Skip to content

Commit 71adf7f

Browse files
TaojunshenTaojunshen
authored
Merge pull request #3332 from MicrosoftDocs/main
3/4/2025 PM Publish
2 parents 077b6fb + 09c094b commit 71adf7f

28 files changed

+284
-274
lines changed

‎articles/ai-foundry/how-to/deploy-models-jais.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: Learn how to use Jais chat models with Azure AI Foundry.
55
ms.service: azure-ai-foundry
66
manager: scottpolly
77
ms.topic: how-to
8-
ms.date: 11/21/2024
8+
ms.date: 03/04/2025
99
ms.reviewer: haelhamm
1010
reviewer: hazemelh
1111
ms.author: ssalgado

‎articles/ai-foundry/how-to/deploy-models-jamba.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: How to deploy AI21's Jamba family models with Azure AI Foundry
55
manager: scottpolly
66
ms.service: azure-ai-foundry
77
ms.topic: how-to
8-
ms.date: 08/06/2024
8+
ms.date: 03/04/2025
99
ms.author: ssalgado
1010
author: ssalgadodev
1111
ms.reviewer: tgokal

‎articles/ai-foundry/how-to/deploy-models-llama.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: Learn how to use the Meta Llama family of models with Azure AI Foun
55
ms.service: azure-ai-foundry
66
manager: scottpolly
77
ms.topic: how-to
8-
ms.date: 12/04/2024
8+
ms.date: 03/04/2025
99
ms.reviewer: shubhiraj
1010
reviewer: shubhirajMsft
1111
ms.author: ssalgado

‎articles/ai-foundry/how-to/deploy-models-tsuzumi.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: Learn how to use tsuzumi-7b models with Azure AI Foundry.
55
ms.service: azure-ai-foundry
66
manager: scottpolly
77
ms.topic: how-to
8-
ms.date: 10/24/2024
8+
ms.date: 03/04/2025
99
ms.reviewer: haelhamm
1010
reviewer: hazemelh
1111
ms.author: ssalgado

‎articles/ai-services/agents/includes/quickstart-javascript.md

Lines changed: 21 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -31,11 +31,18 @@ ms.custom: devx-track-js
3131
| Run | Activation of an agent to begin running based on the contents of Thread. The agent uses its configuration and Thread’s Messages to perform tasks by calling models and tools. As part of a Run, the agent appends Messages to the Thread. |
3232
| Run Step | A detailed list of steps the agent took as part of a Run. An agent can call tools or create Messages during its run. Examining Run Steps allows you to understand how the agent is getting to its results. |
3333

34-
Run the following commands to install the npm packages.
34+
First, initialize a new project by running:
35+
36+
```console
37+
npm init -y
38+
```
39+
40+
Run the following commands to install the npm packages required.
3541

3642
```console
3743
npm install @azure/ai-projects
3844
npm install @azure/identity
45+
npm install dotenv
3946
```
4047

4148
Next, to authenticate your API requests and run the program, use the [az login](/cli/azure/authenticate-azure-cli-interactively) command to sign into your Azure subscription.
@@ -60,7 +67,9 @@ For example, your connection string may look something like:
6067

6168
`eastus.api.azureml.ms;12345678-abcd-1234-9fc6-62780b3d3e05;my-resource-group;my-project-name`
6269

63-
Set this connection string as an environment variable named `PROJECT_CONNECTION_STRING`.
70+
Set this connection string as an environment variable named `PROJECT_CONNECTION_STRING` in a `.env` file.
71+
72+
Next, create an `index.js` file and paste in the code below:
6473

