Skip to content

Commit

Permalink
Merge pull request #35 from MicrosoftDocs/release-2024-openai-aug
Browse files Browse the repository at this point in the history
[Azure OpenAI] [Release branch to main tracking PR]
  • Loading branch information
Albertyang0 authored Sep 3, 2024
2 parents 810cdc8 + 60323ec commit 413694e
Show file tree
Hide file tree
Showing 4 changed files with 767 additions and 22 deletions.
35 changes: 15 additions & 20 deletions articles/ai-services/openai/concepts/models.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
description: Learn about the different model capabilities that are available with Azure OpenAI.
ms.service: azure-ai-openai
ms.topic: conceptual
ms.date: 08/14/2024
ms.date: 08/28/2024
ms.custom: references_regions, build-2023, build-2023-dataai, refefences_regions
manager: nitinme
author: mrbullwinkle #ChrisHMSFT
Expand All @@ -26,24 +26,6 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
| [Whisper](#whisper-models) | A series of models in preview that can transcribe and translate speech to text. |
| [Text to speech](#text-to-speech-models-preview) (Preview) | A series of models in preview that can synthesize text to speech. |

## Early access playground (preview)

On August 6, 2024, OpenAI [announced](https://openai.com/index/introducing-structured-outputs-in-the-api/) the latest version of their flagship GPT-4o model version `2024-08-06`. GPT-4o `2024-08-06` has all the capabilities of the previous version as well as:

* An enhanced ability to support complex structured outputs.
* Max output tokens have been increased from 4,096 to 16,384.

Azure customers can test out GPT-4o `2024-08-06` today in the new AI Studio early access playground (preview).

Unlike the previous early access playground, the AI Studio early access playground (preview) does not require you to have a resource in a specific region.

> [!NOTE]
> Prompts and completions made through the early access playground (preview) may be processed in any Azure OpenAI region, and are currently subject to a 10 request per minute per Azure subscription limit. This limit may change in the future.
>
> Azure OpenAI Service abuse monitoring is enabled for all early access playground users even if approved for modification; default content filters are enabled and cannot be modified.
To test out GPT-4o `2024-08-06`, sign-in to the Azure AI early access playground (preview) using this [link](https://aka.ms/oai/docs/earlyaccessplayground).

## GPT-4o and GPT-4 Turbo

GPT-4o integrates text and images in a single model, enabling it to handle multiple data types simultaneously. This multimodal approach enhances accuracy and responsiveness in human-computer interactions. GPT-4o matches GPT-4 Turbo in English text and coding tasks while offering superior performance in non-English languages and vision tasks, setting new benchmarks for AI capabilities.
Expand All @@ -56,6 +38,7 @@ You need to [create](../how-to/create-resource.md) or use an existing resource i

When your resource is created, you can [deploy](../how-to/create-resource.md#deploy-a-model) the GPT-4o models. If you are performing a programmatic deployment, the **model** names are:

- `gpt-4o` **Version** `2024-08-06`
- `gpt-4o`, **Version** `2024-05-13`
- `gpt-4o-mini` **Version** `2024-07-18`

Expand Down Expand Up @@ -83,8 +66,9 @@ See [model versions](../concepts/model-versions.md) to learn about how Azure Ope

| Model ID | Description | Max Request (tokens) | Training Data (up to) |
| --- | :--- |:--- |:---: |
|`gpt-4o` (2024-08-06) <br> **GPT-4o (Omni)** | **Latest large GA model** <br> - Structured outputs<br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 4,096| Oct 2023 |
|`gpt-4o-mini` (2024-07-18) <br> **GPT-4o mini** | **Latest small GA model** <br> - Fast, inexpensive, capable model ideal for replacing GPT-3.5 Turbo series models. <br> - Text, image processing <br>- JSON Mode <br> - parallel function calling | Input: 128,000 <br> Output: 16,384 | Oct 2023 |
|`gpt-4o` (2024-05-13) <br> **GPT-4o (Omni)** | **Latest large GA model** <br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 4,096| Oct 2023 |
|`gpt-4o` (2024-05-13) <br> **GPT-4o (Omni)** | Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks |Input: 128,000 <br> Output: 4,096| Oct 2023 |
| `gpt-4` (turbo-2024-04-09) <br>**GPT-4 Turbo with Vision** | **New GA model** <br> - Replacement for all previous GPT-4 preview models (`vision-preview`, `1106-Preview`, `0125-Preview`). <br> - [**Feature availability**](#gpt-4o-and-gpt-4-turbo) is currently different depending on method of input, and deployment type. | Input: 128,000 <br> Output: 4,096 | Dec 2023 |
| `gpt-4` (0125-Preview)*<br>**GPT-4 Turbo Preview** | **Preview Model** <br> -Replaces 1106-Preview <br>- Better code generation performance <br> - Reduces cases where the model doesn't complete a task <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) | Input: 128,000 <br> Output: 4,096 | Dec 2023 |
| `gpt-4` (vision-preview)<br>**GPT-4 Turbo with Vision Preview** | **Preview model** <br> - Accepts text and image input. <br> - Supports enhancements <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) | Input: 128,000 <br> Output: 4,096 | Apr 2023 |
Expand Down Expand Up @@ -188,6 +172,17 @@ For more information on Provisioned deployments, see our [Provisioned guidance](

### Global standard model availability

`gpt-4o` **Version:** `2024-08-06`

**Supported regions:**
- eastus
- eastus2
- northcentralus
- southcentralus
- swedencentral
- westus
- westus3

`gpt-4o` **Version:** `2024-05-13`

**Supported regions:**
Expand Down
9 changes: 7 additions & 2 deletions articles/ai-services/openai/how-to/json-mode.md
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ services: cognitive-services
manager: nitinme
ms.service: azure-ai-openai
ms.topic: how-to
ms.date: 12/05/2023
ms.date: 08/29/2024
author: mrbullwinkle
ms.author: mbullwin
recommendations: false
Expand All @@ -17,6 +17,9 @@ recommendations: false

JSON mode allows you to set the models response format to return a valid JSON object as part of a chat completion. While generating valid JSON was possible previously, there could be issues with response consistency that would lead to invalid JSON objects being generated.

> [!NOTE]
> While JSON mode is still supported, when possible we recommend using [structured outputs](./structured-outputs.md). Like JSON mode structured outputs generates valid JSON, but with the added benefit that you can constrain the model to use a specific JSON schema.
## JSON mode support

JSON mode is only currently supported with the following models:
Expand All @@ -27,6 +30,8 @@ JSON mode is only currently supported with the following models:
* `gpt-35-turbo` (0125)
* `gpt-4` (1106-Preview)
* `gpt-4` (0125-Preview)
* `gpt-4o`
* `gpt-4o-mini`

### API support

Expand All @@ -47,7 +52,7 @@ client = AzureOpenAI(
)

response = client.chat.completions.create(
model="gpt-4-0125-Preview", # Model = should match the deployment name you chose for your 0125-Preview model deployment
model="YOUR-MODEL_DEPLOYMENT_NAME", # Model = should match the deployment name you chose for your model deployment
response_format={ "type": "json_object" },
messages=[
{"role": "system", "content": "You are a helpful assistant designed to output JSON."},
Expand Down
Loading

0 comments on commit 413694e

Please sign in to comment.