Skip to content

Commit fcdfea2

Browse files
authored
Merge pull request #3567 from MicrosoftDocs/main
3/17/2025 AM Publish
2 parents 6e505af + f1f5aad commit fcdfea2

15 files changed

+44
-59
lines changed

articles/ai-foundry/how-to/develop/connections-add-sdk.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -8,7 +8,7 @@ ms.custom:
88
- build-2024
99
- ignite-2024
1010
ms.topic: how-to
11-
ms.date: 12/05/2024
11+
ms.date: 03/17/2025
1212
ms.reviewer: dantaylo
1313
ms.author: larryfr
1414
author: Blackmist
-68.6 KB
Loading

articles/ai-foundry/model-inference/includes/use-image-embeddings/python.md

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ author: msakande
77
reviewer: santiagxf
88
ms.service: azure-ai-model-inference
99
ms.topic: how-to
10-
ms.date: 01/22/2025
10+
ms.date: 03/17/2025
1111
ms.author: mopeakande
1212
ms.reviewer: fasantia
1313
ms.custom: generated
@@ -41,7 +41,7 @@ import os
4141
from azure.ai.inference import ImageEmbeddingsClient
4242
from azure.core.credentials import AzureKeyCredential
4343

44-
model = ImageEmbeddingsClient(
44+
client = ImageEmbeddingsClient(
4545
endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
4646
credential=AzureKeyCredential(os.environ["AZURE_INFERENCE_CREDENTIAL"]),
4747
model="Cohere-embed-v3-english"
@@ -55,7 +55,7 @@ import os
5555
from azure.ai.inference import ImageEmbeddingsClient
5656
from azure.identity import DefaultAzureCredential
5757

58-
model = ImageEmbeddingsClient(
58+
client = ImageEmbeddingsClient(
5959
endpoint=os.environ["AZURE_INFERENCE_ENDPOINT"],
6060
credential=DefaultAzureCredential(),
6161
model="Cohere-embed-v3-english"
@@ -70,7 +70,7 @@ To create image embeddings, you need to pass the image data as part of your requ
7070
from azure.ai.inference.models import ImageEmbeddingInput
7171

7272
image_input= ImageEmbeddingInput.load(image_file="sample1.png", image_format="png")
73-
response = model.embed(
73+
response = client.embed(
7474
input=[ image_input ],
7575
)
7676
```
@@ -102,7 +102,7 @@ Some models can generate embeddings from images and text pairs. In this case, yo
102102
```python
103103
text_image_input= ImageEmbeddingInput.load(image_file="sample1.png", image_format="png")
104104
text_image_input.text = "A cute baby sea otter"
105-
response = model.embed(
105+
response = client.embed(
106106
input=[ text_image_input ],
107107
)
108108
```
@@ -117,7 +117,7 @@ The following example shows how to create embeddings that are used to create an
117117
```python
118118
from azure.ai.inference.models import EmbeddingInputType
119119

