Merge pull request #5832 from MicrosoftDocs/main

7/2/2025 11:00 AM IST Publish

Author: PhilKang0704

articles/ai-foundry/agents/concepts/model-region-support.md

@@ -1,4 +1,4 @@
----
+---
 title: Supported models in Azure AI Foundry Agent Service
 titleSuffix: Azure AI Foundry
 description: Learn about the models you can use with Azure AI Foundry Agent Service.
@@ -22,12 +22,12 @@ Azure OpenAI provides customers with choices on the hosting structure that fits
 - **Standard** is offered with a global deployment option, routing traffic globally to provide higher throughput.
 - **Provisioned** is also offered with a global deployment option, allowing customers to purchase and deploy provisioned throughput units across Azure global infrastructure.
 
-All deployments can perform the exact same inference operations, however the billing, scale, and performance are substantially different. To learn more about Azure OpenAI deployment types see [deployment types guide](../../../ai-services/openai/how-to/deployment-types.md).
+All deployments can perform the exact same inference operations, however the billing, scale, and performance are substantially different. To learn more about Azure OpenAI deployment types see [deployment types guide](../../openai/how-to/deployment-types.md).
 
 Azure AI Foundry Agent Service supports the following Azure OpenAI models in the listed regions.
 
 > [!NOTE]
-> * The following table is for serverless API deployment availability. For information on Provisioned Throughput Unit (PTU) availability, see [provisioned throughput](../../../ai-services/openai/concepts/provisioned-throughput.md) in the Azure OpenAI documentation. `GlobalStandard` customers also have access to [global standard models](../../../ai-services/openai/concepts/models.md#global-standard-model-availability). 
+> * The following table is for serverless API deployment availability. For information on Provisioned Throughput Unit (PTU) availability, see [provisioned throughput](../../openai/concepts/provisioned-throughput.md) in the Azure OpenAI documentation. `GlobalStandard` customers also have access to [global standard models](../../openai/concepts/models.md#global-standard-model-availability). 
 > * [Hub based projects](../../what-is-azure-ai-foundry.md#project-types) are limited to the following models: gpt-4o, gpt-4o-mini, gpt-4, gpt-35-turbo
 
 | REGION           | o1 | o3-mini | gpt-4.1, 2025-04-14 | gpt-4.1-mini, 2025-04-14 | gpt-4.1-nano, 2025-04-14 | gpt-4o, 2024-05-13 | gpt-4o, 2024-08-06 | gpt-4o, 2024-11-20 | gpt-4o-mini, 2024-07-18 | gpt-4, 0613 | gpt-4, turbo-2024-04-09 | gpt-4-32k, 0613 | gpt-35-turbo, 1106 | gpt-35-turbo, 0125 |

articles/ai-foundry/agents/faq.yml

@@ -25,7 +25,8 @@ sections:
       - question: |
           Where is this data stored?
         answer: |
-          Data is stored in a secure, Microsoft-managed storage account that is logically separated.  
+          Basic Setup: Data is stored in a secure, Microsoft-managed storage account that is logically separated.  
+          Standard Setup: Data is stored in your own Azure resources, giving you full ownership and control.
       - question: |
           How long is this data stored?
         answer: |

articles/ai-foundry/agents/how-to/tools/fabric.md

@@ -462,4 +462,4 @@ curl --request GET \
 
 ## Next steps
 
-[See the full sample for Fabric data agent.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_fabric.py)
+[See the full sample for Fabric data agent.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-agents/samples/agents_tools/sample_agents_fabric.py)

articles/ai-foundry/agents/how-to/tools/logic-apps.md

@@ -1,4 +1,4 @@
----
+---
 title: 'How to use Logic Apps with Azure AI Foundry Agent Service'
 titleSuffix: Azure AI Foundry
 description: Learn how to integrate Logic Apps with Azure AI Agents to execute tasks like sending emails.
@@ -21,7 +21,7 @@ This article demonstrates how to integrate Logic Apps with Azure AI Agents to ex
 ## Prerequisites
 
