Skip to content

Commit 7eca7b5

Browse files
alexwolfmsftalexwolfmsft
committed
Merge
2 parents 37232e0 + 98a3fdf commit 7eca7b5

File tree

455 files changed

+4858
-6579
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

455 files changed

+4858
-6579
lines changed

‎.openpublishing.redirection.json

Lines changed: 135 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,11 @@
1515
"redirect_url": "/azure/search/search-how-to-dotnet-sdk",
1616
"redirect_document_id": false
1717
},
18+
{
19+
"source_path_from_root": "/articles/ai-services/agents/how-to/tools/overview.md",
20+
"redirect_url": "/azure/ai-services/agents/overview",
21+
"redirect_document_id": false
22+
},
1823
{
1924
"source_path_from_root": "/articles/search/search-howto-index-csv-blobs.md",
2025
"redirect_url": "/azure/search/search-how-to-index-csv-blobs",
@@ -25,10 +30,140 @@
2530
"redirect_url": "/azure/search/search-how-to-large-index",
2631
"redirect_document_id": false
2732
},
33+
{
34+
"source_path_from_root": "/articles/ai-services/agents/concepts/agents.md",
35+
"redirect_url": "/azure/ai-services/agents/overview",
36+
"redirect_document_id": false
37+
},
2838
{
2939
"source_path_from_root": "/articles/ai-services/openai/how-to/use-your-data-securely.md",
3040
"redirect_url": "/azure/ai-services/openai/how-to/on-your-data-configuration",
3141
"redirect_document_id": false
42+
},
43+
{
44+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/concepts/data-formats.md",
45+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
46+
"redirect_document_id": false
47+
},
48+
{
49+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/concepts/entity-components.md",
50+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
51+
"redirect_document_id": false
52+
},
53+
{
54+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/concepts/evaluation-metrics.md",
55+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
56+
"redirect_document_id": false
57+
},
58+
{
59+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/call-api.md",
60+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
61+
"redirect_document_id": false
62+
},
63+
{
64+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/create-project.md",
65+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
66+
"redirect_document_id": false
67+
},
68+
{
69+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/deploy-model.md",
70+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
71+
"redirect_document_id": false
72+
},
73+
{
74+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/design-schema.md",
75+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
76+
"redirect_document_id": false
77+
},
78+
{
79+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/fail-over.md",
80+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
81+
"redirect_document_id": false
82+
},
83+
{
84+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/label-data.md",
85+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
86+
"redirect_document_id": false
87+
},
88+
{
89+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/train-model.md",
90+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
91+
"redirect_document_id": false
92+
},
93+
{
94+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/how-to/view-model-evaluation.md",
95+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
96+
"redirect_document_id": false
97+
},
98+
{
99+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/language-support.md",
100+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
101+
"redirect_document_id": false
102+
},
103+
{
104+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/overview.md",
105+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
106+
"redirect_document_id": false
107+
},
108+
{
109+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/quickstart.md",
110+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
111+
"redirect_document_id": false
112+
},
113+
{
114+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/reference/glossary.md",
115+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
116+
"redirect_document_id": false
117+
},
118+
{
119+
"source_path_from_root": "/articles/ai-services/language-service/custom-text-analytics-for-health/reference/service-limits.md",
120+
"redirect_url": "/azure/ai-services/language-service/text-analytics-for-health/overview",
121+
"redirect_document_id": false
122+
},
123+
{
124+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/concepts/data-formats.md",
125+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
126+
"redirect_document_id": false
127+
},
128+
{
129+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/how-to/call-api.md",
130+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
131+
"redirect_document_id": false
132+
},
133+
{
134+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/how-to/create-project.md",
135+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
136+
"redirect_document_id": false
137+
},
138+
{
139+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/how-to/deploy-model.md",
140+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
141+
"redirect_document_id": false
142+
},
143+
{
144+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/how-to/design-schema.md",
145+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
146+
"redirect_document_id": false
147+
},
148+
{
149+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/how-to/label-data.md",
150+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
151+
"redirect_document_id": false
152+
},
153+
{
154+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/how-to/train-model.md",
155+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
156+
"redirect_document_id": false
157+
},
158+
{
159+
"source_path_from_root": "/articles/ai-services/language-service/sentiment-opinion-mining/custom/quickstart.md",
160+
"redirect_url": "/azure/ai-services/language-service/sentiment-opinion-mining/overview",
161+
"redirect_document_id": false
162+
},
163+
{
164+
"source_path_from_root": "/articles/ai-services/openai/references/azure-machine-learning.md",
165+
"redirect_url": "/azure/ai-services/openai/concepts/use-your-data",
166+
"redirect_document_id": false
32167
}
33168
]
34169
}

