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
* To compose a model trained with a prior version of the API (v2.1 or earlier), train a model with the v3.0 API using the same labeled dataset. That addition ensures that the v2.1 model can be composed with other models.
71
70
72
-
*Models composed with v2.1 of the API continues to be supported, requiring no updates.
71
+
*With models composed using v2.1 of the API continues to be supported, requiring no updates.
73
72
74
-
*The limit for maximum number of custom models that can be composed is 100.
73
+
*For custom models, the maximum number that can be composed is 100.
@@ -70,19 +70,19 @@ Document Intelligence v3.0 supports the following tools, applications, and libra
70
70
71
71
See how data, including customer information, vendor details, and line items, is extracted from contracts. You need the following resources:
72
72
73
-
* An Azure subscription—you can [create one for free](https://azure.microsoft.com/free/cognitive-services/)
73
+
* An Azure subscription—you can [create one for free](https://azure.microsoft.com/free/cognitive-services/).
74
74
75
75
* A [Document Intelligence instance](https://portal.azure.com/#create/Microsoft.CognitiveServicesFormRecognizer) in the Azure portal. You can use the free pricing tier (`F0`) to try the service. After your resource deploys, select **Go to resource** to get your key and endpoint.
76
76
77
77
:::image type="content" source="media/containers/keys-and-endpoint.png" alt-text="Screenshot of keys and endpoint location in the Azure portal.":::
78
78
79
79
## Document Intelligence Studio
80
80
81
-
1. On the Document Intelligence Studio home page, select **Tax Documents**
81
+
1. On the Document Intelligence Studio home page, select **Tax Documents**.
82
82
83
83
1. You can analyze the sample tax documents or upload your own files.
84
84
85
-
1. Select the **Run analysis** button and, if necessary, configure the **Analyze options**:
85
+
1. Select the **Run analysis** button and, if necessary, configure the **Analyze options**:
86
86
87
87
:::image type="content" source="media/studio/run-analysis-analyze-options.png" alt-text="Screenshot of Run analysis and Analyze options buttons in the Document Intelligence Studio.":::
88
88
@@ -111,6 +111,6 @@ The contract key-value pairs and line items extracted are in the `documentResult
111
111
112
112
## Next steps
113
113
114
-
* Try processing your own forms and documents with the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio)
114
+
* Try processing your own forms and documents with the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio).
115
115
116
116
* Complete a [Document Intelligence quickstart](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true) and get started creating a document processing app in the development language of your choice.
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/concept-custom-lifecycle.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
@@ -26,7 +26,7 @@ With the v3.1 (GA) and later APIs, custom models introduce a expirationDateTime
26
26
27
27
With the v3.1 API, custom models introduce a new model expiration property. The model expiration is set to two years from the date the model is built for all requests that use a GA API to build a model. To continue to use the model past the expiration date, you need to train the model with a current GA API version. The API version can be the one that the model was originally trained with or a later API version. The following figure illustrates the options when you need to retrain an expiring or expired model.
28
28
29
-
[](media/model-lifecycle.png)
29
+
:::image type="content" source="media/model-lifecycle.png" alt-text="Screenshot showing how to chose an API version to re-train a model.":::
With the v3.0 and later APIs, the build operation to train model supports a new ```buildMode``` property, to train a custom template model, set the ```buildMode``` to ```template```.
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/concept-general-document.md
+11-11Lines changed: 11 additions & 11 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,14 +1,14 @@
1
1
---
2
2
title: General key-value extraction - Document Intelligence (formerly Form Recognizer)
3
3
titleSuffix: Azure AI services
4
-
description: Extract key-value pairs, tables, selection marks, and text from your documents with Document Intelligence
4
+
description: Extract key-value pairs, tables, selection marks, and text from your documents with Document Intelligence.