 1. Create a Logic App within the same resource group as your Azure AI Project in the Azure portal.
-1. Configure your Logic App to send emails by including an HTTP request trigger that accepts JSON with `to`, `subject`, and `body`. See the [Logic App Workflow guide](../../../../ai-services/openai/how-to/assistants-logic-apps.md) for more information.
+1. Configure your Logic App to send emails by including an HTTP request trigger that accepts JSON with `to`, `subject`, and `body`. See the [Logic App Workflow guide](../../../openai/how-to/assistants-logic-apps.md) for more information.
 1. Set the following environment variables:
    - `PROJECT_ENDPOINT`: The Azure AI Agents endpoint.
    - `MODEL_DEPLOYMENT_NAME`: The deployment name of the AI model.

articles/ai-foundry/agents/how-to/virtual-networks.md

@@ -167,7 +167,7 @@ Virtual networks enable you to specify which endpoints can make API calls to you
 
 ### Network rules
 
-All accounts and their corresponding projects are protected by default with **deny-by-default network rules**, requiring explicit configuration to allow access through private endpoints.
+All accounts and their corresponding projects are protected by default with **Public network access Disabled flag**, requiring explicit configuration to allow access through private endpoints.
 
 These rules apply to **all protocols**, including REST and WebSocket. Even internal testing tools like Azure portal's test consoles require explicit permission to access your account and its child resources—ensuring complete security across all agent projects.
 

articles/ai-foundry/agents/overview.md

@@ -1,4 +1,4 @@
----
+---
 title: What is Azure AI Foundry Agent Service?
 titleSuffix: Azure AI Foundry
 description: Learn how to create agents that apply advanced language models for workflow automation.
@@ -102,7 +102,7 @@ Azure AI Foundry Agent Service provides a production-ready foundation for deploy
 | **1. Visibility into conversations** | Full access to structured [threads](./concepts/threads-runs-messages.md#threads), including both user↔agent and agent↔agent messages. Ideal for UIs, debugging, and training |
 | **2. Multi-agent coordination** | Built-in support for agent-to-agent messaging. |
 | **3. Tool orchestration** | Server-side execution and retry of [tool calls](how-to\tools\overview.md) with structured logging. No manual orchestration required. |
-| **4. Trust and safety** | Integrated [content filters](../../ai-services/openai/how-to/content-filters.md) help prevent misuse and mitigate prompt injection risks (XPIA). all outputs are policy-governed. |
+| **4. Trust and safety** | Integrated [content filters](../openai/how-to/content-filters.md) help prevent misuse and mitigate prompt injection risks (XPIA). all outputs are policy-governed. |
 | **5. Enterprise integration** | Bring your own [storage](./how-to/use-your-own-resources.md#use-an-existing-azure-cosmos-db-for-nosql-account-for-thread-storage), [Azure AI Search index](./how-to/use-your-own-resources.md#use-an-existing-azure-ai-search-resource), and [virtual network](how-to\virtual-networks.md) to meet compliance needs. |
 | **6. Observability and debugging** | Threads, tool invocations, and message traces are [fully traceable](concepts\tracing.md); [Application Insights integration](./how-to/metrics.md) for telemetry |
 | **7. Identity and policy control** | Built on Microsoft Entra with full support for RBAC, audit logs, and enterprise conditional access. |

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

@@ -1,4 +1,4 @@
----
+---
 title: Quotas and limits for Azure AI Foundry Agent Service
 titleSuffix: Azure AI Foundry
 description: Learn about the quotas and limits for when you use Azure AI Foundry Agent Service.
@@ -30,7 +30,7 @@ The 2,000,000 agent limit refers to the maximum number of distinct Agent resourc
 
 ## Quotas and limits for Azure OpenAI models
 
-See the [Azure OpenAI](../../ai-services/openai/quotas-limits.md) for current quotas and limits for the Azure OpenAI models that you can use with Azure AI Foundry Agent Service. 
+See the [Azure OpenAI](../openai/quotas-limits.md) for current quotas and limits for the Azure OpenAI models that you can use with Azure AI Foundry Agent Service. 
 
