Skip to content

Commit 39d44fa

Browse files
v-aljev-alje
committed
Merge branch 'main' into release-agents-foundry
2 parents a85082a + 3487e32 commit 39d44fa

File tree

5 files changed

+19
-10
lines changed

5 files changed

+19
-10
lines changed

‎articles/ai-foundry/model-inference/concepts/models.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -18,7 +18,7 @@ ms.custom: references_regions, tool_generated
1818
Azure AI model inference in Azure AI Foundry gives you access to flagship models in Azure AI to consume them as APIs without hosting them on your infrastructure.
1919

2020
> [!TIP]
21-
> DeepSeek-R1 is available for deployment as [Serverless API endpoint](../../../ai-studio/how-to/deploy-models-deepseek.md).
21+
> DeepSeek-R1 (preview) is available for deployment as [Serverless API endpoint](../../../ai-studio/how-to/deploy-models-deepseek.md).
2222
2323
:::image type="content" source="../media/models/models-catalog.gif" alt-text="An animation showing Azure AI studio model catalog section and the models available." lightbox="../media/models/models-catalog.gif":::
2424

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

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -11,25 +11,25 @@ ms.date: 01/15/2025
1111

1212
| **Region** | **gpt-4o**, **2024-05-13** | **gpt-4o**, **2024-08-06** | **gpt-4o**, **2024-11-20** | **gpt-4o-mini**, **2024-07-18** |
1313
|:-------------------|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|
14-
| australiaeast | ✅ | ✅ | - | ✅ |
14+
| australiaeast | ✅ | ✅ | ✅ | ✅ |
1515
| brazilsouth | ✅ | ✅ | - | ✅ |
1616
| canadacentral | ✅ | ✅ | - | ✅ |
1717
| canadaeast | ✅ | ✅ | ✅ | ✅ |
18-
| eastus | ✅ | ✅ | - | ✅ |
19-
| eastus2 | ✅ | ✅ | - | ✅ |
18+
| eastus | ✅ | ✅ | ✅ | ✅ |
19+
| eastus2 | ✅ | ✅ | ✅ | ✅ |
2020
| francecentral | ✅ | ✅ | - | ✅ |
2121
| germanywestcentral | ✅ | ✅ | - | ✅ |
2222
| japaneast | ✅ | ✅ | - | ✅ |
2323
| koreacentral | ✅ | ✅ | - | ✅ |
2424
| northcentralus | ✅ | ✅ | - | ✅ |
25-
| norwayeast | ✅ | ✅ | - | ✅ |
25+
| norwayeast | ✅ | ✅ | ✅ | ✅ |
2626
| polandcentral | ✅ | ✅ | - | ✅ |
2727
| southafricanorth | ✅ | ✅ | - | ✅ |
2828
| southcentralus | ✅ | ✅ | - | ✅ |
2929
| southeastasia | ✅ | ✅ | - | ✅ |
3030
| southindia | ✅ | ✅ | ✅ | ✅ |
3131
| spaincentral | ✅ | ✅ | - | ✅ |
32-
| swedencentral | ✅ | ✅ | - | ✅ |
32+
| swedencentral | ✅ | ✅ | ✅ | ✅ |
3333
| switzerlandnorth | ✅ | ✅ | - | ✅ |
3434
| switzerlandwest | ✅ | ✅ | - | ✅ |
3535
| uaenorth | ✅ | ✅ | - | ✅ |

‎articles/ai-studio/how-to/deploy-models-deepseek.md

Lines changed: 5 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@ zone_pivot_groups: azure-ai-model-catalog-samples-chat
2121
In this article, you learn about DeepSeek-R1 and how to use them.
2222
DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks. It features 671B total parameters with 37B active parameters, and 128k context length.
2323

24+
[!INCLUDE [models-preview](../includes/models-preview.md)]
2425

2526

2627
::: zone pivot="programming-language-python"
@@ -240,7 +241,7 @@ print_stream(result)
240241

241242
### Apply content safety
242243

243-
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
244+
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
244245

245246
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
246247

@@ -507,7 +508,7 @@ for await (const event of sses) {
507508
508509
### Apply content safety
509510
510-
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
511+
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
511512
512513
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
513514
@@ -800,7 +801,7 @@ StreamMessageAsync(client).GetAwaiter().GetResult();
800801
801802
### Apply content safety
802803
803-
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
804+
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
804805
805806
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
806807
@@ -1086,7 +1087,7 @@ The last message in the stream has `finish_reason` set, indicating the reason fo
10861087

10871088
### Apply content safety
10881089

1089-
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
1090+
The Azure AI model inference API supports [Azure AI content safety](https://aka.ms/azureaicontentsafety). When you use deployments with Azure AI content safety turned on, inputs and outputs pass through an ensemble of classification models aimed at detecting and preventing the output of harmful content. The content filtering (preview) system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions.
10901091

10911092
The following example shows how to handle events when the model detects harmful content in the input prompt and content safety is enabled.
10921093

‎articles/ai-studio/how-to/model-catalog-overview.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -78,6 +78,7 @@ The following list contains Serverless API models. For Azure OpenAI models, see
7878
Model | Managed compute | Serverless API (pay-per-token)
7979
--|--|--
8080
AI21 family models | Not available | Jamba-1.5-Mini <br> Jamba-1.5-Large
81+
Azure DeepSeek | Not available | DeepSeek-R1
8182
Cohere family models | Not available | Cohere-command-r-plus-08-2024 <br> Cohere-command-r-08-2024 <br> Cohere-command-r-plus <br> Cohere-command-r <br> Cohere-embed-v3-english <br> Cohere-embed-v3-multilingual <br> Cohere-rerank-v3-english <br> Cohere-rerank-v3-multilingual
8283
Gretel | Not available | Gretel-Navigator
8384
Healthcare AI family Models | MedImageParse<BR> MedImageInsight<BR> CxrReportGen<BR> Virchow<BR> Virchow2<BR> Prism<BR> BiomedCLIP-PubMedBERT<BR> microsoft-llava-med-v1.5<BR> m42-health-llama3-med4<BR> biomistral-biomistral-7b<BR> microsoft-biogpt-large-pub<BR> microsoft-biomednlp-pub<BR> stanford-crfm-biomedlm<BR> medicalai-clinicalbert<BR> microsoft-biogpt<BR> microsoft-biogpt-large<BR> microsoft-biomednlp-pub<BR> | Not Available

‎articles/ai-studio/includes/region-availability-maas.md

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,13 @@ ms.date: 08/05/2024
1010
ms.custom: include, references_regions
1111
---
1212

13+
### Azure DeepSeek models
14+
15+
| Model | Offer Availability Region | Hub/Project Region for Deployment | Hub/Project Region for Fine tuning |
16+
|---------|---------|---------|---------|
17+
DeepSeek-R1 | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> West US <br> West US 3 | Not available |
18+
19+
1320
### Cohere models
1421

1522

0 commit comments

Comments
 (0)