Skip to content

Commit ed4baa6

Browse files
Albertyang0Albertyang0
authored
Merge pull request #5710 from MicrosoftDocs/model-inference-folder-rename
model-inference-folder-rename -> main -- 06/26 - 5 AM PT
2 parents 80868a7 + 36cc692 commit ed4baa6

File tree

162 files changed

+379
-214
lines changed

Some content is hidden

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

162 files changed

+379
-214
lines changed

‎.openpublishing.redirection.json

Lines changed: 167 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
{
1+
{
22
"redirections": [
33
{
44
"source_path": "articles/ai-foundry/concepts/connections.md",
@@ -319,6 +319,171 @@
319319
"source_path_from_root": "/articles/ai-services/language-service/tutorials/prompt-flow.md",
320320
"redirect_url": "/azure/ai-services/language-service/tutorials/power-automate",
321321
"redirect_document_id": false
322+
},
323+
{
324+
"source_path": "articles/ai-foundry/model-inference/concepts/content-filter.md",
325+
"redirect_url": "../../foundry-models/concepts/content-filter",
326+
"redirect_document_id": false
327+
},
328+
{
329+
"source_path": "articles/ai-foundry/model-inference/concepts/default-safety-policies.md",
330+
"redirect_url": "../../foundry-models/concepts/default-safety-policies",
331+
"redirect_document_id": false
332+
},
333+
{
334+
"source_path": "articles/ai-foundry/model-inference/concepts/deployment-types.md",
335+
"redirect_url": "../../foundry-models/concepts/deployment-types",
336+
"redirect_document_id": false
337+
},
338+
{
339+
"source_path": "articles/ai-foundry/model-inference/concepts/endpoints.md",
340+
"redirect_url": "../../foundry-models/concepts/endpoints",
341+
"redirect_document_id": false
342+
},
343+
{
344+
"source_path": "articles/ai-foundry/model-inference/concepts/models.md",
345+
"redirect_url": "../../foundry-models/concepts/models",
346+
"redirect_document_id": false
347+
},
348+
{
349+
"source_path": "articles/ai-foundry/model-inference/concepts/model-versions.md",
350+
"redirect_url": "../../foundry-models/concepts/model-versions",
351+
"redirect_document_id": false
352+
},
353+
{
354+
"source_path": "articles/ai-foundry/model-inference/how-to/configure-content-filters.md",
355+
"redirect_url": "../../foundry-models/how-to/configure-content-filters",
356+
"redirect_document_id": false
357+
},
358+
{
359+
"source_path": "articles/ai-foundry/model-inference/how-to/configure-deployment-policies.md",
360+
"redirect_url": "../../foundry-models/how-to/configure-deployment-policies",
361+
"redirect_document_id": false
362+
},
363+
{
364+
"source_path": "articles/ai-foundry/model-inference/how-to/configure-entra-id.md",
365+
"redirect_url": "../../foundry-models/how-to/configure-entra-id",
366+
"redirect_document_id": false
367+
},
368+
{
369+
"source_path": "articles/ai-foundry/model-inference/how-to/configure-marketplace.md",
370+
"redirect_url": "../../foundry-models/how-to/configure-marketplace",
371+
"redirect_document_id": false
372+
},
373+
{
374+
"source_path": "articles/ai-foundry/model-inference/how-to/configure-project-connection.md",
375+
"redirect_url": "../../foundry-models/how-to/configure-project-connection",
376+
"redirect_document_id": false
377+
},
378+
{
379+
"source_path": "articles/ai-foundry/model-inference/how-to/create-model-deployments.md",
380+
"redirect_url": "../../foundry-models/how-to/create-model-deployments",
381+
"redirect_document_id": false
382+
},
383+
{
384+
"source_path": "articles/ai-foundry/model-inference/how-to/inference.md",
385+
"redirect_url": "../../foundry-models/how-to/inference",
386+
"redirect_document_id": false
387+
},
388+
{
389+
"source_path": "articles/ai-foundry/model-inference/how-to/manage-costs.md",
390+
"redirect_url": "../../foundry-models/how-to/manage-costs",
391+
"redirect_document_id": false
392+
},
393+
{
394+