120-
response = model.embed(
120+
response = client.embed(
121121
input=[ image_input ],
122122
input_type=EmbeddingInputType.DOCUMENT,
123123
)
@@ -129,7 +129,7 @@ When you work on a query to retrieve such a document, you can use the following
129129
```python
130130
from azure.ai.inference.models import EmbeddingInputType
131131

132-
response = model.embed(
132+
response = client.embed(
133133
input=[ image_input ],
134134
input_type=EmbeddingInputType.QUERY,
135135
)

articles/ai-foundry/model-inference/overview.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -37,9 +37,9 @@ To see details for each model including, language, types, and capabilities, see
3737
| [Azure OpenAI](concepts/models.md#azure-openai) | - o3-mini <br /> - o1 <br /> - gpt-4o <br /> - o1-preview <br /> - o1-mini <br /> - gpt-4o-mini <br /> - text-embedding-3-large <br /> - text-embedding-3-small <br /> |
3838
| [Cohere](concepts/models.md#cohere) | - Cohere-embed-v3-english <br /> - Cohere-embed-v3-multilingual <br /> - Cohere-command-r-plus-08-2024 <br /> - Cohere-command-r-08-2024 <br /> - Cohere-command-r-plus <br /> - Cohere-command-r <br /> |
3939
| [Core42](concepts/models.md#core42) | - jais-30b-chat <br /> |
40-
| [DeepSeek](concepts/models.md#deepseek) | - DeepSeek-R1 |
40+
| [DeepSeek](concepts/models.md#deepseek) | - DeepSeek-V3 <br /> - DeepSeek-R1 <br /> |
4141
| [Meta](concepts/models.md#meta) | - Llama-3.3-70B-Instruct <br /> - Llama-3.2-11B-Vision-Instruct <br /> - Llama-3.2-90B-Vision-Instruct <br /> - Meta-Llama-3.1-405B-Instruct <br /> - Meta-Llama-3-8B-Instruct <br /> - Meta-Llama-3.1-70B-Instruct <br /> - Meta-Llama-3.1-8B-Instruct <br /> - Meta-Llama-3-70B-Instruct <br /> |
42-
| [Microsoft](concepts/models.md#microsoft) | - Phi-3-mini-128k-instruct <br /> - Phi-3-mini-4k-instruct <br /> - Phi-3-small-8k-instruct <br /> - Phi-3-medium-128k-instruct <br /> - Phi-3-medium-4k-instruct <br /> - Phi-3.5-vision-instruct <br /> - Phi-3.5-MoE-instruct <br /> - Phi-3-small-128k-instruct <br /> - Phi-3.5-mini-instruct <br /> - Phi-4 <br /> |
42+
| [Microsoft](concepts/models.md#microsoft) | - Phi-4-multimodal-instruct <br /> - Phi-4-mini-instruct <br /> - Phi-4 <br /> - Phi-3-mini-128k-instruct <br /> - Phi-3-mini-4k-instruct <br /> - Phi-3-small-8k-instruct <br /> - Phi-3-medium-128k-instruct <br /> - Phi-3-medium-4k-instruct <br /> - Phi-3.5-vision-instruct <br /> - Phi-3.5-MoE-instruct <br /> - Phi-3-small-128k-instruct <br /> - Phi-3.5-mini-instruct <br /> |
4343
| [Mistral AI](concepts/models.md#mistral-ai) | - Ministral-3B <br /> - Mistral-large <br /> - Mistral-small <br /> - Mistral-Nemo <br /> - Mistral-large-2407 <br /> - Mistral-Large-2411 <br /> - Codestral-2501 <br /> |
4444
| [NTT Data](concepts/models.md#ntt-data) | - Tsuzumi-7b |
4545

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

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@ deploy_data = {
5656
"properties": {
5757
"model": {
5858
"format": "OpenAI",
59-
"name": <"fine_tuned_model">, #retrieve this value from the previous call, it will look like gpt-35-turbo-0613.ft-b044a9d3cf9c4228b5d393567f693b83
59+
"name": <"fine_tuned_model">, #retrieve this value from the previous call, it will look like gpt-35-turbo-0125.ft-b044a9d3cf9c4228b5d393567f693b83
6060
"version": "1"
6161
}
6262
}
@@ -82,7 +82,7 @@ print(r.json())
8282
| resource_group | The resource group name for your Azure OpenAI resource. |
8383
| resource_name | The Azure OpenAI resource name. |
8484
| model_deployment_name | The custom name for your new fine-tuned model deployment. This is the name that will be referenced in your code when making chat completion calls. |
85-
| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-35-turbo-0613.ft-b044a9d3cf9c4228b5d393567f693b83`. You will need to add that value to the deploy_data json. Alternatively you can also deploy a checkpoint, by passing the checkpoint ID which will appear in the format `ftchkpt-e559c011ecc04fc68eaa339d8227d02d` |
85+
| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-35-turbo-0125.ft-b044a9d3cf9c4228b5d393567f693b83`. You will need to add that value to the deploy_data json. Alternatively you can also deploy a checkpoint, by passing the checkpoint ID which will appear in the format `ftchkpt-e559c011ecc04fc68eaa339d8227d02d` |
8686

8787
### Cross region deployment
8888

@@ -122,7 +122,7 @@ deploy_data = {
122122
"properties": {
123123
"model": {
124124
"format": "OpenAI",
125-
"name": <"FINE_TUNED_MODEL_NAME">, # This value will look like gpt-35-turbo-0613.ft-0ab3f80e4f2242929258fff45b56a9ce
125+
"name": <"FINE_TUNED_MODEL_NAME">, # This value will look like gpt-35-turbo-0125.ft-0ab3f80e4f2242929258fff45b56a9ce
126126
"version": "1",
127127
"source": source
128128
}
@@ -220,7 +220,7 @@ curl -X POST "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resource
220220
| resource_group | The resource group name for your Azure OpenAI resource. |
221221
| resource_name | The Azure OpenAI resource name. |
222222
