Skip to content

Commit c8664f5

Browse files
prmerger-automator[bot]prmerger-automator[bot]
authored
Merge pull request #284690 from mrbullwinkle/mrb_08_14_2024_model_retirement
[Azure OpenAI] Evals + suggested models
2 parents aa9f3fa + 325a147 commit c8664f5

File tree

3 files changed

+45
-24
lines changed

3 files changed

+45
-24
lines changed

‎articles/ai-services/openai/concepts/model-retirements.md

Lines changed: 22 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
44
description: Learn about the model deprecations and retirements in Azure OpenAI.
55
ms.service: azure-ai-openai
66
ms.topic: conceptual
7-
ms.date: 08/08/2024
7+
ms.date: 08/14/2024
88
ms.custom:
99
manager: nitinme
1010
author: mrbullwinkle
@@ -74,9 +74,11 @@ Azure OpenAI notifies those who are members of the following roles for each subs
7474

7575
## How to get ready for model retirements and version upgrades
7676

77-
To prepare for model retirements and version upgrades, we recommend that customers evaluate their applications with the new models and versions and evaluate their behavior. We also recommend that customers update their applications to use the new models and versions before the retirement date.
77+
To prepare for model retirements and version upgrades, we recommend that customers test their applications with the new models and versions and evaluate their behavior. We also recommend that customers update their applications to use the new models and versions before the retirement date.
7878

79-
For more information, see [How to upgrade to a new model or version](./model-versions.md).
79+
For more information on the model evaluation process, see the [Getting started with model evaluation guide](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/how-to-evaluate-amp-upgrade-model-versions-in-the-azure-openai/ba-p/4218880).
80+
81+
For information on the model upgrade process, see [How to upgrade to a new model or version](./model-versions.md).
8082

8183
## Current models
8284

@@ -87,22 +89,22 @@ For more information, see [How to upgrade to a new model or version](./model-ver
8789
8890
These models are currently available for use in Azure OpenAI Service.
8991

90-
| Model | Version | Retirement date |
91-
| ---- | ---- | ---- |
92-
| `gpt-35-turbo` | 0301 | No earlier than October 1, 2024 |
93-
| `gpt-35-turbo`<br>`gpt-35-turbo-16k` | 0613 | November 1, 2024 |
94-
| `gpt-35-turbo` | 1106 | No earlier than Nov 17, 2024 |
95-
| `gpt-35-turbo` | 0125 | No earlier than Feb 22, 2025 |
96-
| `gpt-4`<br>`gpt-4-32k` | 0314 | **Deprecation:** October 1, 2024 <br> **Retirement:** June 6, 2025 |
97-
| `gpt-4`<br>`gpt-4-32k` | 0613 | **Deprecation:** October 1, 2024 <br> **Retirement:** June 6, 2025 |
98-
| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` Version: `turbo-2024-04-09`, starting on November 15, 2024, or later **<sup>1</sup>** |
99-
| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` Version: `turbo-2024-04-09`, starting on November 15, 2024, or later **<sup>1</sup>** |
100-
| `gpt-4` | vision-preview | To be upgraded to `gpt-4` Version: `turbo-2024-04-09`, starting on November 15, 2024, or later **<sup>1</sup>** |
101-
| `gpt-3.5-turbo-instruct` | 0914 | No earlier than Sep 14, 2025 |
102-
| `text-embedding-ada-002` | 2 | No earlier than April 3, 2025 |
103-
| `text-embedding-ada-002` | 1 | No earlier than April 3, 2025 |
104-
| `text-embedding-3-small` | | No earlier than Feb 2, 2025 |
105-
| `text-embedding-3-large` | | No earlier than Feb 2, 2025 |
92+
| Model | Version | Retirement date | Suggested replacement |
93+
| ---- | ---- | ---- | --- |
94+
| `gpt-35-turbo` | 0301 | No earlier than October 1, 2024 | `gpt-4o-mini` |
95+
| `gpt-35-turbo`<br>`gpt-35-turbo-16k` | 0613 | November 1, 2024 | `gpt-4o-mini` |
96+
| `gpt-35-turbo` | 1106 | No earlier than Nov 17, 2024 | `gpt-4o-mini` |
97+
| `gpt-35-turbo` | 0125 | No earlier than Feb 22, 2025 | `gpt-4o-mini` |
98+
| `gpt-4`<br>`gpt-4-32k` | 0314 | **Deprecation:** October 1, 2024 <br> **Retirement:** June 6, 2025 | `gpt-4o` |
99+
| `gpt-4`<br>`gpt-4-32k` | 0613 | **Deprecation:** October 1, 2024 <br> **Retirement:** June 6, 2025 | `gpt-4o` |
100+
| `gpt-4` | 1106-preview | To be upgraded to `gpt-4` Version: `turbo-2024-04-09`, starting on November 15, 2024, or later **<sup>1</sup>** | `gpt-4o`|
101+
| `gpt-4` | 0125-preview |To be upgraded to `gpt-4` Version: `turbo-2024-04-09`, starting on November 15, 2024, or later **<sup>1</sup>** | `gpt-4o` |
102+
| `gpt-4` | vision-preview | To be upgraded to `gpt-4` Version: `turbo-2024-04-09`, starting on November 15, 2024, or later **<sup>1</sup>** | `gpt-4o`|
103+
| `gpt-3.5-turbo-instruct` | 0914 | No earlier than Sep 14, 2025 | |
104+
| `text-embedding-ada-002` | 2 | No earlier than April 3, 2025 | `text-embedding-3-small` or `text-embedding-3-large` |
105+
| `text-embedding-ada-002` | 1 | No earlier than April 3, 2025 | `text-embedding-3-small` or `text-embedding-3-large` |
106+
| `text-embedding-3-small` | | No earlier than Feb 2, 2025 | |
107+
| `text-embedding-3-large` | | No earlier than Feb 2, 2025 | |
106108