5
5
author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-document-intelligence
8
8
ms.custom:
9
9
- ignite-2023
10
10
ms.topic: conceptual
11
-
ms.date: 11/21/2023
11
+
ms.date: 03/06/2024
12
12
ms.author: lajanuar
13
13
---
14
14
@@ -19,7 +19,7 @@ ms.author: lajanuar
19
19
:::moniker range="doc-intel-4.0.0"
20
20
21
21
> [!IMPORTANT]
22
-
> Starting with Document Intelligence **2024-02-29-preview, 2023-10-31-preview** and going forward, the general document model (prebuilt-document) is deprecated. To extract key-value pairs, selection marks, text, tables, and structure from documents, use the following models:
22
+
> Starting with `Document Intelligence versions**2024-02-29-preview, 2023-10-31-preview** and going forward, the general document model (prebuilt-document) is deprecated. To extract key-value pairs, selection marks, text, tables, and structure from documents, use the following models:
The General document model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to extract key-value pairs, tables, and selection marks from documents. General document is available with the v3.1 and v3.0 APIs. For more information, _see_ our [migration guide](v3-1-migration-guide.md).
38
+
The General document model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to extract key-value pairs, tables, and selection marks from documents. General document is available with the v3.1 and v3.0 APIs. For more information, _see_ our [migration guide](v3-1-migration-guide.md).
@@ -47,7 +47,7 @@ The General document model combines powerful Optical Character Recognition (OCR)
47
47
48
48
* The general document model supports structured, semi-structured, and unstructured documents.
49
49
50
-
* Selection marks are identified as fields with a value of ```:selected:``` or ```:unselected:```
50
+
* Selection marks are identified as fields with a value of `:selected:` or `:unselected:`.
51
51
52
52
***Sample document processed in the Document Intelligence Studio***
53
53
@@ -91,7 +91,7 @@ Try extracting data from forms and documents using the Document Intelligence Stu
91
91
92
92
You need the following resources:
93
93
94
-
* An Azure subscription—you can [create one for free](https://azure.microsoft.com/free/cognitive-services/)
94
+
* An Azure subscription—you can [create one for free](https://azure.microsoft.com/free/cognitive-services/).
95
95
96
96
* A [Document Intelligence instance](https://portal.azure.com/#create/Microsoft.CognitiveServicesFormRecognizer) in the Azure portal. You can use the free pricing tier (`F0`) to try the service. After your resource deploys, select **Go to resource** to get your key and endpoint.
97
97
@@ -100,20 +100,20 @@ You need the following resources:
100
100
> [!NOTE]
101
101
> Document Intelligence Studio and the general document model are available with the v3.0 API.
102
102
103
-
1. On the Document Intelligence Studio home page, select **General documents**
103
+
1. On the Document Intelligence Studio home page, select **General documents**.
104
104
105
105
1. You can analyze the sample document or upload your own files.
106
106
107
-
1. Select the **Run analysis** button and, if necessary, configure the **Analyze options**:
107
+
1. Select the **Run analysis** button and, if necessary, configure the **Analyze options**:
108
108
109
109
:::image type="content" source="media/studio/run-analysis-analyze-options.png" alt-text="Screenshot of Run analysis and Analyze options buttons in the Document Intelligence Studio.":::
Key-value pairs are specific spans within the document that identify a label or key and its associated response or value. In a structured form, these pairs could be the label and the value the user entered for that field. In an unstructured document, they could be the date a contract was executed on based on the text in a paragraph. The AI model is trained to extract identifiable keys and values based on a wide variety of document types, formats, and structures.
116
+
Key-value pairs are specific spans within the document that identify a label or key and its associated response or value. In a structured form, these pairs could be the label and the value the user entered for that field. In an unstructured document, they could be the date a contract was executed on based on the text in a paragraph. The AI model is trained to extract identifiable keys and values based on a wide variety of document types, formats, and structures.
117
117
118
118
Keys can also exist in isolation when the model detects that a key exists, with no associated value or when processing optional fields. For example, a middle name field can be left blank on a form in some instances. Key-value pairs are spans of text contained in the document. For documents where the same value is described in different ways, for example, customer/user, the associated key is either customer or user (based on context).