| model_deployment_name | The custom name for your new fine-tuned model deployment. This is the name that will be referenced in your code when making chat completion calls. |
223-
| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-35-turbo-0613.ft-b044a9d3cf9c4228b5d393567f693b83`. You'll need to add that value to the deploy_data json. Alternatively you can also deploy a checkpoint, by passing the checkpoint ID which will appear in the format `ftchkpt-e559c011ecc04fc68eaa339d8227d02d` |
223+
| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-35-turbo-0125.ft-b044a9d3cf9c4228b5d393567f693b83`. You'll need to add that value to the deploy_data json. Alternatively you can also deploy a checkpoint, by passing the checkpoint ID which will appear in the format `ftchkpt-e559c011ecc04fc68eaa339d8227d02d` |
224224

225225

226226
### Cross region deployment

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

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,12 @@ ms.service: azure-ai-openai
1515

1616
## Dashboards
1717

18-
Azure OpenAI provides out-of-box dashboards for each of your Azure OpenAI resources. To access the monitoring dashboards sign-in to [https://portal.azure.com](https://portal.azure.com) and select the overview pane for one of your Azure OpenAI resources.
18+
Azure OpenAI provides out-of-box dashboards for each of your Azure OpenAI resources. There are two key dashboards to monitor your resource:
19+
20+
- The metrics dashboard in the AI Foundry Azure OpenAI resource view
21+
- The dashboard in the overview pane within the Azure portal
22+
23+
To access the monitoring dashboards, sign in to the [Azure portal](https://portal.azure.com) and then select the overview pane for one of your Azure OpenAI resources. To see the AI Foundry metrics dashboard from the Azure portal, select the overview pane and **Go to Azure AI Foundry portal**. Under tools, select the metrics dashboard.
1924

2025
:::image type="content" source="../media/monitoring/dashboard.png" alt-text="Screenshot that shows out-of-box dashboards for an Azure OpenAI resource in the Azure portal." lightbox="../media/monitoring/dashboard.png" border="false":::
2126

articles/ai-services/openai/includes/fine-tune-models.md

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -17,11 +17,7 @@ manager: nitinme
1717
1818
| Model ID | Fine-tuning regions | Max request (tokens) | Training Data (up to) |
1919
| --- | --- | :---: | :---: |
20-
| `gpt-35-turbo` (0613) | East US2 <br> North Central US <br> Sweden Central <br> Switzerland West | 4,096 | Sep 2021 |
2120
| `gpt-35-turbo` (1106) | East US2 <br> North Central US <br> Sweden Central <br> Switzerland West | Input: 16,385<br> Output: 4,096 | Sep 2021|
2221
| `gpt-35-turbo` (0125) | East US2 <br> North Central US <br> Sweden Central <br> Switzerland West | 16,385 | Sep 2021 |
23-
| `gpt-4` (0613) <sup>**1**</sup> | North Central US <br> Sweden Central | 8192 | Sep 2021 |
2422
| `gpt-4o-mini` (2024-07-18) | North Central US <br> Sweden Central | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 64,536 | Oct 2023 |
2523
| `gpt-4o` (2024-08-06) | East US2 <br> North Central US <br> Sweden Central | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 64,536 | Oct 2023 |
26-
27-
**<sup>1</sup>** GPT-4 is currently in public preview.

articles/ai-services/openai/includes/fine-tuning-openai-in-ai-studio.md

Lines changed: 2 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -28,15 +28,11 @@ ms.custom: include, build-2024
2828

2929
The following models support fine-tuning:
3030

31-
- `gpt-35-turbo` (0613)
3231
- `gpt-35-turbo` (1106)
3332
- `gpt-35-turbo` (0125)
34-
- `gpt-4` (0613)**<sup>*</sup>**
3533
- `gpt-4o` (2024-08-06)
3634
- `gpt-4o-mini` (2024-07-18)
3735

38-
**<sup>*</sup>** Fine-tuning for this model is currently in public preview.
39-
4036
Or you can fine tune a previously fine-tuned model, formatted as base-model.ft-{jobid}.
4137

4238
Consult the [models page](../concepts/models.md#fine-tuning-models) to check which regions currently support fine-tuning.
@@ -62,7 +58,7 @@ Take a moment to review the fine-tuning workflow for using Azure AI Foundry:
6258

6359
Your training data and validation data sets consist of input and output examples for how you would like the model to perform.
6460

65-
The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo-0613` the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
61+
The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document and must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
6662

6763
It's generally recommended to use the instructions and prompts that you found worked best in every training example. This will help you get the best results, especially if you have fewer than a hundred examples.
6864

@@ -117,7 +113,7 @@ To fine-tune an Azure OpenAI model in an existing Azure AI Foundry project, foll
117113

118114
1. Select a base model to fine-tune. Your choice influences both the performance and the cost of your model. In this example, we are choosing the `gpt-35-turbo` model. Then select **Confirm**.