 ## Next steps
 

articles/ai-foundry/concepts/ai-red-teaming-agent.md

@@ -1,4 +1,4 @@
----
+---
 title: AI Red Teaming Agent
 titleSuffix: Azure AI Foundry
 description: This article provides conceptual overview of the AI Red Teaming Agent.
@@ -47,7 +47,7 @@ We encourage teams to use the AI Red Teaming Agent to run automated scans throug
 - Development: Upgrading models within your application or creating fine-tuned models for your specific application.
 - Pre-deployment: Before deploying GenAI applications to productions.
 
-In production, we recommend implementing **safety mitigations** such as [Azure AI Content Safety filters](../../ai-services/content-safety/overview.md) or implementing safety system messages using our [templates](../../ai-services/openai/concepts/safety-system-message-templates.md).
+In production, we recommend implementing **safety mitigations** such as [Azure AI Content Safety filters](../../ai-services/content-safety/overview.md) or implementing safety system messages using our [templates](../openai/concepts/safety-system-message-templates.md).
 
 ## How AI Red Teaming works
 
@@ -109,6 +109,6 @@ Learn more about the tools leveraged by the AI Red Teaming Agent.
 
 The most effective strategies for risk assessment we’ve seen leverage automated tools to surface potential risks, which are then analyzed by expert human teams for deeper insights. If your organization is just starting with AI red teaming, we encourage you to explore the resources created by our own AI red team at Microsoft to help you get started.
 
-- [Planning red teaming for large language models (LLMs) and their applications](../../ai-services/openai/concepts/red-teaming.md)
+- [Planning red teaming for large language models (LLMs) and their applications](../openai/concepts/red-teaming.md)
 - [Three takeaways from red teaming 100 generative AI products](https://www.microsoft.com/security/blog/2025/01/13/3-takeaways-from-red-teaming-100-generative-ai-products/)
 - [Microsoft AI Red Team building future of safer AI](https://www.microsoft.com/security/blog/2023/08/07/microsoft-ai-red-team-building-future-of-safer-ai/)

articles/ai-foundry/concepts/content-filtering.md

@@ -1,4 +1,4 @@
----
+---
 title: Azure AI Foundry content filtering
 titleSuffix: Azure AI Foundry
 description: Learn about the content filtering capabilities of Azure OpenAI in Azure AI Foundry portal.
@@ -20,7 +20,7 @@ author: PatrickFarley
 [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) includes a content filtering system that works alongside core models and image generation models.
 
 > [!IMPORTANT]
-> The content filtering system isn't applied to prompts and completions processed by the Whisper model in Azure OpenAI in Azure AI Foundry Models. Learn more about the [Whisper model in Azure OpenAI](../../ai-services/openai/concepts/models.md).
+> The content filtering system isn't applied to prompts and completions processed by the Whisper model in Azure OpenAI in Azure AI Foundry Models. Learn more about the [Whisper model in Azure OpenAI](../openai/concepts/models.md).
 
 ## How it works 
 
@@ -73,12 +73,12 @@ You can also enable the following special output filters:
 
 ### Configurability (preview)
 
-[!INCLUDE [content-filter-configurability](../../ai-services/openai/includes/content-filter-configurability.md)]
+[!INCLUDE [content-filter-configurability](../openai/includes/content-filter-configurability.md)]
 
 
 ## Related content
 
-- Learn more about the [underlying models that power Azure OpenAI](../../ai-services/openai/concepts/models.md).
+- Learn more about the [underlying models that power Azure OpenAI](../openai/concepts/models.md).
 - Azure AI Foundry content filtering is powered by [Azure AI Content Safety](../../ai-services/content-safety/overview.md).
 - Learn more about understanding and mitigating risks associated with your application: [Overview of Responsible AI practices for Azure OpenAI models](/azure/ai-foundry/responsible-ai/openai/overview).
 - Learn more about evaluating your generative AI models and AI systems via [Azure AI Evaluation](https://aka.ms/genaiopsevals). 

articles/ai-foundry/concepts/fine-tuning-overview.md

@@ -1,4 +1,4 @@
----
+---
 title: Fine-tune models with Azure AI Foundry
 titleSuffix: Azure AI Foundry
 description: This article explains what fine-tuning is and under what circumstances you should consider doing it.
@@ -39,7 +39,7 @@ Before picking a model, it's important to select the fine-tuning product that ma
 
 For most customers, serverless provides the best balance of ease-of-use, cost efficiency, and access to premium models. This document focuses on serverless options.
 