6574
```javascript
6675
// index.js
@@ -75,12 +84,16 @@ import {
7584
ToolUtility,
7685
} from "@azure/ai-projects";
7786
import { DefaultAzureCredential } from "@azure/identity";
87+
import dotenv from 'dotenv';
88+
89+
dotenv.config();
7890

79-
const connectionString =
80-
process.env["AZURE_AI_PROJECTS_CONNECTION_STRING"] || "<project connection string>";
91+
// Set the connection string from the environment variable
92+
const connectionString = process.env.PROJECT_CONNECTION_STRING;
8193

94+
// Throw an error if the connection string is not set
8295
if (!connectionString) {
83-
throw new Error("AZURE_AI_PROJECTS_CONNECTION_STRING must be set in the environment variables");
96+
throw new Error("Please set the PROJECT_CONNECTION_STRING environment variable.");
8497
}
8598

8699
export async function main() {
@@ -149,7 +162,7 @@ export async function main() {
149162
// messages[0] is the most recent
150163
for (let i = messages.data.length - 1; i >= 0; i--) {
151164
const m = messages.data[i];
152-
if (isOutputOfType(m.content[0], "text")) {
165+
if (m.content && m.content.length > 0 && isOutputOfType(m.content[0], "text")) {
153166
const textContent = m.content[0];
154167
console.log(`${textContent.text.value}`);
155168
console.log(`---------------------------------`);
@@ -164,3 +177,5 @@ main().catch((err) => {
164177
console.error("The sample encountered an error:", err);
165178
});
166179
```
180+
181+
Run the code using `node index.js` and observe.

‎articles/ai-services/openai/concepts/provisioned-throughput.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -48,14 +48,14 @@ The amount of throughput (tokens per minute or TPM) a deployment gets per PTU is
4848

4949
To help with simplifying the sizing effort, the following table outlines the TPM per PTU for the specified models. To understand the impact of output tokens on the TPM per PTU limit, use the 3 input token to 1 output token ratio. For a detailed understanding of how different ratios of input and output tokens impact the throughput your workload needs, see the [Azure OpenAI capacity calculator](https://oai.azure.com/portal/calculator). The table also shows Service Level Agreement (SLA) Latency Target Values per model. For more information about the SLA for Azure OpenAI Service, see the [Service Level Agreements (SLA) for Online Services page](https://www.microsoft.com/licensing/docs/view/Service-Level-Agreements-SLA-for-Online-Services?lang=1)
5050

51-
|Topic| **gpt-4o** | **gpt-4o-mini** |
52-
| --- | --- | --- |
53-
|Global & data zone provisioned minimum deployment|15|15|
54-
|Global & data zone provisioned scale increment|5|5|
55-
|Regional provisioned minimum deployment | 50 | 25|
56-
|Regional provisioned scale increment|50|25|
57-
|Input TPM per PTU | 2,500 | 37,000 |
58-
|Latency Target Value |25 Tokens Per Second|33 Tokens Per Second|
51+
|Topic| **gpt-4o** | **gpt-4o-mini** | **o1**|
52+
| --- | --- | --- | --- |
53+
|Global & data zone provisioned minimum deployment|15|15|15|
54+
|Global & data zone provisioned scale increment|5|5|5|
55+
|Regional provisioned minimum deployment|50|25|50|
56+
|Regional provisioned scale increment|50|25|50|
57+
|Input TPM per PTU |2,500|37,000|230|
58+
|Latency Target Value |25 Tokens Per Second|33 Tokens Per Second|25 Tokens Per Second|
5959

6060
For a full list see the [Azure OpenAI Service in Azure AI Foundry portal calculator](https://oai.azure.com/portal/calculator).
6161

‎articles/ai-services/openai/how-to/fine-tuning-deploy.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -378,7 +378,7 @@ Azure OpenAI fine-tuning supports the following deployment types.
378378

379379
:::image type="content" source="../media/fine-tuning/global-standard.png" alt-text="Screenshot of the global standard deployment user experience with a fine-tuned model." lightbox="../media/fine-tuning/global-standard.png":::
380380

381-
Global Standard fine-tuning deployments currently do not support vision and structured outputs.
381+
Global Standard fine-tuned deployments currently support structured outputs only on GPT-4o.
382382