"source_path": "articles/ai-foundry/model-inference/how-to/monitor-models.md",
395+
"redirect_url": "../../foundry-models/how-to/monitor-models",
396+
"redirect_document_id": false
397+
},
398+
{
399+
"source_path": "articles/ai-foundry/model-inference/how-to/quickstart-ai-project.md",
400+
"redirect_url": "../../foundry-models/how-to/quickstart-ai-project",
401+
"redirect_document_id": false
402+
},
403+
{
404+
"source_path": "articles/ai-foundry/model-inference/how-to/quickstart-create-resources.md",
405+
"redirect_url": "../../foundry-models/how-to/quickstart-create-resources",
406+
"redirect_document_id": false
407+
},
408+
{
409+
"source_path": "articles/ai-foundry/model-inference/how-to/quickstart-github-models.md",
410+
"redirect_url": "../../foundry-models/how-to/quickstart-github-models",
411+
"redirect_document_id": false
412+
},
413+
{
414+
"source_path": "articles/ai-foundry/model-inference/how-to/use-blocklists.md",
415+
"redirect_url": "../../foundry-models/how-to/use-blocklists",
416+
"redirect_document_id": false
417+
},
418+
{
419+
"source_path": "articles/ai-foundry/model-inference/how-to/use-chat-completions.md",
420+
"redirect_url": "../../foundry-models/how-to/use-chat-completions",
421+
"redirect_document_id": false
422+
},
423+
{
424+
"source_path": "articles/ai-foundry/model-inference/how-to/use-chat-multi-modal.md",
425+
"redirect_url": "../../foundry-models/how-to/use-chat-multi-modal",
426+
"redirect_document_id": false
427+
},
428+
{
429+
"source_path": "articles/ai-foundry/model-inference/how-to/use-chat-reasoning.md",
430+
"redirect_url": "../../foundry-models/how-to/use-chat-reasoning",
431+
"redirect_document_id": false
432+
},
433+
{
434+
"source_path": "articles/ai-foundry/model-inference/how-to/use-embeddings.md",
435+
"redirect_url": "../../foundry-models/how-to/use-embeddings",
436+
"redirect_document_id": false
437+
},
438+
{
439+
"source_path": "articles/ai-foundry/model-inference/how-to/use-image-embeddings.md",
440+
"redirect_url": "../../foundry-models/how-to/use-image-embeddings",
441+
"redirect_document_id": false
442+
},
443+
{
444+
"source_path": "articles/ai-foundry/model-inference/how-to/use-structured-outputs.md",
445+
"redirect_url": "../../foundry-models/how-to/use-structured-outputs",
446+
"redirect_document_id": false
447+
},
448+
{
449+
"source_path": "articles/ai-foundry/model-inference/how-to/github/create-model-deployments.md",
450+
"redirect_url": "../../../foundry-models/how-to/github/create-model-deployments",
451+
"redirect_document_id": false
452+
},
453+
{
454+
"source_path": "articles/ai-foundry/model-inference/tutorials/get-started-deepseek-r1.md",
455+
"redirect_url": "../../foundry-models/tutorials/get-started-deepseek-r1",
456+
"redirect_document_id": false
457+
},
458+
{
459+
"source_path": "articles/ai-foundry/model-inference/overview.md",
460+
"redirect_url": "../foundry-models/overview",
461+
"redirect_document_id": false
462+
},
463+
{
464+
"source_path": "articles/ai-foundry/model-inference/quotas-limits.md",
465+
"redirect_url": "../foundry-models/quotas-limits",
466+
"redirect_document_id": false
467+
},
468+
{
469+
"source_path": "articles/ai-foundry/model-inference/supported-languages.md",
470+
"redirect_url": "../foundry-models/supported-languages",
471+
"redirect_document_id": false
472+
},
473+
{
474+
"source_path": "articles/ai-foundry/model-inference/supported-languages-openai.md",
475+
"redirect_url": "../foundry-models/supported-languages-openai",
476+
"redirect_document_id": false
477+
},
478+
{
479+
"source_path": "articles/ai-foundry/model-inference/faq.yml",
480+
"redirect_url": "../foundry-models/faq",
481+
"redirect_document_id": false
482+
},
483+
{
484+
"source_path": "articles/ai-foundry/model-inference/index.yml",
485+
"redirect_url": "../foundry-models/index",
486+
"redirect_document_id": false
322487
}
323488
]
324-
}
489+
}

