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/concept-analyze-document-response.md
+7-8Lines changed: 7 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,11 +6,10 @@ author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-document-intelligence
8
8
ms.topic: conceptual
9
-
ms.date: 08/07/2024
9
+
ms.date: 09/26/2024
10
10
ms.author: vikurpad
11
11
ms.custom:
12
12
- references_regions
13
-
- ignite-2023
14
13
monikerRange: '>=doc-intel-3.0.0'
15
14
---
16
15
@@ -22,7 +21,7 @@ In this article, let's examine the different objects returned as part of the `An
22
21
23
22
## Analyze document request
24
23
25
-
The Document Intelligence APIs analyze images, PDFs, and other document files to extract and detect various content, layout, style, and semantic elements. The analyze operation is an async API. Submitting a document returns an **Operation-Location** header that contains the URL to poll for completion. When an analysis request completes successfully, the response contains the elements described in the [model data extraction](concept-model-overview.md#model-data-extraction).
24
+
The Document Intelligence APIs analyze images, PDFs, and other document files to extract and detect various content, layout, style, and semantic elements. The `Analyze` operation is an async API. Submitting a document returns an **Operation-Location** header that contains the URL to poll for completion. When an analysis request completes successfully, the response contains the elements described in the [model data extraction](concept-model-overview.md#model-data-extraction).
26
25
27
26
### Response elements
28
27
@@ -43,7 +42,7 @@ The top-level content property contains a concatenation of all content elements
43
42
44
43
## Analyze response
45
44
46
-
The analyze response for each API returns different objects. API responses contain elements from component models where applicable.
45
+
The `Analyze` response for each API returns different objects. API responses contain elements from component models where applicable.
47
46
48
47
| Response content | Description | API |
49
48
|--|--|--|
@@ -52,8 +51,8 @@ The analyze response for each API returns different objects. API responses conta
52
51
|**styles**| Identified text element properties. | Read, Layout, General Document, Prebuilt, and Custom models|
53
52
|**languages**| Identified language associated with each span of the text extracted | Read |
54
53
|**tables**| Tabular content identified and extracted from the document. Tables relate to tables identified by the pretrained layout model. Content labeled as tables is extracted as structured fields in the documents object.| Layout, General Document, Invoice, and Custom models |
55
-
|**figures**| Figures (charts, images) identified and extracted from the document, providing visual representations that aid in the understanding of complex information. | Layout model |
56
-
|**sections**| Hierarchical document structure identified and extracted from the document. Section or subsection with the corresponding elements (paragraph, table, figure) attached to it. | Layout model |
54
+
|**figures**| Figures (charts, images) identified and extracted from the document, providing visual representations that aid in the understanding of complex information. |The Layout model |
55
+
|**sections**| Hierarchical document structure identified and extracted from the document. Section or subsection with the corresponding elements (paragraph, table, figure) attached to it. |The Layout model |
57
56
|**keyValuePairs**| Key-value pairs recognized by a pretrained model. The key is a span of text from the document with the associated value. | General document and Invoice models |
58
57
|**documents**| Fields recognized are returned in the `fields` dictionary within the list of documents| Prebuilt models, Custom models.|
59
58
@@ -142,7 +141,7 @@ Based on its position and styling, a cell can be classified as general content,
142
141
Figures (charts, images) in documents play a crucial role in complementing and enhancing the textual content, providing visual representations that aid in the understanding of complex information. The figures object detected by the Layout model has key properties like `boundingRegions` (the spatial locations of the figure on the document pages, including the page number and the polygon coordinates that outline the figure's boundary), `spans` (details the text spans related to the figure, specifying their offsets and lengths within the document's text. This connection helps in associating the figure with its relevant textual context), `elements` (the identifiers for text elements or paragraphs within the document that are related to or describe the figure) and `caption`, if any.
143
142
144
143
When *output=figures* is specified during the initial `Analyze` operation, the service generates cropped images for all detected figures that can be accessed via `/analyeResults/{resultId}/figures/{figureId}`.
