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/how-to/provisioned-get-started.md
+13-13Lines changed: 13 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,40 +37,40 @@ Creating a new deployment requires available (unused) quota to cover the desired
37
37
38
38
Then 200 PTUs of quota are considered used, and there are 300 PTUs available for use to create new deployments.
39
39
40
-
A default amount of PTU quota is assigned to all subscriptions in several regions. You can view the quota available to you in a region by visiting the Quotas blade in Azure OpenAI Studio and selecting the desired subscription and region. For example, the screenshot below shows a quota limit of 500 PTUs in West US for the selected subscription. Note that you might see lower values of available default quotas.
41
-
40
+
A default amount of provisioned and global provisioned quota is assigned to all subscriptions in several regions. You can view the quota available to you in a region by visiting the Quotas blade in Azure OpenAI Studio and selecting the desired subscription and region. For example, the screenshot below shows a quota limit of 500 PTUs in West US for the selected subscription. Note that you might see lower values of available default quotas.
41
+
42
42
:::image type="content" source="../media/provisioned/available-quota.png" alt-text="A screenshot of the available quota in Azure OpenAI studio." lightbox="../media/provisioned/available-quota.png":::
43
43
44
44
Additional quota can be requested by clicking the Request Quota link to the right of the “Usage/Limit” column. (This is off-screen in the screenshot above).
45
45
46
46
## Create an Azure OpenAI resource
47
47
48
-
Provisioned Throughput deployments are created via Azure OpenAI resource objects within Azure. You must have an Azure OpenAI resource in each region where you intend to create a deployment. Use the Azure portal to [create a resource](./create-resource.md) in a region with available quota, if required.
48
+
Provisioned and global provisioned deployments are created via Azure OpenAI resource objects within Azure. You must have an Azure OpenAI resource in each region where you intend to create a deployment. Use the Azure portal to [create a resource](./create-resource.md) in a region with available quota, if required.
49
49
50
50
> [!NOTE]
51
-
> Azure OpenAI resources can support multiple types of Azure OpenAI deployments at the same time. It is not necessary to dedicate new resources for your provisioned deployments.
52
-
53
-
## Create your provisioned deployment - capacity is available
51
+
> Azure OpenAI resources can support multiple types of Azure OpenAI deployments at the same time. It is not necessary to dedicate new resources for your provisioned or global provisioned deployments.
52
+
## Create your provisioned or global provisioned deployment - capacity is available
54
53
55
-
After you purchase a commitment on your quota, you can create a deployment. To create a provisioned deployment, you can follow these steps; the choices described reflect the entries shown in the screenshot.
54
+
once you have verified your quota, you can create a deployment. To create a provisioned deployment, you can follow these steps; the choices described reflect the entries shown in the screenshot.
56
55
57
56
:::image type="content" source="../media/provisioned/deployment-screen.png" alt-text="Screenshot of the Azure OpenAI Studio deployment page for a provisioned deployment." lightbox="../media/provisioned/deployment-screen.png":::
58
57
59
58
60
59
61
60
1. Sign into the [Azure OpenAI Studio](https://oai.azure.com)
62
-
2. Choose the subscription that was enabled for provisioned deployments & select the desired resource in a region where you have the quota.
61
+
1. Choose the subscription that was enabled for provisioned and global provisioned deployments & select the desired resource in a region where you have the quota.
62
+
63
63
3. Under **Management** in the left-nav select **Deployments**.
64
64
4. Select Create new deployment and configure the following fields. Expand the **advanced options** drop-down menu.
65
65
5. Fill out the values in each field. Here's an example:
66
66
67
67
| Field | Description | Example |
68
-
|--|--|--|
68
+
|--|--|--|
69
69
| Select a model| Choose the specific model you wish to deploy. | GPT-4 |
70
70
| Model version | Choose the version of the model to deploy. | 0613 |
71
71
| Deployment Name | The deployment name is used in your code to call the model by using the client libraries and the REST APIs. | gpt-4|
72
72
| Content filter | Specify the filtering policy to apply to the deployment. Learn more on our [Content Filtering](../concepts/content-filter.md) how-to. | Default |
73
-
| Deployment Type |This impacts the throughput and performance. Choose Provisioned-Managed for your provisioned deployment | Provisioned-Managed |
73
+
| Deployment Type |This impacts the throughput and performance. Choose Provisioned-Managed or Global Provisioned-Managed for your deployment | Provisioned-Managed |
74
74
| Provisioned Throughput Units | Choose the amount of throughput you wish to include in the deployment. | 100 |
75
75
76
76
Important things to note:
@@ -87,7 +87,7 @@ The image below shows the pricing confirmation you will see. The price shown is
87
87
88
88
:::image type="content" source="../media/provisioned/confirm-pricing.png" alt-text="Screenshot showing the pricing confirmation screen." lightbox="../media/provisioned/confirm-pricing.png":::
89
89
90
-
If you wish to create your deployment programmatically, you can do so with the following Azure CLI command. Update the `sku-capacity` with the desired number of provisioned throughput units.
90
+
If you wish to create your deployment programmatically, you can do so with the following Azure CLI command. To specify the deployment type, modify the `sku-name` to `ProvisionedManaged` or `GlobalProvisionedManaged` based on the intended deployment type. Update the `sku-capacity` with the desired number of provisioned throughput units.
91
91
92
92
```cli
93
93
az cognitiveservices account deployment create \
@@ -101,9 +101,9 @@ az cognitiveservices account deployment create \
101
101
--sku-name ProvisionedManaged
102
102
```
103
103
104
-
REST, ARM template, Bicep, and Terraform can also be used to create deployments. See the section on automating deployments in the [Managing Quota](quota.md?tabs=rest#automate-deployment) how-to guide and replace the `sku.name` with "ProvisionedManaged" rather than "Standard."
104
+
REST, ARM template, Bicep, and Terraform can also be used to create deployments. See the section on automating deployments in the [Managing Quota](quota.md?tabs=rest#automate-deployment) how-to guide and replace the `sku.name` with "ProvisionedManaged" or "GlobalProvisionedManaged" rather than "Standard."
105
105
106
-
## Create your provisioned deployment – Capacity is not available
106
+
## Create your provisioned or global provisioned deployment – Capacity is not available
107
107
108
108
Due to the dynamic nature of capacity availability, it is possible that the region of your selected resource might not have the service capacity to create the deployment of the specified model, version, and number of PTUs.
0 commit comments