‎articles/ai-foundry/model-inference/breadcrumb/toc.yml renamed to ‎articles/ai-foundry/foundry-models/breadcrumb/toc.yml

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -7,5 +7,5 @@
77
topicHref: /azure/ai-studio/index
88
items:
99
- name: Foundry Models
10-
tocHref: /azure/ai-foundry/model-inference/
11-
topicHref: /azure/ai-foundry/model-inference/index
10+
tocHref: /azure/ai-foundry/foundry-models/
11+
topicHref: /azure/ai-foundry/foundry-models/index

‎articles/ai-foundry/model-inference/concepts/content-filter.md renamed to ‎articles/ai-foundry/foundry-models/concepts/content-filter.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -80,7 +80,7 @@ Detecting indirect attacks requires using document delimiters when constructing
8080

8181
## Configurability
8282

83-
[!INCLUDE [content-filter-configurability](../includes/content-filter-configurability.md)]
83+
[!INCLUDE [content-filter-configurability](../../foundry-models/includes/content-filter-configurability.md)]
8484

8585
## Scenario details
8686

‎articles/ai-foundry/model-inference/concepts/default-safety-policies.md renamed to ‎articles/ai-foundry/foundry-models/concepts/default-safety-policies.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -16,12 +16,12 @@ reviewer: santiagxf
1616

1717
Azure AI Foundry Models includes default safety applied to all models, excluding Azure OpenAI Whisper. These configurations provide you with a responsible experience by default.
1818

19-
Default safety aims to mitigate risks such as hate and fairness, sexual, violence, self-harm, protected material content, and user prompt injection attacks. To learn more about content filtering, read [our documentation describing categories and severity levels](content-filter.md).
19+
Default safety aims to mitigate risks such as hate and fairness, sexual, violence, self-harm, protected material content, and user prompt injection attacks. To learn more about content filtering, read [our documentation describing categories and severity levels](../../model-inference/concepts/content-filter.md).
2020

2121
This document describes the default configuration.
2222

2323
> [!TIP]
24-
> By default, all model deployments use the default configuration. However, you can configure content filtering per model deployment as explained at [Configuring content filtering](../how-to/configure-content-filters.md).
24+
> By default, all model deployments use the default configuration. However, you can configure content filtering per model deployment as explained at [Configuring content filtering](../../model-inference/how-to/configure-content-filters.md).
2525
2626
## Text models
2727

@@ -80,4 +80,4 @@ Content filters apply only to text prompts and completions. Images aren't subjec
8080

8181
## Next steps
8282

83-
* [Configure content filters in Azure AI Foundry Models](../how-to/configure-content-filters.md)
83+
* [Configure content filters in Azure AI Foundry Models](../../model-inference/how-to/configure-content-filters.md)

‎articles/ai-foundry/model-inference/concepts/deployment-types.md renamed to ‎articles/ai-foundry/foundry-models/concepts/deployment-types.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -33,7 +33,7 @@ Azure AI Foundry Models provides customers with choices on the hosting structure
3333

3434
Global deployments are available in the same Azure AI Foundry Services as non-global deployment types but allow you to leverage Azure's global infrastructure to dynamically route traffic to the data center with best availability for each request. Global standard provides the highest default quota and eliminates the need to load balance across multiple resources.
3535

