Skip to content

Commit 7341d04

Browse files
TaojunshenTaojunshen
authored
Merge pull request #733 from MicrosoftDocs/main
10/9/2024 PM Publish
2 parents aecb9f8 + 9d892e0 commit 7341d04

27 files changed

+133
-125
lines changed

‎articles/ai-services/openai/concepts/models.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -430,10 +430,10 @@ These models can only be used with Embedding API requests.
430430
431431
| Model ID | Max Request (tokens) | Output Dimensions |Training Data (up-to)
432432
|---|---| :---:|:---:|:---:|
433-
| `text-embedding-ada-002` (version 2) |8,191 | 1,536 | Sep 2021 |
433+
| `text-embedding-ada-002` (version 2) |8,192 | 1,536 | Sep 2021 |
434434
| `text-embedding-ada-002` (version 1) |2,046 | 1,536 | Sep 2021 |
435-
| `text-embedding-3-large` | 8,191 | 3,072 |Sep 2021 |
436-
| `text-embedding-3-small` | 8,191| 1,536 | Sep 2021 |
435+
| `text-embedding-3-large` | 8,192 | 3,072 |Sep 2021 |
436+
| `text-embedding-3-small` | 8,192| 1,536 | Sep 2021 |
437437

438438
> [!NOTE]
439439
> When sending an array of inputs for embedding, the max number of input items in the array per call to the embedding endpoint is 2048.

‎articles/ai-services/openai/how-to/embeddings.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -126,8 +126,9 @@ return $response.data.embedding
126126

127127
### Verify inputs don't exceed the maximum length
128128

129-
- The maximum length of input text for our latest embedding models is 8192 tokens. You should verify that your inputs don't exceed this limit before making a request.
129+
- The maximum length of input text for our latest embedding models is 8,192 tokens. You should verify that your inputs don't exceed this limit before making a request.
130130
- If sending an array of inputs in a single embedding request the max array size is 2048.
131+
- The sum of the token count of the entire array of inputs sent in a single API call is subject to the max token limit of 8192. For example, you cannot send an array of 2,048 inputs with each input having five tokens or more. The total token count of this API request would be 10,240 total tokens, 2,048 tokens over the 8192 per API call token limit.
131132

132133

133134
## Limitations & risks

‎articles/ai-services/openai/includes/model-matrix/provisioned-models.md

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -11,7 +11,7 @@ ms.date: 10/03/2024
1111

1212
| **Region** | **gpt-4**, **0613** | **gpt-4**, **1106-Preview** | **gpt-4**, **0125-Preview** | **gpt-4**, **turbo-2024-04-09** | **gpt-4o**, **2024-05-13** | **gpt-4o**, **2024-08-06** | **gpt-4o-mini**, **2024-07-18** | **gpt-4-32k**, **0613** | **gpt-35-turbo**, **1106** | **gpt-35-turbo**, **0125** |
1313
|:-------------------|:-------------------:|:---------------------------:|:---------------------------:|:-------------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|:-----------------------:|:--------------------------:|:--------------------------:|
14-
| australiaeast | ✅ | ✅ | ✅ | ✅ | ✅ | - | ✅ | ✅ | ✅ | ✅ |
14+
| australiaeast | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
1515
| brazilsouth | ✅ | ✅ | ✅ | - | ✅ | - | ✅ | ✅ | ✅ | - |
1616
| canadacentral | ✅ | - | - | - | - | - | - | ✅ | - | ✅ |
1717
| canadaeast | ✅ | ✅ | - | ✅ | ✅ | - | ✅ | - | ✅ | - |
@@ -22,14 +22,14 @@ ms.date: 10/03/2024
2222
| japaneast | - | ✅ | ✅ | ✅ | ✅ | - | ✅ | - | - | ✅ |
2323
| koreacentral | ✅ | - | - | ✅ | ✅ | - | ✅ | ✅ | ✅ | - |
2424
| northcentralus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
25-
| norwayeast | ✅ | - | ✅ | - | - | - | - | ✅ | - | - |
25+
| norwayeast | ✅ | - | ✅ | - | - | - | ✅ | ✅ | - | - |
2626
| polandcentral | ✅ | ✅ | ✅ | ✅ | ✅ | - | - | ✅ | ✅ | ✅ |
27-
| southafricanorth | ✅ | ✅ | - | ✅ | - | - | - | ✅ | ✅ | - |
27+
| southafricanorth | ✅ | ✅ | - | ✅ | ✅ | - | - | ✅ | ✅ | - |
2828
| southcentralus | ✅ | ✅ | ✅ | ✅ | ✅ | - | - | ✅ | ✅ | ✅ |
2929
| southindia | ✅ | ✅ | ✅ | - | ✅ | - | ✅ | ✅ | ✅ | ✅ |
3030
| swedencentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
3131
| switzerlandnorth | ✅ | ✅ | ✅ | ✅ | ✅ | - | ✅ | ✅ | ✅ | ✅ |
3232
| switzerlandwest | - | - | - | - | - | - | - | - | - | ✅ |
3333
| uksouth | ✅ | ✅ | ✅ | ✅ | ✅ | - | - | ✅ | ✅ | ✅ |
34-
| westus | ✅ | ✅ | ✅ | ✅ | ✅ | - | ✅ | ✅ | ✅ | ✅ |
35-
| westus3 | ✅ | ✅ | ✅ | ✅ | ✅ | - | - | ✅ | ✅ | ✅ |
34+
| westus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
35+
| westus3 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | - | ✅ | ✅ | ✅ |