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

Lines changed: 15 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -17,9 +17,6 @@ ms.custom: references_regions, tool_generated
1717

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

20-
> [!TIP]
21-
> DeepSeek-R1 (preview) is available for deployment as [Serverless API endpoint](../../../ai-studio/how-to/deploy-models-deepseek.md).
22-
2320
:::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":::
2421

2522
Model availability varies by model provider, deployment SKU, and cloud. All models available in Azure AI Model Inference support the [Global standard](deployment-types.md#global-standard) deployment type which uses global capacity to guarantee throughput. [Azure OpenAI models](#azure-openai) also support regional deployments and [sovereign clouds](/entra/identity-platform/authentication-national-cloud)—Azure Government, Azure Germany, and Azure China 21Vianet.
@@ -52,10 +49,11 @@ Azure OpenAI Service offers a diverse set of models with different capabilities
5249
- Models that can transcribe and translate speech to text
5350

5451
| Model | Type | Tier | Capabilities |
55-
| ------ | ---- | --- | ------------ |
52+
| ------ | ---- | ---- | ------------ |
53+
| [o3-mini](https://ai.azure.com/explore/models/o3-mini/version/2025-01-31/registry/azure-openai) | chat-completion | Global standard | - **Input:** text and image (200,000 tokens) <br /> - **Output:** text (100,000 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON, structured outputs |
5654
| [o1](https://ai.azure.com/explore/models/o1/version/2024-12-17/registry/azure-openai) | chat-completion | Global standard | - **Input:** text and image (200,000 tokens) <br /> - **Output:** text (100,000 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON, structured outputs |
5755
| [o1-preview](https://ai.azure.com/explore/models/o1-preview/version/1/registry/azure-openai) | chat-completion | Global standard <br />Standard<br /> | - **Input:** text (128,000 tokens) <br /> - **Output:** (32,768 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON, structured outputs |
58-
| [o1-mini](https://ai.azure.com/explore/models/o1-mini/version/1/registry/azure-openai) | chat-completion | Global standard <br />Standard | - **Input:** text (128,000 tokens) <br /> - **Output:** (65,536 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON, structured outputs |
56+
| [o1-mini](https://ai.azure.com/explore/models/o1-mini/version/1/registry/azure-openai) | chat-completion | Global standard <br />Standard | - **Input:** text (128,000 tokens) <br /> - **Output:** (65,536 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
5957
| [gpt-4o-realtime-preview](https://ai.azure.com/explore/models/gpt-4o-realtime-preview/version/2024-10-01/registry/azure-openai) | real-time | Global standard | - **Input:** control, text, and audio (131,072 tokens) <br /> - **Output:** text and audio (16,384 tokens) <br /> - **Languages:** en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
6058
| [gpt-4o](https://ai.azure.com/explore/models/gpt-4o/version/2024-11-20/registry/azure-openai) | chat-completion | Global standard <br />Standard<br />Batch<br />Provisioned<br />Global provisioned<br />Data Zone | - **Input:** text and image (131,072 tokens) <br /> - **Output:** text (16,384 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON, structured outputs |
6159
| [gpt-4o-mini](https://ai.azure.com/explore/models/gpt-4o-mini/version/2024-07-18/registry/azure-openai) | chat-completion | Global standard <br />Standard<br />Batch<br />Provisioned<br />Global provisioned<br />Data Zone | - **Input:** text, image, and audio (131,072 tokens) <br /> - **Output:** (16,384 tokens) <br /> - **Languages:** `en`, `it`, `af`, `es`, `de`, `fr`, `id`, `ru`, `pl`, `uk`, `el`, `lv`, `zh`, `ar`, `tr`, `ja`, `sw`, `cy`, `ko`, `is`, `bn`, `ur`, `ne`, `th`, `pa`, `mr`, and `te`. <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON, structured outputs |
@@ -93,6 +91,16 @@ Core42 includes autoregressive bi-lingual LLMs for Arabic & English with state-o
9391