36-
Customers with high consistent volume may experience greater latency variability. The threshold is set per model. See the [quotas page to learn more](../quotas-limits.md). For applications that require the lower latency variance at large workload usage, we recommend purchasing provisioned throughput.
36+
Customers with high consistent volume may experience greater latency variability. The threshold is set per model. See the [quotas page to learn more](../../model-inference/quotas-limits.md). For applications that require the lower latency variance at large workload usage, we recommend purchasing provisioned throughput.
3737

3838
## Global provisioned
3939

@@ -119,5 +119,5 @@ Administrators can control which model deployment types are available to their u
119119

120120
## Related content
121121

122-
- [Quotas & limits](../quotas-limits.md)
122+
- [Quotas & limits](../../model-inference/quotas-limits.md)
123123
- [Data privacy, and security for Azure AI Foundry Models](../../how-to/concept-data-privacy.md)

‎articles/ai-foundry/model-inference/concepts/endpoints.md renamed to ‎articles/ai-foundry/foundry-models/concepts/endpoints.md

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -36,7 +36,7 @@ Deployments capture:
3636

3737
An Azure AI Foundry resource can have as many model deployments as needed and they don't incur in cost unless inference is performed for those models. Deployments are Azure resources and hence they're subject to Azure policies.
3838

39-
To learn more about how to create deployments see [Add and configure model deployments](../how-to/create-model-deployments.md).
39+
To learn more about how to create deployments see [Add and configure model deployments](../../model-inference/how-to/create-model-deployments.md).
4040

4141
## Endpoints
4242

@@ -46,7 +46,7 @@ Azure AI Foundry Services (formerly known Azure AI Services) expose multiple end
4646
> * Azure AI inference endpoint (usually with the form `https://<resource-name>.services.ai.azure.com/models`)
4747
> * Azure OpenAI endpoint (usually with the form `https://<resource-name>.openai.azure.com`)
4848
49-
The **Azure AI inference endpoint** allows customers to use a single endpoint with the same authentication and schema to generate inference for the deployed models in the resource. All the models support this capability. This endpoint follows the [Azure AI Model Inference API](.././reference/reference-model-inference-api.md).
49+
The **Azure AI inference endpoint** allows customers to use a single endpoint with the same authentication and schema to generate inference for the deployed models in the resource. All the models support this capability. This endpoint follows the [Azure AI Model Inference API](../../model-inference/reference/reference-model-inference-api.md).
5050

5151
The **Azure OpenAI API** exposes the full capabilities of OpenAI models and supports more features like assistants, threads, files, and batch inference. Non-OpenAI models may also be exposed in this route.
5252

@@ -60,21 +60,21 @@ The inference endpoint routes requests to a given deployment by matching the par
6060

6161
For example, if you create a deployment named `Mistral-large`, then such deployment can be invoked as:
6262

63-
[!INCLUDE [code-create-chat-client](../includes/code-create-chat-client.md)]
63+
[!INCLUDE [code-create-chat-client](../../foundry-models/includes/code-create-chat-client.md)]
6464

6565
For a chat model, you can create a request as follows:
6666

67-
[!INCLUDE [code-create-chat-completion](../includes/code-create-chat-completion.md)]
67+
[!INCLUDE [code-create-chat-completion](../../foundry-models/includes/code-create-chat-completion.md)]
6868

69-
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](../how-to/create-model-deployments.md).
69+
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](../../model-inference/how-to/create-model-deployments.md).
7070

7171
## Key-less authentication
7272

7373
Models deployed to Azure AI Foundry Models 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.
7474

75-
To use key-less authentication, [configure your resource and grant access to users](../how-to/configure-entra-id.md) to perform inference. Once configured, then you can authenticate as follows:
75+
To use key-less authentication, [configure your resource and grant access to users](../../model-inference/how-to/configure-entra-id.md) to perform inference. Once configured, then you can authenticate as follows:
7676

77-
[!INCLUDE [code-create-chat-client-entra](../includes/code-create-chat-client-entra.md)]
77+
[!INCLUDE [code-create-chat-client-entra](../../foundry-models/includes/code-create-chat-client-entra.md)]
7878