‎articles/ai-studio/concepts/encryption-keys-portal.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,7 @@ The following data is stored on the managed resources.
5050
A new architecture for customer-managed key encryption with hubs is available in preview, which resolves the dependency on the managed resource group. In this new model, encrypted data is stored service-side on Microsoft-managed resources instead of in managed resources in your subscription. Metadata is stored in multitenant resources using document-level CMK encryption. An Azure AI Search instance is hosted on the Microsoft-side per customer, and for each hub. Due to its dedicated resource model, its Azure cost is charged in your subscription via the hub resource.
5151

5252
> [!NOTE]
53-
> During this preview key rotation and user-assigned identity capabilities are not supported. Server-side encryption is currently not supported in reference to an Azure Key Vault for storing your encryption key that has public network access disabled.
53+
> During this preview key rotation and user-assigned identity capabilities are not supported. Service-side encryption is currently not supported in reference to an Azure Key Vault for storing your encryption key that has public network access disabled.
5454
5555
## Use customer-managed keys with Azure Key Vault
5656

@@ -83,7 +83,7 @@ Customer-managed key encryption is configured via Azure portal in a similar way
8383
1. Create a new Azure resource in Azure portal.
8484
1. Under the encryption tab, select your encryption key.
8585

86-
:::image type="content" source="../../machine-learning/media/concept-customer-managed-keys/cmk-service-side-encryption.png" alt-text="Screenshot of the encryption tab with the option for server side encryption selected." lightbox="../../machine-learning/media/concept-customer-managed-keys/cmk-service-side-encryption.png":::
86+
:::image type="content" source="../../machine-learning/media/concept-customer-managed-keys/cmk-service-side-encryption.png" alt-text="Screenshot of the encryption tab with the option for service side encryption selected." lightbox="../../machine-learning/media/concept-customer-managed-keys/cmk-service-side-encryption.png":::
8787

8888
Alternatively, use infrastructure-as-code options for automation. Example Bicep templates for Azure AI Studio are available on the Azure Quickstart repo:
8989
1. [CMK encryption for hub](https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aistudio-cmk).

‎articles/ai-studio/how-to/model-catalog-overview.md

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -53,6 +53,8 @@ For more information on Azure OpenAI models, see [What is Azure OpenAI Service?]
5353
The model catalog offers two distinct ways to deploy models for your use: managed compute and serverless APIs.
5454

5555
The deployment options and features available for each model vary, as described in the following tables. [Learn more about data processing with the deployment options]( concept-data-privacy.md).
56+
57+
### Capabilities of model deployment options
5658
<!-- docutune:disable -->
5759

5860
Features | Managed compute | Serverless API (pay-as-you-go)
@@ -62,6 +64,8 @@ API authentication | Keys and Microsoft Entra authentication. | Keys only.
6264
Content safety | Use Azure AI Content Safety service APIs. | Azure AI Content Safety filters are available integrated with inference APIs. Azure AI Content Safety filters are billed separately.
6365
Network isolation | [Configure managed networks for Azure AI Studio hubs](configure-managed-network.md). | Managed compute follow your hub's public network access (PNA) flag setting. For more information, see the [Network isolation for models deployed via Serverless APIs](#network-isolation-for-models-deployed-via-serverless-apis) section later in this article.
6466

67+
### Available models for supported deployment options
68+
6569
Model | Managed compute | Serverless API (pay-as-you-go)
6670
--|--|--
6771
Llama family models | Llama-2-7b <br> Llama-2-7b-chat <br> Llama-2-13b <br> Llama-2-13b-chat <br> Llama-2-70b <br> Llama-2-70b-chat <br> Llama-3-8B-Instruct <br> Llama-3-70B-Instruct <br> Llama-3-8B <br> Llama-3-70B | Llama-3-70B-Instruct <br> Llama-3-8B-Instruct <br> Llama-2-7b <br> Llama-2-7b-chat <br> Llama-2-13b <br> Llama-2-13b-chat <br> Llama-2-70b <br> Llama-2-70b-chat

‎articles/ai-studio/media/explore/custom-navigation.gif

-2.07 MB
Binary file not shown.

0 commit comments

Comments
 (0)