9492
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=core42).
9593

94+
### DeepSeek
95+
96+
DeepSeek family of models include DeepSeek-R1, which excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.
97+
98+
| Model | Type | Tier | Capabilities |
99+
| ------ | ---- | --- | ------------ |
100+
| [DeekSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (16,384 tokens) <br /> - **Output:** (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text. |
101+
102+
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=deepseek).
103+
96104
### Meta
97105

98106
Meta Llama models and tools are a collection of pretrained and fine-tuned generative AI text and image reasoning models. Meta models range is scale to include:
@@ -143,10 +151,10 @@ Mistral AI offers two categories of models: premium models including Mistral Lar
143151
| Model | Type | Tier | Capabilities |
144152
| ------ | ---- | --- | ------------ |
145153
| [Ministral-3B](https://ai.azure.com/explore/models/Ministral-3B/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
146-
| [Mistral-large](https://ai.azure.com/explore/models/Mistral-large/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
154+
| [Mistral-large](https://ai.azure.com/explore/models/Mistral-large/version/1/registry/azureml-mistral) <br /> (deprecated) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
147155
| [Mistral-small](https://ai.azure.com/explore/models/Mistral-small/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
148156
| [Mistral-Nemo](https://ai.azure.com/explore/models/Mistral-Nemo/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** en, fr, de, es, it, zh, ja, ko, pt, nl, and pl <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
149-
| [Mistral-large-2407](https://ai.azure.com/explore/models/Mistral-large-2407/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** en, fr, de, es, it, zh, ja, ko, pt, nl, and pl <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
157+
| [Mistral-large-2407](https://ai.azure.com/explore/models/Mistral-large-2407/version/1/registry/azureml-mistral) <br /> (legacy) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** en, fr, de, es, it, zh, ja, ko, pt, nl, and pl <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
150158
| [Mistral-Large-2411](https://ai.azure.com/explore/models/Mistral-Large-2411/version/2/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (128,000 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** en, fr, de, es, it, zh, ja, ko, pt, nl, and pl <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
151159
| [Codestral-2501](https://ai.azure.com/explore/models/Codestral-2501/version/2/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (262,144 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** en <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
152160

‎articles/ai-foundry/model-inference/how-to/inference.md

Lines changed: 9 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -48,6 +48,14 @@ For a chat model, you can create a request as follows:
4848

4949
If you specify a model name that doesn't match any given model deployment, you get an error that the model doesn't exist. You can control which models are available for users by creating model deployments as explained at [add and configure model deployments](create-model-deployments.md).
5050

51+
## Key-less authentication
52+
53+
Models deployed to Azure AI model inference in Azure AI Services support key-less authorization using Microsoft Entra ID. Key-less authorization enhances security, simplifies the user experience, reduces operational complexity, and provides robust compliance support for modern development. It makes it a strong choice for organizations adopting secure and scalable identity management solutions.
54+
55+
To use key-less authentication, [configure your resource and grant access to users](configure-entra-id.md) to perform inference. Once configured, then you can authenticate as follows:
56+
57+
[!INCLUDE [code-create-chat-client-entra](../includes/code-create-chat-client-entra.md)]
58+
5159
## Limitations
5260

5361
* Azure OpenAI Batch can't be used with the Azure AI model inference endpoint. You have to use the dedicated deployment URL as explained at [Batch API support in Azure OpenAI documentation](../../../ai-services/openai/how-to/batch.md#api-support).
@@ -56,4 +64,4 @@ If you specify a model name that doesn't match any given model deployment, you g
5664
## Next steps
5765

5866
* [Use embedding models](use-embeddings.md)
59-
* [Use chat completion models](use-chat-completions.md)
67+
* [Use chat completion models](use-chat-completions.md)

0 commit comments

Comments
 (0)