7979
## Limitations
8080

@@ -83,5 +83,5 @@ To use key-less authentication, [configure your resource and grant access to use
8383

8484
## Next steps
8585

86-
- [Models](models.md)
87-
- [Deployment types](deployment-types.md)
86+
- [Models](../../model-inference/concepts/models.md)
87+
- [Deployment types](../../model-inference/concepts/deployment-types.md)

‎articles/ai-foundry/model-inference/concepts/model-versions.md renamed to ‎articles/ai-foundry/foundry-models/concepts/model-versions.md

File renamed without changes.

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

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -61,10 +61,10 @@ DeepSeek family of models includes DeepSeek-R1, which excels at reasoning tasks
6161
| ------ | ---- | ---- | ------------ |
6262
| [DeepSeek-R1-0528]() <br /> | chat-completion | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:** text (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
6363
| [DeepSeek-V3-0324](https://ai.azure.com/explore/models/deepseek-v3-0324/version/1/registry/azureml-deepseek) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
64-
| [DeepSeek-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 (163,840 tokens) <br /> - **Output:** (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text. |
64+
| [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek) | chat-completion <br /> [(with reasoning content)](../../model-inference/how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:** (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text. |
6565
| [DeepSeek-V3](https://ai.azure.com/explore/models/deepseek-v3/version/1/registry/azureml-deepseek) <br />(Legacy) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
6666

67-
For a tutorial on DeepSeek-R1, see [Tutorial: Get started with DeepSeek-R1 reasoning model in Azure AI Foundry Models](../tutorials/get-started-deepseek-r1.md).
67+
For a tutorial on DeepSeek-R1, see [Tutorial: Get started with DeepSeek-R1 reasoning model in Azure AI Foundry Models](../../model-inference/tutorials/get-started-deepseek-r1.md).
6868

6969
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=deepseek).
7070

@@ -75,7 +75,7 @@ Microsoft models include various model groups such as MAI models, Phi models, he
7575

7676
| Model | Type | Tier | Capabilities |
7777
| ------ | ---- | --- | ------------ |
78-
| [MAI-DS-R1](https://ai.azure.com/explore/models/MAI-DS-R1/version/1/registry/azureml) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:** (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text. |
78+
| [MAI-DS-R1](https://ai.azure.com/explore/models/MAI-DS-R1/version/1/registry/azureml) | chat-completion <br /> [(with reasoning content)](../../model-inference/how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:** (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text. |
7979

8080
### Mistral AI
8181

@@ -112,7 +112,7 @@ xAI's Grok 3 and Grok 3 Mini models are designed to excel in various enterprise
112112

113113
Models from Partners and Community available for deployment with pay-as-you-go billing (for example, Cohere models) are offered by the model provider but hosted in Microsoft-managed Azure infrastructure and accessed via API in the Azure AI Foundry. Model providers define the license terms and set the price for use of their models, while Azure AI Foundry manages the hosting infrastructure.
114114

115-
Models from Partners and Community are offered through Azure Marketplace and [requires additional configuration for enabling](../how-to/configure-marketplace.md).
115+
Models from Partners and Community are offered through Azure Marketplace and [requires additional configuration for enabling](../../model-inference/how-to/configure-marketplace.md).
116116

117117
### AI21 Labs
118118

@@ -229,4 +229,4 @@ Those models can be of open access or IP protected. In both cases, you have to d
229229

230230
## Next steps
231231

232-
- Get started today and [deploy your fist model in Azure AI Foundry Models](../how-to/create-model-deployments.md)
232+
- Get started today and [deploy your fist model in Azure AI Foundry Models](../../model-inference/how-to/create-model-deployments.md)

‎articles/ai-foundry/model-inference/context/context.yml renamed to ‎articles/ai-foundry/foundry-models/context/context.yml

File renamed without changes.

0 commit comments

Comments
 (0)