Merge pull request #7243 from MicrosoftDocs/main

Auto Publish – main to live - 2025-09-23 22:09 UTC

Author: learn-build-service-prod[bot]

articles/ai-foundry/concepts/model-lifecycle-retirement.md

@@ -94,20 +94,20 @@ The following tables list the timelines for models that are on track for retirem
 |-------|-------------------|------------------------|-----------------------|-----------------------------|
 | [Command R](https://ai.azure.com/explore/models/Cohere-command-r/version/1/registry/azureml-cohere?cid=learnDocs) | February 24, 2025 | March 25, 2025 | June 30, 2025 | [Cohere Command R 08-2024](https://aka.ms/azureai/landing/Cohere-command-r-08-2024?cid=learnDocs) |
 | [Command R+](https://ai.azure.com/explore/models/Cohere-command-r-plus/version/1/registry/azureml-cohere?cid=learnDocs) | February 24, 2025 | March 25, 2025 | June 30, 2025 | [Cohere Command R+ 08-2024](https://aka.ms/azureai/landing/Cohere-command-r-plus-08-2024?cid=learnDocs) |
-| [Cohere-rerank-v3-english](https://ai.azure.com/explore/models/Cohere-rerank-v3-english/version/1/registry/azureml-cohere) | February 28, 2025 | March 31, 2025 | June 30, 2025 | [Cohere-rerank-v3.5](https://ai.azure.com/explore/models/Cohere-rerank-v3.5/version/1/registry/azureml-cohere) |
-| [Cohere-rerank-v3-multilingual](https://ai.azure.com/explore/models/Cohere-rerank-v3-multilingual/version/1/registry/azureml-cohere) | February 28, 2025 | March 31, 2025 | June 30, 2025 | [Cohere-rerank-v3.5](https://ai.azure.com/explore/models/Cohere-rerank-v3.5/version/1/registry/azureml-cohere) |
+| [Cohere-rerank-v3-english](https://ai.azure.com/explore/models/Cohere-rerank-v3-english/version/1/registry/azureml-cohere/?cid=learnDocs) | February 28, 2025 | March 31, 2025 | June 30, 2025 | [Cohere-rerank-v3.5](https://ai.azure.com/explore/models/Cohere-rerank-v3.5/version/1/registry/azureml-cohere/?cid=learnDocs) |
+| [Cohere-rerank-v3-multilingual](https://ai.azure.com/explore/models/Cohere-rerank-v3-multilingual/version/1/registry/azureml-cohere/?cid=learnDocs) | February 28, 2025 | March 31, 2025 | June 30, 2025 | [Cohere-rerank-v3.5](https://ai.azure.com/explore/models/Cohere-rerank-v3.5/version/1/registry/azureml-cohere/?cid=learnDocs) |
 
 #### Core42
 
 | Model | Legacy date (UTC) | Deprecation date (UTC) | Retirement date (UTC) | Suggested replacement model |
 |-------|-------------------|------------------------|-----------------------|-----------------------------|
-| [jais-30b-chat](https://ai.azure.com/explore/models/jais-30b-chat/version/3/registry/azureml-core42) | September 30, 2025 | October 31, 2025 | January 30, 2026 | N/A |
+| [jais-30b-chat](https://ai.azure.com/explore/models/jais-30b-chat/version/3/registry/azureml-core42/?cid=learnDocs) | September 30, 2025 | October 31, 2025 | January 30, 2026 | N/A |
 
 #### DeepSeek
 
 | Model | Legacy date (UTC) | Deprecation date (UTC) | Retirement date (UTC) | Suggested replacement model |
 |-------|-------------------|------------------------|-----------------------|-----------------------------|
-| [DeepSeek-V3](https://aka.ms/azureai/landing/DeepSeek-V3) | April 10, 2025 | May 31, 2025 | August 31, 2025 | [DeepSeek-V3-0324](https://aka.ms/azureai/landing/DeepSeek-V3-0324) |
+| [DeepSeek-V3](https://aka.ms/azureai/landing/DeepSeek-V3?cid=learnDocs) | April 10, 2025 | May 31, 2025 | August 31, 2025 | [DeepSeek-V3-0324](https://aka.ms/azureai/landing/DeepSeek-V3-0324?cid=learnDocs) |
 