119115

120-
1. For `gpt-35-turbo` we have different versions available for fine-tuning, so please choose which version you'd like to fine-tune. We will choose (0301).
116+
1. For `gpt-35-turbo` we have different versions available for fine-tuning, so please choose which version you'd like to fine-tune. We will choose (0125).
121117

122118
1. We also recommend including the `suffix` parameter to make it easier to distinguish between different iterations of your fine-tuned model. `suffix` takes a string, and is set to identify the fine-tuned model. With the OpenAI Python API a string of up to 18 characters is supported that will be added to your fine-tuned model name.
123119

articles/ai-services/openai/includes/fine-tuning-python.md

Lines changed: 8 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -26,15 +26,11 @@ ms.author: mbullwin
2626

2727
The following models support fine-tuning:
2828

29-
- `gpt-35-turbo` (0613)
3029
- `gpt-35-turbo` (1106)
3130
- `gpt-35-turbo` (0125)
32-
- `gpt-4` (0613)**<sup>*</sup>**
3331
- `gpt-4o` (2024-08-06)
3432
- `gpt-4o-mini` (2024-07-18)
3533

36-
**<sup>*</sup>** Fine-tuning for this model is currently in public preview.
37-
3834
Or you can fine tune a previously fine-tuned model, formatted as `base-model.ft-{jobid}`.
3935

4036

@@ -57,9 +53,9 @@ Take a moment to review the fine-tuning workflow for using the Python SDK with A
5753

5854
Your training data and validation data sets consist of input and output examples for how you would like the model to perform.
5955

60-
The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document. For `gpt-35-turbo-0613` the fine-tuning dataset must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
56+
The training and validation data you use **must** be formatted as a JSON Lines (JSONL) document and must be formatted in the conversational format that is used by the [Chat completions](../how-to/chatgpt.md) API.
6157

62-
If you would like a step-by-step walk-through of fine-tuning a `gpt-35-turbo-0613` please refer to the [Azure OpenAI fine-tuning tutorial](../tutorials/fine-tune.md)
58+
If you would like a step-by-step walk-through of fine-tuning a `gpt-4o-mini-2024-07-18` please refer to the [Azure OpenAI fine-tuning tutorial](../tutorials/fine-tune.md)
6359

6460
### Example file format
6561

@@ -196,7 +192,7 @@ In this example we are also passing the seed parameter. The seed controls the re
196192
response = client.fine_tuning.jobs.create(
197193
training_file=training_file_id,
198194
validation_file=validation_file_id,
199-
model="gpt-35-turbo-0613", # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters.
195+
model="gpt-35-turbo-0125", # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters.
200196
seed = 105 # seed parameter controls reproducibility of the fine-tuning job. If no seed is specified one will be generated automatically.
201197
)
202198

@@ -235,7 +231,7 @@ client = AzureOpenAI(
235231

236232
client.fine_tuning.jobs.create(
237233
training_file="file-abc123",
238-
model="gpt-35-turbo-0613", # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters.
234+
model="gpt-35-turbo-0125", # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters.
239235
hyperparameters={
240236
"n_epochs":2
241237
}
@@ -327,7 +323,7 @@ Unlike the previous SDK commands, deployment must be done using the control plan
327323
| resource_group | The resource group name for your Azure OpenAI resource. |
328324
| resource_name | The Azure OpenAI resource name. |
329325
| model_deployment_name | The custom name for your new fine-tuned model deployment. This is the name that will be referenced in your code when making chat completion calls. |
330-
| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-35-turbo-0613.ft-b044a9d3cf9c4228b5d393567f693b83`. You will need to add that value to the deploy_data json. Alternatively you can also deploy a checkpoint, by passing the checkpoint ID which will appear in the format `ftchkpt-e559c011ecc04fc68eaa339d8227d02d` |
326+
| fine_tuned_model | Retrieve this value from your fine-tuning job results in the previous step. It will look like `gpt-35-turbo-0125.ft-b044a9d3cf9c4228b5d393567f693b83`. You will need to add that value to the deploy_data json. Alternatively you can also deploy a checkpoint, by passing the checkpoint ID which will appear in the format `ftchkpt-e559c011ecc04fc68eaa339d8227d02d` |
331327

332328
```python
333329
import json
@@ -348,7 +344,7 @@ deploy_data = {
348344
"properties": {
349345
"model": {
350346
"format": "OpenAI",
351-
"name": <"fine_tuned_model">, #retrieve this value from the previous call, it will look like gpt-35-turbo-0613.ft-b044a9d3cf9c4228b5d393567f693b83
347+
"name": <"fine_tuned_model">, #retrieve this value from the previous call, it will look like gpt-35-turbo-0125.ft-b044a9d3cf9c4228b5d393567f693b83
352348
"version": "1"
353349
}
354350
}
@@ -374,7 +370,7 @@ Learn more about cross region deployment and use the deployed model [here](../ho
374370

