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/openai/quotas-limits.md
+7-6Lines changed: 7 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,7 +10,7 @@ ms.custom:
10
10
- ignite-2023
11
11
- references_regions
12
12
ms.topic: conceptual
13
-
ms.date: 08/14/2024
13
+
ms.date: 08/16/2024
14
14
ms.author: mbullwin
15
15
---
16
16
@@ -50,27 +50,28 @@ The following sections provide you with a quick guide to the default quotas and
50
50
| GPT-4 `vision-preview` & GPT-4 `turbo-2024-04-09` default max tokens | 16 <br><br> Increase the `max_tokens` parameter value to avoid truncated responses. GPT-4o max tokens defaults to 4096. |
51
51
| Max number of custom headers in API requests<sup>1</sup> | 10 |
52
52
53
-
<sup>1</sup> Our current APIs allow up to 10 custom headers, which are passed through the pipeline, and returned. We have noticed some customers now exceed this header count resulting in HTTP 431 errors. There is no solution for this error, other than to reduce header volume. **In future API versions we will no longer pass through custom headers**. We recommend customers not depend on custom headers in future system architectures.
54
-
53
+
<sup>1</sup> Our current APIs allow up to 10 custom headers, which are passed through the pipeline, and returned. We have noticed some customers now exceed this header count resulting in HTTP 431 errors. There is no solution for this error, other than to reduce header volume. **In future API versions we will no longer pass through custom headers**. We recommend customers not depend on custom headers in future system architectures.
Copy file name to clipboardExpand all lines: articles/ai-services/what-are-ai-services.md
+12-7Lines changed: 12 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -21,30 +21,35 @@ ms.custom:
21
21
22
22
## Available Azure AI services
23
23
24
-
Learn how an Azure AI service can help your enhance applications and optimize your workflows:
24
+
When building AI applications, use the following Azure AI services:
25
25
26
26
| Service | Description |
27
27
| --- | --- |
28
-
|[Anomaly Detector](./Anomaly-Detector/index.yml) (retired) | Identify potential problems early on. |
29
28
|[Azure AI Search](../search/index.yml)| Bring AI-powered cloud search to your mobile and web apps. |
30
29
|[Azure OpenAI](./openai/index.yml)| Perform a wide variety of natural language tasks. |
31
30
|[Bot Service](/composer/)| Create bots and connect them across channels. |
32
-
|[Content Moderator](./content-moderator/index.yml) (retired) | Detect potentially offensive or unwanted content. |
33
31
|[Content Safety](./content-safety/index.yml)| An AI service that detects unwanted contents. |
34
32
|[Custom Vision](./custom-vision-service/index.yml)| Customize image recognition for your business. |
|[Face](./computer-vision/overview-identity.md)| Detect and identify people and emotions in images. |
37
35
|[Immersive Reader](./immersive-reader/index.yml)| Help users read and comprehend text. |
38
36
|[Language](./language-service/index.yml)| Build apps with industry-leading natural language understanding capabilities. |
39
-
|[Language understanding](./luis/index.yml) (retired) | Understand natural language in your apps. |
40
-
|[Metrics Advisor](./metrics-advisor/index.yml) (retired) | An AI service that detects unwanted contents. |
41
-
|[Personalizer](./personalizer/index.yml) (retired) | Create rich, personalized experiences for each user. |
42
-
|[QnA maker](./qnamaker/index.yml) (retired) | Distill information into easy-to-navigate questions and answers. |
43
37
|[Speech](./speech-service/index.yml)| Speech to text, text to speech, translation, and speaker recognition. |
44
38
|[Translator](./translator/index.yml)| Use AI-powered translation technology to translate more than 100 in-use, at-risk, and endangered languages and dialects. |
45
39
|[Video Indexer](/azure/azure-video-indexer/)| Extract actionable insights from your videos. |
46
40
|[Vision](./computer-vision/index.yml)| Analyze content in images and videos. |
47
41
42
+
The following Azure AI services are scheduled for retirement. These services are still available for existing applications but don't use them for new AI applications:
43
+
44
+
| Service | Description |
45
+
| --- | --- |
46
+
|[Anomaly Detector](./Anomaly-Detector/index.yml) (retired) | Identify potential problems early on. |
47
+
|[Content Moderator](./content-moderator/index.yml) (retired) | Detect potentially offensive or unwanted content. |
48
+
|[Language understanding](./luis/index.yml) (retired) | Understand natural language in your apps. |
49
+
|[Metrics Advisor](./metrics-advisor/index.yml) (retired) | An AI service that detects unwanted contents. |
50
+
|[Personalizer](./personalizer/index.yml) (retired) | Create rich, personalized experiences for each user. |
51
+
|[QnA maker](./qnamaker/index.yml) (retired) | Distill information into easy-to-navigate questions and answers. |
52
+
48
53
## Pricing tiers and billing
49
54
50
55
Pricing tiers (and the amount you get billed) are based on the number of transactions you send using your authentication information. Each pricing tier specifies the:
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/configure-managed-network.md
+46Lines changed: 46 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -629,6 +629,52 @@ To configure a managed virtual network that allows only approved outbound commun
629
629
630
630
---
631
631
632
+
## Manually provision a managed VNet
633
+
634
+
The managed VNet is automatically provisioned when you create a compute instance. When you rely on automatic provisioning, it can take around __30 minutes__ to create the first compute instance as it is also provisioning the network. If you configured FQDN outbound rules (only available with allow only approved mode), the first FQDN rule adds around __10 minutes__ to the provisioning time. If you have a large set of outbound rules to be provisioned in the managed network, it can take longer for provisioning to complete. The increased provisioning time can cause your first compute instance creation to time out.
635
+
636
+
To reduce the wait time and avoid potential timeout errors, we recommend manually provisioning the managed network. Then wait until the provisioning completes before you create a compute instance.
637
+
638
+
> [!NOTE]
639
+
> To create an online deployment, you must manually provision the managed network, or create a compute instance first which will automatically provision it.
640
+
641
+
# [Azure portal](#tab/portal)
642
+
643
+
Use the __Azure CLI__or __Python SDK__ tabs to learn how to manually provision the managed VNet.
644
+
645
+
# [Azure CLI](#tab/azure-cli)
646
+
647
+
The following example shows how to provision a managed VNet.
648
+
649
+
```azurecli
650
+
az ml workspace provision-network -g my_resource_group -n my_ai_hub_name
651
+
```
652
+
653
+
To verify that the provisioning has completed, use the following command:
654
+
655
+
```azurecli
656
+
az ml workspace show -n my_ai_hub_name -g my_resource_group --query managed_network
657
+
```
658
+
659
+
# [Python SDK](#tab/python)
660
+
661
+
The following example shows how to provision a managed VNet:
To verify that the AI Hub has been provisioned, use `ml_client.workspaces.get()` to get the AI Hub information. The `managed_network`property contains the status of the managed network.
0 commit comments