383383
### Provisioned Managed (preview)
384384

@@ -392,7 +392,7 @@ Global Standard fine-tuning deployments currently do not support vision and stru
392392

393393
[Provisioned managed](./deployment-types.md#provisioned) fine-tuned deployments offer [predictable performance](../concepts/provisioned-throughput.md#what-do-the-provisioned-deployment-types-provide) for fine-tuned deployments. As part of public preview, provisioned managed deployments may be created regionally via the data-plane [REST API](../reference.md#data-plane-inference) version `2024-10-01` or newer. See below for examples.
394394

395-
Provisioned Managed fine-tuning deployments currently do not support vision and structured outputs.
395+
Provisioned Managed fine-tuned deployments currently support structured outputs only on GPT-4o.
396396

397397
#### Creating a Provisioned Managed deployment
398398

‎articles/ai-services/openai/how-to/fine-tuning-vision.md

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -16,6 +16,10 @@ ms.author: mbullwin
1616

1717
Fine-tuning is also possible with images in your JSONL files. Just as you can send one or many image inputs to chat completions, you can include those same message types within your training data. Images can be provided either as publicly accessible URLs or data URIs containing [base64 encoded images](/azure/ai-services/openai/how-to/gpt-with-vision?tabs=rest#call-the-chat-completion-apis).
1818

19+
## Model support
20+
21+
Vision fine-tuning is supported for `gpt-4o` version `2024-08-06` models only.
22+
1923
## Image dataset requirements
2024

2125
- Your training file can contain a maximum of 50,000 examples that contain images (not including text examples).

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

Lines changed: 30 additions & 28 deletions
Original file line numberDiff line numberDiff line change
@@ -6,33 +6,35 @@ manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: include
88
ms.custom: references_regions
9-
ms.date: 02/06/2025
9+
ms.date: 03/04/2025
1010
---
1111