 #### Gretel
 
@@ -147,12 +147,12 @@ The following tables list the timelines for models that are on track for retirem
 
 | Model | Legacy date (UTC) | Deprecation date (UTC) | Retirement date (UTC) | Suggested replacement model |
 |-------|-------------------|------------------------|-----------------------|-----------------------------|
-| [Mistral-Nemo](https://ai.azure.com/explore/models/Mistral-Nemo/version/1/registry/azureml-mistral) | September 30, 2025 | October 31, 2025 | January 30, 2026 | [Mistral-small-2503](https://aka.ms/aistudio/landing/mistral-small-2503) |
-| [Mistral-large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411) | September 30, 2025 | October 31, 2025 | January 30, 2026 | [Mistral-medium-2505](https://ai.azure.com/explore/models/mistral-medium-2505/version/1/registry/azureml-mistral) |
-| [Mistral-ocr-2503](https://ai.azure.com/explore/models/mistral-ocr-2503/version/1/registry/azureml-mistral) | September 30, 2025 | October 31, 2025 | January 30, 2026 | [Mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral) |
+| [Mistral-Nemo](https://ai.azure.com/explore/models/Mistral-Nemo/version/1/registry/azureml-mistral/?cid=learnDocs) | September 30, 2025 | October 31, 2025 | January 30, 2026 | [Mistral-small-2503](https://aka.ms/aistudio/landing/mistral-small-2503) |
+| [Mistral-large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411) | September 30, 2025 | October 31, 2025 | January 30, 2026 | [Mistral-medium-2505](https://ai.azure.com/explore/models/mistral-medium-2505/version/1/registry/azureml-mistral/?cid=learnDocs) |
+| [Mistral-ocr-2503](https://ai.azure.com/explore/models/mistral-ocr-2503/version/1/registry/azureml-mistral/?cid=learnDocs) | September 30, 2025 | October 31, 2025 | January 30, 2026 | [Mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral/?cid=learnDocs) |
 | [Mistral-small](https://ai.azure.com/explore/models/Mistral-small/version/1/registry/azureml-mistral/?cid=learnDocs) | March 31, 2025 | April 30, 2025 | July 31, 2025 | [Mistral-small-2503](https://aka.ms/aistudio/landing/mistral-small-2503) |
-| [Mistral-large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407) | January 13, 2025 | February 13, 2025 | May 13, 2025 | [Mistral-medium-2505](https://ai.azure.com/explore/models/mistral-medium-2505/version/1/registry/azureml-mistral) |
-| [Mistral-large](https://aka.ms/azureai/landing/Mistral-Large) | December 15, 2024 | January 15, 2025 | April 15, 2025 | [Mistral-medium-2505](https://ai.azure.com/explore/models/mistral-medium-2505/version/1/registry/azureml-mistral) |
+| [Mistral-large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407?cid=learnDocs) | January 13, 2025 | February 13, 2025 | May 13, 2025 | [Mistral-medium-2505](https://ai.azure.com/explore/models/mistral-medium-2505/version/1/registry/azureml-mistral/?cid=learnDocs) |
+| [Mistral-large](https://aka.ms/azureai/landing/Mistral-Large?cid=learnDocs) | December 15, 2024 | January 15, 2025 | April 15, 2025 | [Mistral-medium-2505](https://ai.azure.com/explore/models/mistral-medium-2505/version/1/registry/azureml-mistral/?cid=learnDocs) |
 
