1. Select the **Create** button.
34
+
1. Select **Create**.
35
35
36
36
## Create a resource
37
37
38
-
1.Next, you're going to fill out the **`Create Document Intelligence`** fields with the following values:
38
+
1.Fill out the **Create Form Recognizer** fields with the following values:
39
39
40
-
***Subscription**. Select your current subscription.
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
-
***Region**. Select your local region.
43
-
***Name**. Enter a name for your resource. We recommend using a descriptive name, for example *YourNameDocumentIntelligence*.
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.
40
+
***Subscription**: Select your current subscription.
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
+
***Region**: Select your local region.
43
+
***Name**: Enter a name for your resource. We recommend that you use a descriptive name, for example,*YourNameDocumentIntelligence*.
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. You can upgrade later to a paid tier for production.
45
45
46
-
1. Select **Review + Create**.
46
+
1. Select **Review + create**.
47
47
48
-
:::image type="content" source="../media/logic-apps-tutorial/logic-app-connector-demo-two.png" alt-text="Still image showing the correct values for creating Document Intelligence resource.":::
48
+
:::image type="content" source="../media/logic-apps-tutorial/logic-app-connector-demo-two.png" alt-text="Screenshot that shows the correct values for creating a Document Intelligence resource.":::
49
49
50
-
1. Azure will run a quick validation check, after a few seconds you should see a green banner that says **Validation Passed**.
50
+
1. Azure runs a quick validation check. After a few seconds, a green banner appears that says **Validation Passed**.
51
51
52
-
1.Once the validation banner appears, select the **Create** button from the bottom-left corner.
52
+
1.After the validation banner appears, select **Create**.
53
53
54
-
1.After you select create, you'll be redirected to a new page that says **Deployment in progress**. After a few seconds, you'll see a message that says,**Your deployment is complete**.
54
+
1.A new page opens that says **Deployment in progress**. After a few seconds, a message appears that says **Your deployment is complete**.
55
55
56
-
## Get Endpoint URL and keys
56
+
## Get endpoint URL and keys
57
57
58
-
1.Once you receive the *deployment is complete*message, select the **Go to resource** button.
58
+
1.After you receive the message, select **Go to resource**.
59
59
60
-
1. Copy the key and endpoint values from your Document Intelligence resource paste them in a convenient location, such as *Microsoft Notepad*. You need the key and endpoint values to connect your application to the Document Intelligence API.
60
+
1. Copy the key and endpoint values from your Document Intelligence resource. Paste the values in a convenient location, such as Notepad. You need the key and endpoint values to connect your application to the Document Intelligence API.
61
61
62
-
1. If your overview page doesn't have the keys and endpoint visible, you can select the **Keys and Endpoint** button, on the left pane, and retrieve them there.
62
+
1. If your overview page doesn't show the keys and endpoint, select **Keys and Endpoint** on the left pane, and retrieve them there.
63
63
64
-
:::image border="true" type="content" source="../media/containers/keys-and-endpoint.png" alt-text="Still photo showing how to access resource key and endpoint URL.":::
64
+
:::image border="true" type="content" source="../media/containers/keys-and-endpoint.png" alt-text="Screenshot that shows how to access the resource key and endpoint URL.":::
65
65
66
-
That's it! You're now ready to start automating data extraction using Azure AI Document Intelligence.
66
+
## Related content
67
67
68
-
## Next steps
69
-
70
-
* Try the [Document Intelligence Studio](../concept-document-intelligence-studio.md), an online tool for visually exploring, understanding, and integrating features from the Document Intelligence service into your applications.
71
-
72
-
* Complete a Document Intelligence quickstart and get started creating a document processing app in the development language of your choice:
68
+
* Try [Document Intelligence Studio](../concept-document-intelligence-studio.md), an online tool that helps you visually explore, understand, and integrate features from Document Intelligence into your applications.
69
+
* Finish a Document Intelligence quickstart and then create a document processing app in the development language of your choice:
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/includes/input-requirements.md
+13-22Lines changed: 13 additions & 22 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,33 +7,24 @@ ms.author: lajanuar
7
7
---
8
8
<!-- markdownlint-disable MD041 -->
9
9
10
-
Supported file formats:
10
+
The following file formats are supported.
11
11
12
-
|Model | PDF |Image: </br>`JPEG/JPG`, `PNG`, `BMP`, `TIFF`, `HEIF`|Microsoft Office: </br> Word (`DOCX`), Excel (`XLSX`), PowerPoint (`PPTX`), HTML|
12
+
|Model | PDF |Image: </br>JPEG/JPG, PNG, BMP, TIFF, HEIF | Office: </br> Word (DOCX), Excel (XLSX), PowerPoint (PPTX), HTML|
13
13
|--------|:----:|:-----:|:---------------:|
14
14
|Read | ✔ | ✔ | ✔ |
15
15
|Layout | ✔ | ✔ | ✔ |
16
-
|General Document| ✔ | ✔ ||
16
+
|General document| ✔ | ✔ ||
17
17
|Prebuilt | ✔ | ✔ ||
18
18
|Custom extraction | ✔ | ✔ ||
19
19
|Custom classification | ✔ | ✔ | ✔ |
20
20
21
-
* For best results, provide one clear photo or high-quality scan per document.
22
-
23
-
* For PDF and TIFF, up to 2,000 pages can be processed (with a free tier subscription, only the first two pages are processed).
24
-
25
-
* The file size for analyzing documents is 500 MB for paid (S0) tier and `4` MB for free (F0) tier.
26
-
27
-
* Image dimensions must be between 50 pixels x 50 pixels and 10,000 pixels x 10,000 pixels.
28
-
29
-
* If your PDFs are password-locked, you must remove the lock before submission.
30
-
31
-
* 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).
32
-
33
-
* 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.
34
-
35
-
* For custom extraction model training, the total size of training data is 50 MB for template model and `1` GB for the neural model.
36
-
37
-
* 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.
38
-
39
-
* For office file types (docx, xlsx, pptx), there's a maximum string length limit of 8,000,000 characters.
21
+
***Photos and scans**: For best results, provide one clear photo or high-quality scan per document.
22
+
***PDFs and TIFFs**: For PDFs and TIFFs, up to 2,000 pages can be processed. (With a free-tier subscription, only the first two pages are processed.)
23
+
***File size**: The file size for analyzing documents is 500 MB for the paid (S0) tier and 4 MB for the free (F0) tier.
24
+
***Image dimensions**: The dimensions must be between 50 pixels x 50 pixels and 10,000 pixels x 10,000 pixels.
25
+
***Password locks**: If your PDFs are password-locked, you must remove the lock before submission.
26
+
***Text height**: 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.
27
+
***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.
28
+
***Custom extraction model training**: The total size of training data is 50 MB for template model and 1 GB for the neural model.
29
+
***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.
30
+
***Office file types (DOCX, XLSX, PPTX)**: The maximum string length limit is 8 million characters.
0 commit comments