107109
**<sup>1</sup>** We will notify all customers with these preview deployments at least 30 days before the start of the upgrades. We will publish an upgrade schedule detailing the order of regions and model versions that we will follow during the upgrades, and link to that schedule from here.
108110

@@ -114,7 +116,7 @@ These models were deprecated on July 6, 2023 and were retired on June 14, 2024.
114116
If you're an existing customer looking for information about these models, see [Legacy models](./legacy-models.md).
115117

116118
| Model | Deprecation date | Retirement date | Suggested replacement |
117-
| --------- | --------------------- | ------------------- | -------------------- |
119+
| --------- | --------------------- | ------------------- | -------------------- |
118120
| ada | July 6, 2023 | June 14, 2024 | babbage-002 |
119121
| babbage | July 6, 2023 | June 14, 2024 | babbage-002 |
120122
| curie | July 6, 2023 | June 14, 2024 | davinci-002 |

‎articles/ai-services/openai/overview.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ author: mrbullwinkle
77
ms.author: mbullwin
88
ms.service: azure-ai-openai
99
ms.topic: overview
10-
ms.date: 08/06/2024
10+
ms.date: 08/14/2024
1111
ms.custom: build-2023, build-2023-dataai
1212
recommendations: false
1313
---
@@ -20,8 +20,8 @@ Azure OpenAI Service provides REST API access to OpenAI's powerful language mode
2020

2121
| Feature | Azure OpenAI |
2222
| --- | --- |
23-
| Models available | **GPT-4o**<br> **GPT-4 series (including GPT-4 Turbo with Vision)** <br>**GPT-3.5-Turbo series**<br> Embeddings series <br> Learn more in our [Models](./concepts/models.md) page.|
24-
| Fine-tuning | `GPT-4` (preview) <br>`GPT-3.5-Turbo` (0613) <br> `babbage-002` <br> `davinci-002`.|
23+
| Models available | **GPT-4o & GPT-4o mini**<br> **GPT-4 series (including GPT-4 Turbo with Vision)** <br>**GPT-3.5-Turbo series**<br> Embeddings series <br> Learn more in our [Models](./concepts/models.md) page.|
24+
| Fine-tuning | `GPT-4o-mini` (preview) <br> `GPT-4` (preview) <br>`GPT-3.5-Turbo` (0613) <br> `babbage-002` <br> `davinci-002`.|
2525
| Price | [Available here](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) <br> For details on GPT-4 Turbo with Vision, see the [special pricing information](../openai/concepts/gpt-with-vision.md#special-pricing-information).|
2626
| Virtual network support & private link support | Yes, unless using [Azure OpenAI on your data](./concepts/use-your-data.md). |
2727
| Managed Identity| Yes, via Microsoft Entra ID |

‎articles/ai-services/openai/whats-new.md

Lines changed: 20 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,7 +10,7 @@ ms.custom:
1010
- ignite-2023
1111
- references_regions
1212
ms.topic: whats-new
13-
ms.date: 08/06/2024
13+
ms.date: 08/14/2024
1414
recommendations: false
1515
---
1616

@@ -20,6 +20,25 @@ This article provides a summary of the latest releases and major documentation u
2020

2121
## August 2024
2222

23+
### New preview API release
24+
25+
API version `2024-07-01-preview` is the latest dataplane authoring & inference API release. It replaces API version `2024-05-01-preview` and adds support for:
26+
27+
- [Batch API support added](./how-to/batch.md)
28+
- [Vector store chunking strategy parameters](/azure/ai-services/openai/reference-preview?#request-body-17)
29+
- `max_num_results` that the file search tool should output.
30+
31+
For more information see our [reference documentation](./reference-preview.md)
32+
33+
### GPT-4o mini regional availability
34+
35+
- GPT-4o mini is available for standard and global standard deployment in the East US and Sweden Central regions.
36+
- GPT-4o mini is available for global batch deployment in East US, Sweden Central, and West US regions.
37+
38+
### Evaluations guide
39+
40+
- New blog post on [getting started with model evaluations](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/how-to-evaluate-amp-upgrade-model-versions-in-the-azure-openai/ba-p/4218880). We recommend using this guide as part of the [model upgrade and retirement process](./concepts/model-retirements.md).
41+
2342
### Latest GPT-4o model available in the early access playground (preview)
2443

2544
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:

0 commit comments

Comments
 (0)