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/content-safety/concepts/groundedness.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -57,7 +57,7 @@ The maximum character limit for the grounding sources is 55,000 characters per A
57
57
58
58
To use this API, you must create your Azure AI Content Safety resource in the supported regions. Currently, it's available in the following Azure regions:
59
59
- East US 2
60
-
- East US (only for non-reasoning)
60
+
- East US
61
61
- West US
62
62
- Sweden Central
63
63
@@ -75,4 +75,4 @@ If you need a higher rate, [contact us](mailto:[email protected]
75
75
Follow the quickstart to get started using Azure AI Content Safety to detect groundedness.
@@ -62,26 +62,26 @@ Use the following table as a reference. Replace *\<modelId>* and *\<document-url
62
62
Open a console window and run the following cURL command. The commands include the endpoint and key environment variables previously created in the set environment variables section. Replace those variables if your variable names differ. Remember to replace the *\<modelId>* and *\<document-url>* parameters.
To enable add-on capabilities, use the `features` query parameter in the POST request. There are four add-on capabilities available with the `2023-07-31` (GA) release: *ocr.highResolution*, *ocr.formula*, *ocr.font*, and *queryFields.premium*. To learn more about each of the capabilities, see [Custom models](../../../concept-accuracy-confidence.md).
68
+
To enable add-on capabilities, use the `features` query parameter in the POST request. There are four add-on capabilities available with the `2023-07-31` (GA) and later releases: *ocr.highResolution*, *ocr.formula*, *ocr.font*, and *queryFields.premium*. To learn more about each of the capabilities, see [Custom models](../../../concept-accuracy-confidence.md).
69
69
70
70
You can only call the *highResolution*, *formula*, and *font* capabilities for the Read and Layout model, and the *queryFields* capability for the General Documents model. The following example shows how to call the *highResolution*, *formula*, and *font* capabilities for the Layout model.
You receive a `202 (Success)` response that includes an `Operation-location` header. Use the value of this header to retrieve the response results.
79
79
80
-
:::image type="content" source="../../../media/how-to/rest-get-response.png" alt-text="Screenshot shows a POST response with the operation location highlighted.":::
80
+
:::image type="content" source="../../../media/quickstarts/operation-location-result-id.png" alt-text="Screenshot shows a POST response with the operation location highlighted.":::
81
81
82
82
### Get analyze result (GET Request)
83
83
84
-
After you call the [`Analyze document`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-2023-07-31&preserve-view=true&tabs=HTTP) API, call the [`Get analyze` result}(/rest/api/aiservices/document-models/get-analyze-result?view=rest-aiservices-2023-07-31&preserve-view=true&tabs=HTTP) API to get the status of the operation and the extracted data.
84
+
After you call the [`Analyze document`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-2024-02-29-preview&preserve-view=true&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&tabs=HTTP) API to get the status of the operation and the extracted data.
85
85
86
86
<!-- markdownlint-disable MD024 -->
87
87
@@ -100,7 +100,7 @@ Use the NodeJS *json tool* as a JSON formatter for cURL. If you don't have [Node
100
100
1. Pretty print the JSON output by including the pipe character `| json` with your GET requests.
101
101
102
102
```console
103
-
curl -i -X GET "<endpoint>formrecognizer/documentModels/prebuilt-read/analyzeResults/0e49604a-2d8e-4b15-b6b8-bb456e5d3e0a?api-version=2023-07-31"-H "Ocp-Apim-Subscription-Key: <subscription key>" | json
103
+
curl -i -X GET "<endpoint>documentintelligence/documentModels/prebuilt-read/analyzeResults/0e49604a-2d8e-4b15-b6b8-bb456e5d3e0a?api-version=2024-02-29-preview"-H "Ocp-Apim-Subscription-Key: <subscription key>" | json
104
104
```
105
105
106
106
#### [macOS](#tab/macOS)
@@ -110,7 +110,7 @@ The *json_pp* command tool ships with macOS and can be used as a JSON formatter
110
110
- Pretty print the JSON output by including `| json_pp` with your GET requests.
111
111
112
112
```console
113
-
curl -i -X GET "{endpoint}formrecognizer/documentModels/prebuilt-read/analyzeResults/0e49604a-2d8e-4b15-b6b8-bb456e5d3e0a?api-version=2023-07-31"-H "Ocp-Apim-Subscription-Key: <subscription key>" | json_pp
113
+
curl -i -X GET "{endpoint}documentintelligence/documentModels/prebuilt-read/analyzeResults/0e49604a-2d8e-4b15-b6b8-bb456e5d3e0a?api-version=2024-02-29-preview"-H "Ocp-Apim-Subscription-Key: <subscription key>" | json_pp
114
114
```
115
115
116
116
#### [Linux](#tab/linux)
@@ -120,7 +120,7 @@ The *json_pp* command line tool is preinstalled in most Linux distributions. If
120
120
- Pretty print the JSON output by including `| json_pp` with your `GET` requests.
