Skip to content

Commit 8be4b9d

Browse files
v-aljev-alje
committed
Merge branch 'main' into release-preview-health-ai-models
2 parents 6b97dc6 + 6eadfc0 commit 8be4b9d

31 files changed

+54
-39
lines changed

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

Lines changed: 3 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@ manager: nitinme
66
ms.service: azure-ai-openai
77
ms.custom: references_regions
88
ms.topic: how-to
9-
ms.date: 10/14/2024
9+
ms.date: 10/18/2024
1010
author: mrbullwinkle
1111
ms.author: mbullwin
1212
recommendations: false
@@ -67,19 +67,15 @@ Refer to the [models page](../concepts/models.md) for the most up-to-date inform
6767

6868
API support was first added with `2024-07-01-preview`. Use `2024-10-01-preview` to take advantage of the latest features.
6969

70-
### Not supported
70+
### Feature support
7171

7272
The following aren't currently supported:
7373

7474
- Integration with the Assistants API.
7575
- Integration with Azure OpenAI On Your Data feature.
7676

7777
> [!NOTE]
78-
> There is a known issue with Azure OpenAI global batch and [structured outputs](./structured-outputs.md). Currently, lines in your jsonl file with structured output requests will fail with the following error message written to the error file:
79-
>
80-
> ***response_format value as json_schema is enabled only for api versions 2024-08-01-preview and later***.
81-
>
82-
>This error will occur even when your code targets the latest preview APIs which support structured outputs. Once the issue is resolved, this page will be updated.
78+
> Structured outputs is now supported with Global Batch when used in conjunction with API version `2024-08-01-preview` or later. Use `2024-10-01-preview` for the latest features.
8379
8480
### Global batch deployment
8581

‎articles/ai-services/openai/how-to/code-interpreter.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -145,14 +145,14 @@ assistant = client.beta.assistants.create(
145145
```console
146146
# Upload a file with an "assistants" purpose
147147

148-
curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/files?api-version=2024-05-01-preview \
148+
curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/files?api-version=2024-08-01-preview \
149149
-H "api-key: $AZURE_OPENAI_API_KEY" \
150150
-F purpose="assistants" \
151151
-F file="@c:\\path_to_file\\file.csv"
152152

153153
# Create an assistant using the file ID
154154

155-
curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/assistants?api-version=2024-05-01-preview \
155+
curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/assistants?api-version=2024-08-01-preview \
156156
-H "api-key: $AZURE_OPENAI_API_KEY" \
157157
-H 'Content-Type: application/json' \
158158
-d '{

‎articles/ai-services/openai/how-to/provisioned-throughput-onboarding.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ title: Azure OpenAI Service Provisioned Throughput Units (PTU) onboarding
33
description: Learn about provisioned throughput units onboarding and Azure OpenAI.
44
ms.service: azure-ai-openai
55
ms.topic: conceptual
6-
ms.date: 09/12/2024
6+
ms.date: 10/18/2024
77
manager: nitinme
88
author: mrbullwinkle
99
ms.author: mbullwin
@@ -33,7 +33,7 @@ Determining the right amount of provisioned throughput, or PTUs, you require for
3333

3434
### Estimate provisioned throughput and cost
3535

36-
To get a quick estimate for your workload, open the capacity planner in the [Azure OpenAI Studio](https://oai.azure.com). The capacity planner is under **Management** > **Quotas** > **Provisioned**.
36+
To get a quick estimate for your workload, open the capacity planner in the [Azure OpenAI Studio](https://oai.azure.com). The capacity planner is under **Shared resources** > **Quota** > **Azure OpenAI Provisioned**.
3737

3838
The **Provisioned** option and the capacity planner are only available in certain regions within the Quota pane, if you don't see this option setting the quota region to *Sweden Central* will make this option available. Enter the following parameters based on your workload.
3939

‎articles/ai-services/openai/how-to/structured-outputs.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -18,8 +18,8 @@ Structured outputs make a model follow a [JSON Schema](https://json-schema.org/o
1818

1919
> [!NOTE]
2020
> * Currently structured outputs is not supported on [bring your own data](../concepts/use-your-data.md) scenario.
21-
>
22-
> * There is a known issue blocking structured outputs support for [global batch](batch.md).
21+
22+
2323

2424
## Supported models
2525

‎articles/ai-services/openai/includes/batch/batch-python.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -55,6 +55,12 @@ Like [fine-tuning](../../how-to/fine-tuning.md), global batch uses files in JSON
5555
{"custom_id": "request-1", "method": "POST", "url": "/chat/completions", "body": {"model": "REPLACE-WITH-MODEL-DEPLOYMENT-NAME", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": [{"type": "text", "text": "What’s in this image?"},{"type": "image_url","image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}],"max_tokens": 1000}}
5656
```
5757

58+
# [Structured outputs](#tab/structured-outputs)
59+
60+
```json
61+
{"custom_id": "task-0", "method": "POST", "url": "/chat/completions", "body": {"model": "REPLACE-WITH-MODEL-DEPLOYMENT-NAME", "messages": [{"role": "system", "content": "Extract the event information."}, {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}], "response_format": {"type": "json_schema", "json_schema": {"name": "CalendarEventResponse", "strict": true, "schema": {"type": "object", "properties": {"name": {"type": "string"}, "date": {"type": "string"}, "participants": {"type": "array", "items": {"type": "string"}}}, "required": ["name", "date", "participants"], "additionalProperties": false}}}}}
62+
```
63+
5864
---
5965

6066
The `custom_id` is required to allow you to identify which individual batch request corresponds to a given response. Responses won't be returned in identical order to the order defined in the `.jsonl` batch file.