145
-
`FigureId`will be included in each figure object, following an undocumented convention of `{pageNumber}.{figureIndex}` where `figureIndex` resets to one per page.
144
+
`FigureId`is included in each figure object, following an undocumented convention of `{pageNumber}.{figureIndex}` where `figureIndex` resets to one per page.
146
145
147
146
```json
148
147
{
@@ -255,7 +254,7 @@ The semantic schema of a document type is described via the fields it contains.
255
254
| date | Date | ISO 8601 - YYYY-MM-DD | InvoiceDate: "5/7/2022" → "2022-05-07" |
256
255
| time | Time | ISO 8601 - hh:mm:ss | TransactionTime: "9:45 PM" → "21:45:00" |
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/concept-custom-classifier.md
+5-6Lines changed: 5 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,16 +1,15 @@
1
1
---
2
-
title: Custom classification model - Document Intelligence
2
+
title: Custom classification model - Document Intelligence
3
3
titleSuffix: Azure AI services
4
4
description: Use the custom classification model to train a model to identify and split the documents you process within your application.
5
5
author: vkurpad
6
6
manager: nitinme
7
7
ms.service: azure-ai-document-intelligence
8
8
ms.topic: conceptual
9
-
ms.date: 08/07/2024
9
+
ms.date: 09/26/2024
10
10
ms.author: lajanuar
11
11
ms.custom:
12
12
- references_regions
13
-
- ignite-2023
14
13
monikerRange: '>=doc-intel-3.1.0'
15
14
---
16
15
@@ -50,7 +49,6 @@ Custom classification models are deep-learning-model types that combine layout a
50
49
Custom classification models can analyze a single- or multi-file documents to identify if any of the trained document types are contained within an input file. Here are the currently supported scenarios:
51
50
52
51
* A single file containing one document type, such as a loan application form.
53
-
54
52
* A single file containing multiple document types. For instance, a loan application package that contains a loan application form, payslip, and bank statement.
55
53
56
54
* A single file containing multiple instances of the same document. For instance, a collection of scanned invoices.
@@ -59,7 +57,8 @@ Custom classification models can analyze a single- or multi-file documents to id
59
57
60
58
✔️ The maximum allowed number of classes is `500`. The maximum allowed number of document samples per class is `100`.
61
59
62
-
The model classifies each page of the input document, unless specified, to one of the classes in the labeled dataset. You can specify the page numbers to analyze in the input document as well. To set the threshold for your application, use the confidence score from the response.
60
+
The model classifies each page of the input document, unless specified, to one of the classes in the labeled dataset. You can specify the page numbers to analyze in the input document as well. To set the threshold for your application, use the confidence score from the response.
61
+
63
62
### Incremental training
64
63
65
64
With custom models, you need to maintain access to the training dataset to update your classifier with new samples for an existing class, or add new classes. Classifier models now support incremental training where you can reference an existing classifier and append new samples for an existing class or add new classes with samples. Incremental training enables scenarios where data retention is a challenge and the classifier needs to be updated to align with changing business needs. Incremental training is supported with models trained with API version `2024-02-29-preview` and later.
@@ -250,7 +249,7 @@ Alternatively, if you have a flat list of files or only plan to use a few select
250
249
```
251
250
252
251
As an example, the file list `car-maint.jsonl` contains the following files.