12-
| **Region** | **gpt-4o**, **2024-05-13** | **gpt-4o**, **2024-08-06** | **gpt-4o**, **2024-11-20** | **gpt-4o-mini**, **2024-07-18** |
13-
|:-------------------|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|
14-
| australiaeast | ✅ | ✅ | ✅ | ✅ |
15-
| brazilsouth | ✅ | ✅ | ✅ | ✅ |
16-
| canadacentral | ✅ | ✅ | ✅ | ✅ |
17-
| canadaeast | ✅ | ✅ | ✅ | ✅ |
18-
| eastus | ✅ | ✅ | ✅ | ✅ |
19-
| eastus2 | ✅ | ✅ | ✅ | ✅ |
20-
| francecentral | ✅ | ✅ | ✅ | ✅ |
21-
| germanywestcentral | ✅ | ✅ | ✅ | ✅ |
22-
| japaneast | ✅ | ✅ | ✅ | ✅ |
23-
| koreacentral | ✅ | ✅ | ✅ | ✅ |
24-
| northcentralus | ✅ | ✅ | ✅ | ✅ |
25-
| norwayeast | ✅ | ✅ | ✅ | ✅ |
26-
| polandcentral | ✅ | ✅ | ✅ | ✅ |
27-
| southafricanorth | ✅ | ✅ | ✅ | ✅ |
28-
| southcentralus | ✅ | ✅ | ✅ | ✅ |
29-
| southeastasia | ✅ | ✅ | ✅ | ✅ |
30-
| southindia | ✅ | ✅ | ✅ | ✅ |
31-
| swedencentral | ✅ | ✅ | ✅ | ✅ |
32-
| switzerlandnorth | ✅ | ✅ | ✅ | ✅ |
33-
| switzerlandwest | ✅ | ✅ | ✅ | ✅ |
34-
| uaenorth | ✅ | ✅ | ✅ | ✅ |
35-
| uksouth | ✅ | ✅ | ✅ | ✅ |
36-
| westeurope | ✅ | ✅ | ✅ | ✅ |
37-
| westus | ✅ | ✅ | ✅ | ✅ |
38-
| westus3 | ✅ | ✅ | ✅ | ✅ |
12+
| **Region** | **o1**, **2024-12-17** | **gpt-4o**, **2024-05-13** | **gpt-4o**, **2024-08-06** | **gpt-4o**, **2024-11-20** | **gpt-4o-mini**, **2024-07-18** |
13+
|:-------------------|:----------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|
14+
| australiaeast | - | ✅ | ✅ | ✅ | ✅ |
15+
| brazilsouth | - | ✅ | ✅ | ✅ | ✅ |
16+
| canadacentral | - | ✅ | ✅ | ✅ | ✅ |
17+
| canadaeast | - | ✅ | ✅ | ✅ | ✅ |
18+
| eastus | ✅ | ✅ | ✅ | ✅ | ✅ |
19+
| eastus2 | - | ✅ | ✅ | ✅ | ✅ |
20+
| francecentral | ✅ | ✅ | ✅ | ✅ | ✅ |
21+
| germanywestcentral | - | ✅ | ✅ | ✅ | ✅ |
22+
| italynorth | - | ✅ | ✅ | ✅ | ✅ |
23+
| japaneast | - | ✅ | ✅ | ✅ | ✅ |
24+
| koreacentral | - | ✅ | ✅ | ✅ | ✅ |
25+
| northcentralus | - | ✅ | ✅ | ✅ | ✅ |
26+
| norwayeast | - | ✅ | ✅ | ✅ | ✅ |
27+
| polandcentral | - | ✅ | ✅ | ✅ | ✅ |
28+
| southafricanorth | ✅ | ✅ | ✅ | ✅ | ✅ |
29+
| southcentralus | ✅ | ✅ | ✅ | ✅ | ✅ |
30+
| southeastasia | - | ✅ | ✅ | ✅ | ✅ |
31+
| southindia | ✅ | ✅ | ✅ | ✅ | ✅ |
32+
| spaincentral | ✅ | ✅ | ✅ | ✅ | ✅ |
33+
| swedencentral | ✅ | ✅ | ✅ | ✅ | ✅ |
34+
| switzerlandnorth | ✅ | ✅ | ✅ | ✅ | ✅ |
35+
| switzerlandwest | ✅ | ✅ | ✅ | ✅ | ✅ |
36+
| uaenorth | - | ✅ | ✅ | ✅ | ✅ |
37+
| uksouth | ✅ | ✅ | ✅ | ✅ | ✅ |
38+
| westeurope | ✅ | ✅ | ✅ | ✅ | ✅ |
39+
| westus | ✅ | ✅ | ✅ | ✅ | ✅ |
40+
| westus3 | ✅ | ✅ | ✅ | ✅ | ✅ |

‎articles/ai-services/openai/quotas-limits.md

Lines changed: 9 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: conceptual
13-
ms.date: 2/27/2025
13+
ms.date: 3/04/2025
1414
ms.author: mbullwin
1515
---
1616

@@ -94,6 +94,14 @@ The following sections provide you with a quick guide to the default quotas and
9494
| `o1` & `o1-preview` | Default | 3 M | 500 |
9595
| `o1-mini`| Default | 5 M | 500 |
9696

97+
### `o3-mini` data zone standard
98+
99+
| Model|Tier| Quota Limit in tokens per minute (TPM) | Requests per minute |
100+
|---|---|:---:|:---:|
101+
| `o3-mini` | Enterprise agreement | 20 M | 2 K |
102+
| `o3-mini` | Default | 2 M | 200 |
103+
104+
97105
### o1-preview & o1-mini standard
98106

99107
| Model|Tier| Quota Limit in tokens per minute (TPM) | Requests per minute |

0 commit comments

Comments
 (0)