‎articles/ai-services/openai/includes/batch/batch-rest.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,12 @@ Like [fine-tuning](../../how-to/fine-tuning.md), global batch uses files in JSON
4444
{"custom_id": "request-1", "method": "POST", "url": "/chat/completions", "body": {"model": "REPLACE-WITH-MODEL-DEPLOYMENT-NAME", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": [{"type": "text", "text": "What’s in this image?"},{"type": "image_url","image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}],"max_tokens": 1000}}
4545
```
4646

47+
# [Structured outputs](#tab/structured-outputs)
48+
49+
```json
50+
{"custom_id": "task-0", "method": "POST", "url": "/chat/completions", "body": {"model": "REPLACE-WITH-MODEL-DEPLOYMENT-NAME", "messages": [{"role": "system", "content": "Extract the event information."}, {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}], "response_format": {"type": "json_schema", "json_schema": {"name": "CalendarEventResponse", "strict": true, "schema": {"type": "object", "properties": {"name": {"type": "string"}, "date": {"type": "string"}, "participants": {"type": "array", "items": {"type": "string"}}}, "required": ["name", "date", "participants"], "additionalProperties": false}}}}}
51+
```
52+
4753
---
4854

4955
The `custom_id` is required to allow you to identify which individual batch request corresponds to a given response. Responses won't be returned in identical order to the order defined in the `.jsonl` batch file.

‎articles/ai-services/openai/includes/batch/batch-studio.md

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,13 @@ Like [fine-tuning](../../how-to/fine-tuning.md), global batch uses files in JSON
4444
{"custom_id": "request-1", "method": "POST", "url": "/chat/completions", "body": {"model": "REPLACE-WITH-MODEL-DEPLOYMENT-NAME", "messages": [{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": [{"type": "text", "text": "What’s in this image?"},{"type": "image_url","image_url": {"url": "https://raw.githubusercontent.com/MicrosoftDocs/azure-docs/main/articles/ai-services/openai/media/how-to/generated-seattle.png"}}]}],"max_tokens": 1000}}
4545
```
4646

47+
# [Structured outputs](#tab/structured-outputs)
48+
49+
```json
50+
{"custom_id": "task-0", "method": "POST", "url": "/chat/completions", "body": {"model": "REPLACE-WITH-MODEL-DEPLOYMENT-NAME", "messages": [{"role": "system", "content": "Extract the event information."}, {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}], "response_format": {"type": "json_schema", "json_schema": {"name": "CalendarEventResponse", "strict": true, "schema": {"type": "object", "properties": {"name": {"type": "string"}, "date": {"type": "string"}, "participants": {"type": "array", "items": {"type": "string"}}}, "required": ["name", "date", "participants"], "additionalProperties": false}}}}}
51+
```
52+
53+
4754
---
4855

4956
The `custom_id` is required to allow you to identify which individual batch request corresponds to a given response. Responses won't be returned in identical order to the order defined in the `.jsonl` batch file.

‎articles/ai-studio/concepts/concept-model-distillation.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,8 @@ The main steps in knowledge distillation are:
3131

3232
## Sample notebook
3333

34-
You can use the [sample notebook](https://aka.ms/meta-llama-3.1-distillation) to see how to perform distillation. In this sample notebook, the teacher model uses the Meta Llama 3.1 405B instruction model, and the student model uses the Meta Llama 3.1 8B instruction model.
34+
You can use the [sample notebook](https://github.com/Azure/azureml-examples/tree/main/sdk/python/foundation-models/system/distillation) to see how to perform distillation. In this sample notebook, the teacher model uses the Meta Llama 3.1 405B instruction model, and the student model uses the Meta Llama 3.1 8B instruction model.
35+
3536

3637
We used an advanced prompt during synthetic data generation. The advanced prompt incorporates chain-of-thought (CoT) reasoning, which results in higher-accuracy data labels in the synthetic data. This labeling further improves the accuracy of the distilled model.
3738

‎articles/ai-studio/concepts/connections.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
title: Connections in Azure AI Studio
33
titleSuffix: Azure AI Studio
44
description: This article introduces connections in Azure AI Studio.
5-
manager: nitinme
5+
manager: scottpolly
66
ms.service: azure-ai-studio
77
ms.custom:
88
- ignite-2023

‎articles/ai-studio/concepts/fine-tuning-overview.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@
22
title: Fine-tuning in Azure AI Studio
33
titleSuffix: Azure AI Studio
44
description: This article introduces fine-tuning of models in Azure AI Studio.
5-
manager: nitinme
5+
manager: scottpolly
66
ms.service: azure-ai-studio
77
ms.custom:
88
- build-2024

0 commit comments

Comments
 (0)