 ## Related content
 

articles/ai-foundry/foundry-models/concepts/models-from-partners.md

@@ -106,9 +106,9 @@ Mistral AI offers two categories of models: premium models such as Mistral Large
 | [Ministral-3B](https://ai.azure.com/explore/models/Ministral-3B/version/1/registry/azureml-mistral/?cid=learnDocs) | chat-completion | - **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 | Foundry, Hub-based |
 | [Mistral-Nemo](https://ai.azure.com/explore/models/Mistral-Nemo/version/1/registry/azureml-mistral/?cid=learnDocs) | chat-completion | - **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 | Foundry, Hub-based |
 | [Mistral-small-2503](https://ai.azure.com/explore/models/Mistral-small-2503/version/1/registry/azureml-mistral/?cid=learnDocs) | chat-completion | - **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 | Foundry, Hub-based |
-| [Mistral-medium-2505](https://aka.ms/aistudio/landing/mistral-medium-2505) | chat-completion |  - **Input:** text (128,000 tokens), image <br /> - **Output:** text (128,000 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text, JSON | Foundry, Hub-based|
+| [Mistral-medium-2505](https://aka.ms/aistudio/landing/mistral-medium-2505?cid=learnDocs) | chat-completion |  - **Input:** text (128,000 tokens), image <br /> - **Output:** text (128,000 tokens) <br />  - **Tool calling:** No <br /> - **Response formats:** Text, JSON | Foundry, Hub-based|
 | [Mistral-Large-2411](https://ai.azure.com/explore/models/Mistral-Large-2411/version/2/registry/azureml-mistral/?cid=learnDocs) | chat-completion | - **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 | Foundry, Hub-based |
-| [Mistral-OCR-2503](https://aka.ms/aistudio/landing/mistral-ocr-2503) | image to text |  - **Input:** image or PDF pages (1,000 pages, max 50MB PDF file) <br> - **Output:** text <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON, Markdown | Hub-based|
+| [Mistral-OCR-2503](https://aka.ms/aistudio/landing/mistral-ocr-2503?cid=learnDocs) | image to text |  - **Input:** image or PDF pages (1,000 pages, max 50MB PDF file) <br> - **Output:** text <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON, Markdown | Hub-based|
 | [mistralai-Mistral-7B-Instruct-v01](https://ai.azure.com/explore/models/mistralai-Mistral-7B-Instruct-v01/version/11/registry/azureml/?cid=learnDocs) | chat-completion | - **Input:** text  <br /> - **Output:** text  <br /> - **Languages:** en <br />  - **Response formats:** Text | Hub-based |
 | [mistralai-Mistral-7B-Instruct-v0-2](https://ai.azure.com/explore/models/mistralai-Mistral-7B-Instruct-v0-2/version/6/registry/azureml/?cid=learnDocs) | chat-completion | - **Input:** text <br /> - **Output:** text <br /> - **Languages:** en <br /> - **Response formats:** Text | Hub-based |
 | [mistralai-Mixtral-8x7B-Instruct-v01](https://ai.azure.com/explore/models/mistralai-Mixtral-8x7B-Instruct-v01/version/10/registry/azureml/?cid=learnDocs) | chat-completion | - **Input:** text  <br /> - **Output:** text <br /> - **Languages:** en <br /> - **Response formats:** Text | Hub-based |
@@ -161,4 +161,4 @@ See [this model collection in Azure AI Foundry portal](https://ai.azure.com/expl
 - [Deployment overview for Azure AI Foundry Models](../../concepts/deployments-overview.md)
 - [Add and configure models to Azure AI Foundry Models](../how-to/create-model-deployments.md)
 - [Deployment types in Azure AI Foundry Models](deployment-types.md)
-- [Serverless API inference examples for Foundry Models](../../concepts/models-inference-examples.md)
+- [Serverless API inference examples for Foundry Models](../../concepts/models-inference-examples.md)

articles/ai-foundry/foundry-models/quotas-limits.md

@@ -68,25 +68,7 @@ The Usage Limit determines the level of usage above which customers might see la
 
 ## Request increases to the default limits
 
-You can submit limit increase requests, which we evaluate one at a time. [Open an online customer support request](https://portal.azure.com/#blade/Microsoft_Azure_Support/HelpAndSupportBlade/newsupportrequest/). When you request an endpoint limit increase, provide the following information:
-
-1. Select **Service and subscription limits (quotas)** as the **Issue type** when you open the support request.
-
-1. Select the subscription you want to use.
-
-1. Select **Cognitive Services** as **Quota type**.
-
-1. Select **Next**.
-
-1. On the **Additional details** tab, provide detailed reasons for the limit increase so that your request can be processed. Be sure to add the following information to the reason for limit increase:
-
-   * Model name, model version (if applicable), and deployment type (SKU).
-   * Description of your scenario and workload.
-   * Rationale for the requested increase.
-   * Target throughput: Tokens per minute, requests per minute, and other relevant metrics.
-   * Planned time plan (by when you need increased limits).
-
-1. Select **Save and continue**.
+[!INCLUDE [quota-increase- request](../openai/includes/quota-increase-request.md)]
 