253
-
252
+
254
253
```json
255
254
{"file":"classifier/car-maint/Commercial Motor Vehicle - Adatum.pdf"}
256
255
{"file":"classifier/car-maint/Commercial Motor Vehicle - Fincher.pdf"}
1. Next, you're going to fill out the **Create Document Intelligence** fields with the following values:
40
+
1. Next, you're going to fill out the **`Create Document Intelligence`** fields with the following values:
41
41
42
42
***Subscription**. Select your current subscription.
43
-
***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 a pre-existing group.
43
+
***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.
44
44
***Region**. Select your local region.
45
45
***Name**. Enter a name for your resource. We recommend using a descriptive name, for example *YourNameFormRecognizer*.
46
46
***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.
@@ -140,7 +140,7 @@ You receive a `202 (Success)` response that includes a read-only **Operation-Loc
140
140
141
141
:::moniker range="doc-intel-4.0.0"
142
142
143
-
After you call the [`Analyze document`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-2024-02-29-preview&preserve-view=true&branch=docintelligence&tabs=HTTP) API, call the [**Get analyze result**](/rest/api/aiservices/document-models/get-analyze-result?view=rest-aiservices-2024-02-29-preview&preserve-view=true&branch=docintelligence&tabs=HTTP) API to get the status of the operation and the extracted data. Before you run the command, make these changes:
143
+
After you call the [`Analyze document`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v4.0%20(2024-07-31-preview)&preserve-view=true&tabs=HTTP) API, call the [**Get analyze result**](/rest/api/aiservices/document-models/get-analyze-result?view=rest-aiservices-v4.0%20(2024-07-31-preview)&preserve-view=true&tabs=HTTP) API to get the status of the operation and the extracted data. Before you run the command, make these changes:
144
144
:::moniker-end
145
145
146
146
:::moniker range="doc-intel-3.1.0"
@@ -165,7 +165,7 @@ After you call the [`Analyze document`](/rest/api/aiservices/document-models/ana
165
165
:::moniker range="doc-intel-4.0.0"
166
166
167
167
```bash
168
-
curl -v -X GET "{endpoint}/documentintelligence/documentModels/{modelId}/analyzeResults/{resultId}?api-version=2024-02-29-preview" -H "Ocp-Apim-Subscription-Key: {key}"
168
+
curl -v -X GET "{endpoint}/documentintelligence/documentModels/{modelId}/analyzeResults/{resultId}?api-version=2024-07-31-preview" -H "Ocp-Apim-Subscription-Key: {key}"
169
169
```
170
170
171
171
:::moniker-end
@@ -202,7 +202,7 @@ You receive a `200 (Success)` response with JSON output. The first field, `"stat
Copy file name to clipboardExpand all lines: articles/ai-services/speech-service/speech-services-quotas-and-limits.md
+4Lines changed: 4 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -136,6 +136,10 @@ The limits in this table apply per Speech resource when you create a personal vo
136
136
| Quota | Free (F0)| Standard (S0) |
137
137
|-----|-----|-----|
138
138
| New connections per minute | Not available for F0 | 2 new connections per minute |
139
+
| Max connection duration with speaking | Not available for F0 | 10 minutes<sup>1</sup> |
140
+
| Max connection duration with idle state | Not available for F0 | 5 minutes |
141
+
142
+
<sup>1</sup> To ensure continuous operation of the real-time avatar for more than 10 minutes, you can enable auto-reconnect. For information about how to set up auto-reconnect, refer to this [sample code](https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/js/browser/avatar/README.md) (search "auto reconnect").
You can find end-to-end working samples on [GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/samples/js/browser/avatar).
182
182
183
+
## Close the real-time avatar connection
184
+
185
+
To avoid unnecessary costs after you finish using the real-time avatar, it’s important to close the connection. There are several ways to do this:
186
+
187
+
- When the browser web page is closed, the WebRTC client side peer connection object will be released, and the avatar connection will be automatically closed after a few seconds.
188
+
- If the avatar remains idle for 5 minutes, the connection will be automatically closed by the avatar service.
189
+
- You can proactively close the avatar connection by running the following code:
190
+
191
+
```javascript
192
+
avatarSynthesizer.close()
193
+
```
194
+
195
+
You can find end-to-end working samples on [GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/samples/js/browser/avatar).
196
+
183
197
## Edit background
184
198
185
199
The avatar real-time synthesis API currently doesn't support setting a background image/video and only supports setting a solid-color background, without transparent background support. However, there's an alternative way to implement background customization on the client side, following these guidelines:
0 commit comments