119
119
@@ -131,7 +131,7 @@ Keys can also exist in isolation when the model detects that a key exists, with
131
131
132
132
## Considerations
133
133
134
-
*Keys are spans of text extracted from the document, for semi structured documents, keys can need to be mapped to an existing dictionary of keys.
134
+
*Because keys are spans of text extracted from the document, for semi structured documents, keys need to be mapped to an existing dictionary of keys.
135
135
136
136
* Expect to see key-value pairs with a key, but no value. For example if a user chose to not provide an email address on the form.
The Document Intelligence health insurance card model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract key information from US health insurance cards. A health insurance card is a key document for care processing and can be digitally analyzed for patient onboarding, financial coverage information, cashless payments, and insurance claim processing. The health insurance card model analyzes health card images; extracts key information such as insurer, member, prescription, and group number; and returns a structured JSON representation. Health insurance cards can be presented in various formats and quality including phone-captured images, scanned documents, and digital PDFs.
33
+
The Document Intelligence health insurance card model combines powerful Optical Character Recognition (OCR) capabilities with deep learning models to analyze and extract key information from US health insurance cards. A health insurance card is a key document for care processing and can be digitally analyzed for patient onboarding, financial coverage information, cashless payments, and insurance claim processing. The health insurance card model analyzes health card images; extracts key information such as insurer, member, prescription, and group number; and returns a structured JSON representation. Health insurance cards can be presented in various formats and quality including phone-captured images, scanned documents, and digital PDFs.
34
34
35
35
***Sample health insurance card processed using Document Intelligence Studio***
36
36
@@ -73,7 +73,7 @@ Document Intelligence v3.0 supports the following tools, applications, and libra
73
73
74
74
See how data is extracted from health insurance cards using the Document Intelligence Studio. You need the following resources:
75
75
76
-
* An Azure subscription—you can [create one for free](https://azure.microsoft.com/free/cognitive-services/)
76
+
* An Azure subscription—you can [create one for free](https://azure.microsoft.com/free/cognitive-services/).
77
77
78
78
* A [Document Intelligence instance](https://portal.azure.com/#create/Microsoft.CognitiveServicesFormRecognizer) in the Azure portal. You can use the free pricing tier (`F0`) to try the service. After your resource deploys, select **Go to resource** to get your key and endpoint.
79
79
@@ -91,7 +91,7 @@ See how data is extracted from health insurance cards using the Document Intelli
91
91
:::image type="content" source="media/studio/run-analysis-analyze-options.png" alt-text="Screenshot of Run analysis and Analyze options buttons in the Document Intelligence Studio.":::
@@ -149,6 +149,6 @@ See how data is extracted from health insurance cards using the Document Intelli
149
149
150
150
## Next steps
151
151
152
-
* Try processing your own forms and documents with the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio)
152
+
* Try processing your own forms and documents with the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio).
153
153
154
154
* Complete a [Document Intelligence quickstart](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.1.0&preserve-view=true) and get started creating a document processing app in the development language of your choice.
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/concept-invoice.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
@@ -223,7 +223,7 @@ See how data, including customer information, vendor details, and line items, is
223
223
| KVKNumber(NL-only) | String | A unique identifier for businesses registered in the Netherlands|12345678|
224
224
| PaymentDetails | Array | An array that holds Payment Option details such as `IBAN`,`SWIFT`, `BPay(AU)`||
225
225
| TotalDiscount | Number | The total discount applied to an invoice | Integer |
226
-
| TaxItems | Array | AN array that holds added tax information such as `CGST`, `IGST`, and `SGST`. This line item is currently only available for the Germany (`de`),Spain (`es`), Portugal (`pt`),and English Canada (`en-CA`) locales||
226
+
| TaxItems | Array | AN array that holds added tax information such as `CGST`, `IGST`, and `SGST`. This line item is currently only available for the Germany (`de`),Spain (`es`), Portugal (`pt`),and English Canada (`en-CA`) locales||
0 commit comments