 ## General best practices to stay within rate limits
 

articles/ai-foundry/how-to/create-projects.md

@@ -20,10 +20,7 @@ ai-usage: ai-assisted
 
 # Create a project for Azure AI Foundry (Foundry projects)
 
-> [!NOTE]
-> An alternate hub project creation article is available: [Create a hub project for Azure AI Foundry](hub-create-projects.md).
-
-This article describes how to create a project in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs). Projects let you organize your work for exploring new ideas and as you prototype on a particular use case.
+This article describes how to create a project in [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs). Projects let you organize your work, such as agents, evaluations, and files, as you build stateful apps and explore new ideas.
 
 [!INCLUDE [create-project-fdp](../includes/create-project-fdp.md)]
 

articles/ai-foundry/includes/create-project-fdp.md

@@ -15,17 +15,19 @@ ms.custom:
 
 * [!INCLUDE [fdp-description](../includes/fdp-description.md)]
 
-* This project type gives you the best support for:
+* This project type gives you access to the latest generative AI features in AI Foundry, including:
 
     * Agents 
-    * AI Foundry API to work with agents and across models
-    * Models sold directly by Azure - Azure OpenAI, DeepSeek, xAI, etc.
+    * Foundry SDK and API to build agents and switch easily between models
+    * Models sold directly by Azure - Azure OpenAI, Mistral, xAI, DeepSeek, etc.
     * Partner & Community Models sold through Marketplace - Stability, Bria, Cohere, etc. 
-    * Project files (directly upload files and start experimenting)
-    * Project-level isolation of files and outputs 
+    * Content understanding 
     * Evaluations
     * Fine-tuning
-    * Playgrounds
+    * OpenAI SDK and API incl. Batch and Stored Completions
+    * AI Services
+
+* Do you need access to Open Source models, or PromptFlow? [Create a hub project type](../how-to/hub-create-projects.md) instead.
 
 ## Prerequisites
 
@@ -58,7 +60,7 @@ Use the following tabs to select the method you plan to use to create a [!INCLUD
         DefaultAzureCredential(interactive_browser_tenant_id="<TENANT_ID>")
         ```
             
-    1. (Optional) If you're working on in the [Azure Government - US](/azure/azure-government/documentation-government-welcome) or [Azure China 21Vianet](https://azure.microsoft.com/global-infrastructure/services/?regions=china-east-2%2cchina-non-regional&products=all) regions, specify the region into which you want to authenticate. You can specify the region with `DefaultAzureCredential`. The following example authenticates to the Azure Government - US region:
+    1. (Optional) If you're working on in the [Azure Government - US](/azure/azure-government/documentation-government-welcome) or [Azure operated by 21Vianet](https://azure.microsoft.com/global-infrastructure/services/?regions=china-east-2%2cchina-non-regional&products=all) regions, specify the region into which you want to authenticate. You can specify the region with `DefaultAzureCredential`. The following example authenticates to the Azure Government - US region:
             
         ```python
         from azure.identity import AzureAuthorityHosts

articles/ai-foundry/includes/create-second-fdp-project.md

@@ -16,26 +16,32 @@ ms.custom:
 ---
 
 
-Create multiple [!INCLUDE [fdp-project-name](fdp-project-name.md)]s on an existing `AI Foundry` resource, so you can share your environment with your team for collaboration. 
+Create multiple [!INCLUDE [fdp-project-name](fdp-project-name.md)]s on an existing `AI Foundry` resource to enable team collaboration and shared resource access including security, deployments, and connected tools. This setup is ideal in restricted Azure subscriptions where developers need self-serve exploration ability within the setup of a pre-configured environment.
+
+:::image type="content" source="../media/how-to/projects/projects-multi-setup.png" alt-text="Diagram shows how a team could share resource access with multiple projects on a Foundry resource.":::
 
 [!INCLUDE [fdp-project-name](fdp-project-name.md)]s as Azure child resources may get assigned their own access controls, but share common settings such as network security, deployments, and Azure tool integration from their parent resource.
 