121
121
122
122
```console
123
-
curl -i -X GET "<endpoint>formrecognizer/documentModels/prebuilt-read/analyzeResults/0e49604a-2d8e-4b15-b6b8-bb456e5d3e0a?api-version=2023-07-31"-H "Ocp-Apim-Subscription-Key: <subscription key>" | json_pp
123
+
curl -i -X GET "<endpoint>documentintelligence/documentModels/prebuilt-read/analyzeResults/0e49604a-2d8e-4b15-b6b8-bb456e5d3e0a?api-version=2024-02-29-preview"-H "Ocp-Apim-Subscription-Key: <subscription key>" | json_pp
124
124
```
125
125
126
126
---
@@ -130,11 +130,11 @@ The *json_pp* command line tool is preinstalled in most Linux distributions. If
130
130
Before you run the following command, make these changes:
131
131
132
132
- Replace *\<POST response>* with the `Operation-location` header from the [POST response](#post-response).
133
-
- Replace *\<FR_KEY* with the variable for your environment variable if it differs from the name in the code.
133
+
- Replace *\<DI_KEY* with the variable for your environment variable if it differs from the name in the code.
134
134
- Replace *\<json-tool> with your JSON formatting tool.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/how-to/managed-identity.md
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
4
4
description: Provides guidance on how to set managed identity with Microsoft Entra ID
5
5
ms.service: azure-ai-openai
6
6
ms.topic: how-to
7
-
ms.date: 02/29/2024
7
+
ms.date: 04/03/2024
8
8
author: mrbullwinkle
9
9
ms.author: mbullwin
10
10
recommendations: false
@@ -31,7 +31,7 @@ In the following sections, you'll use the Azure CLI to sign in, and obtain a bea
31
31
32
32
## Assign yourself to the Cognitive Services User role
33
33
34
-
Assign yourself the [Cognitive Services User](role-based-access-control.md#cognitive-services-contributor) role to allow you to use your account to make Azure OpenAI API calls rather than having to use key-based auth. After you make this change it can take up to 5 minutes before the change takes effect.
34
+
Assign yourself either the [Cognitive Services OpenAI User](role-based-access-control.md#cognitive-services-openai-user) or [Cognitive Services OpenAI Contributor](role-based-access-control.md#cognitive-services-openai-contributor) role to allow you to use your account to make Azure OpenAI inference API calls rather than having to use key-based auth. After you make this change it can take up to 5 minutes before the change takes effect.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/how-to/role-based-access-control.md
+4-2Lines changed: 4 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,7 +7,7 @@ author: mrbullwinkle
7
7
manager: nitinme
8
8
ms.service: azure-ai-language
9
9
ms.topic: how-to
10
-
ms.date: 11/15/2023
10
+
ms.date: 04/03/2024
11
11
ms.author: mbullwin
12
12
recommendations: false
13
13
---
@@ -53,6 +53,7 @@ If a user were granted role-based access to only this role for an Azure OpenAI r
53
53
✅ Ability to view the resource and associated model deployments in Azure OpenAI Studio. <br>
54
54
✅ Ability to view what models are available for deployment in Azure OpenAI Studio. <br>
55
55
✅ Use the Chat, Completions, and DALL-E (preview) playground experiences to generate text and images with any models that have already been deployed to this Azure OpenAI resource. <br>
56
+
✅ Make inference API calls with Microsoft Entra ID.
56
57
57
58
A user with only this role assigned would be unable to:
58
59
@@ -101,6 +102,7 @@ This role is typically granted access at the resource group level for a user in
101
102
A user with only this role assigned would be unable to:
102
103
103
104
❌ Access quota <br>
105
+
❌ Make inference API calls with Microsoft Entra ID.
104
106
105
107
### Cognitive Services Usages Reader
106
108
@@ -148,7 +150,7 @@ All the capabilities of Cognitive Services Contributor plus the ability to:
148
150
|Create customized content filters|❌|❌|✅| ➖ |
149
151
|Add a data source for the “on your data” feature|❌|❌|✅| ➖ |
150
152
|Access quota|❌|❌|❌|✅|
151
-
153
+
|Make inference API calls with Microsoft Entra ID| ✅ | ✅ | ❌ | ➖ |
152
154
## Common Issues
153
155
154
156
### Unable to view Azure Cognitive Search option in Azure OpenAI Studio
0 commit comments