375371
Once you have created a fine-tuned model you might want to continue to refine the model over time through further fine-tuning. Continuous fine-tuning is the iterative process of selecting an already fine-tuned model as a base model and fine-tuning it further on new sets of training examples.
376372

377-
To perform fine-tuning on a model that you have previously fine-tuned you would use the same process as described in [create a customized model](#create-a-customized-model) but instead of specifying the name of a generic base model you would specify your already fine-tuned model's ID. The fine-tuned model ID looks like `gpt-35-turbo-0613.ft-5fd1918ee65d4cd38a5dcf6835066ed7`
373+
To perform fine-tuning on a model that you have previously fine-tuned you would use the same process as described in [create a customized model](#create-a-customized-model) but instead of specifying the name of a generic base model you would specify your already fine-tuned model's ID. The fine-tuned model ID looks like `gpt-35-turbo-0125.ft-5fd1918ee65d4cd38a5dcf6835066ed7`
378374

379375
```python
380376
from openai import AzureOpenAI
@@ -388,7 +384,7 @@ client = AzureOpenAI(
388384
response = client.fine_tuning.jobs.create(
389385
training_file=training_file_id,
390386
validation_file=validation_file_id,
391-
model="gpt-35-turbo-0613.ft-5fd1918ee65d4cd38a5dcf6835066ed7" # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters.
387+
model="gpt-35-turbo-0125.ft-5fd1918ee65d4cd38a5dcf6835066ed7" # Enter base model name. Note that in Azure OpenAI the model name contains dashes and cannot contain dot/period characters.
392388
)
393389

394390
job_id = response.id

0 commit comments

Comments
 (0)