-Your first project (default project) plays a special role and has access to more features:
+While not all Foundry capabilities support organizing work in projects yet, your resource's first "default" project is more powerful. You can identify it by the tag "default" in UX experiences and the resource property "is_default" when using code options.
 
-| Feature | Default [!INCLUDE [fdp-project-name](fdp-project-name.md)] | Nondefault [!INCLUDE [fdp-project-name](fdp-project-name.md)] |
+| Feature | Default project | Other projects |
 |--|--|--|
 | Model inference | ✅ | ✅ |
 | Playgrounds | ✅ | ✅ |
 | Agents | ✅ | ✅ |
 | Evaluations | ✅ | ✅ |
+| Tracing | ✅ | ✅ |
+| Datasets | ✅ | ✅ |
+| Indexes | ✅ | ✅ |
+| Foundry SDK and API | ✅ | ✅ |
+| Content understanding | ✅ | ✅ |
+| OpenAI SDK and API | ✅ | - |
+| OpenAI Batch, Fine-tuning, Stored completions | ✅ | - |
+| Language fine-tuning | ✅ | ✅ |
+| Speech fine-tuning | ✅ | - |
 | Connections | ✅ | ✅ |
-| AI Foundry API that works with agents and across models | ✅ | ✅ |
-| Project-level isolation of files and outputs | ✅ | ✅ |
-| Azure OpenAI with Batch, StoredCompletions, Fine-tuning | ✅ |  |
-| Backwards compatible with project-less {account}.cognitiveservices.com data plane API | ✅ |  |
-| Content safety | ✅ |  |
 
-* To add a nondefault project to a resource:
+* To add a project to a Foundry resource:
 
     # [Azure AI Foundry portal](#tab/ai-foundry)
 

articles/ai-foundry/includes/fdp-description.md

@@ -11,4 +11,4 @@ ms.custom: include
 ---
 
 
-A **[!INCLUDE [fdp](fdp-project-name.md)]** is built on an Azure AI Foundry resource. This project type allows for a simple setup, access to agents, and industry leading models from OpenAI, Mistral, Meta, and more. 
+An **[!INCLUDE [fdp](fdp-project-name.md)]** is managed under an Azure AI Foundry resource. It's a container for access management, data upload and integration, and monitoring. This lets you keep your work separated between use cases without needing to create extra Azure resources.

articles/ai-foundry/media/how-to/projects/projects-multi-setup.png

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn how to use prompt engineering to optimize your work with Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 07/02/2025
+ms.date: 09/23/2025
 ms.custom: references_regions, build-2023, build-2023-dataai
 manager: nitinme
 author: mrbullwinkle
@@ -14,11 +14,9 @@ recommendations: false
 
 # Prompt engineering techniques
 
-GPT-3, GPT-3.5, GPT-4, and GPT-4o models from OpenAI are prompt-based. With prompt-based models, the user interacts with the model by entering a text prompt, to which the model responds with a text completion. This completion is the model’s continuation of the input text. These techniques aren't recommended for o-series models.
+These techniques aren't recommended for reasoning models like gpt-5 and o-series models.
 
-While these models are extremely powerful, their behavior is also very sensitive to the prompt. This makes prompt construction an important skill to develop.
-
-Prompt construction can be difficult. In practice, the prompt acts to configure the model weights to complete the desired task, but it's more of an art than a science, often requiring experience and intuition to craft a successful prompt. The goal of this article is to help get you started with this learning process. It attempts to capture general concepts and patterns that apply to all GPT models. However it's important to understand that each model behaves differently, so the learnings might not apply equally to all models.
+Prompt construction can be difficult. In practice, the prompt acts assist the model complete the desired task, but it's more of an art than a science, often requiring experience and intuition to craft a successful prompt. The goal of this article is to help get you started with this learning process. It attempts to capture general concepts and patterns that apply to all GPT models. However it's important to understand that each model behaves differently, so the learnings might not apply equally to all models.
 
 ## Basics