-To find steps to fine-tuning a model in AI Foundry, see [Fine-tune Models in AI Foundry](../how-to/fine-tune-serverless.md) or [Fine-tune models using managed compute](../how-to/fine-tune-managed-compute.md). For detailed guidance on OpenAI fine-tuning see [Fine-tune Azure OpenAI Models](../../ai-services/openai/how-to/fine-tuning.md).
+To find steps to fine-tuning a model in AI Foundry, see [Fine-tune Models in AI Foundry](../how-to/fine-tune-serverless.md) or [Fine-tune models using managed compute](../how-to/fine-tune-managed-compute.md). For detailed guidance on OpenAI fine-tuning see [Fine-tune Azure OpenAI Models](../openai/how-to/fine-tuning.md).
 
 ## Training Techniques
 
@@ -90,21 +90,21 @@ This table provides an overview of the models available
 3. **Choose your technique:** Begin with Supervised Fine-Tuning (SFT) unless you have specific requirements for reasoning models / RFT.
 4. **Iterate and evaluate:** Fine-tuning is an iterative process—start with a baseline, measure performance, and refine your approach based on results.
 
-To find steps to fine-tuning a model in AI Foundry, see [Fine-tune Models in AI Foundry](../how-to/fine-tune-serverless.md), [Fine-tune Azure OpenAI Models](../../ai-services/openai/how-to/fine-tuning.md), or [Fine-tune models using managed compute](../how-to/fine-tune-managed-compute.md).
+To find steps to fine-tuning a model in AI Foundry, see [Fine-tune Models in AI Foundry](../how-to/fine-tune-serverless.md), [Fine-tune Azure OpenAI Models](../openai/how-to/fine-tuning.md), or [Fine-tune models using managed compute](../how-to/fine-tune-managed-compute.md).
 
 ## Fine-Tuning Availability
 
 Now that you know when to use fine-tuning for your use case, you can go to Azure AI Foundry to find models available to fine-tune.
 
 **To fine-tune an AI Foundry model using Serverless** you must have a hub/project in the region where the model is available for fine tuning. See [Region availability for models in serverless API deployment](../how-to/deploy-models-serverless-availability.md) for detailed information on model and region availability, and [How to Create a Hub based project](../how-to/create-projects.md) to create your project.
 
-**To fine-tune an OpenAI model** you can use an Azure OpenAI Resource, a Foundry resource or default project, or a hub/project. GPT 4.1, 4.1-mini and 4.1-nano are available in all regions with Global Training. For regional availability, see [Regional Availability and Limits for Azure OpenAI Fine Tuning](../../ai-services/openai/concepts/models.md). See [Create a project for Azure AI Foundry](../how-to/create-projects.md) for instructions on creating a new project.
+**To fine-tune an OpenAI model** you can use an Azure OpenAI Resource, a Foundry resource or default project, or a hub/project. GPT 4.1, 4.1-mini and 4.1-nano are available in all regions with Global Training. For regional availability, see [Regional Availability and Limits for Azure OpenAI Fine Tuning](../openai/concepts/models.md). See [Create a project for Azure AI Foundry](../how-to/create-projects.md) for instructions on creating a new project.
 
 **To fine-tune a model using Managed Compute** you must have a hub/project and available VM quota for training and inferencing. See [Fine-tune models using managed compute (preview)](../how-to/fine-tune-managed-compute.md) for more details on how to use managed compute fine tuning, and [How to Create a Hub based project](../how-to/create-projects.md) to create your project.
 
 
 ## Related content
 
 - [Fine-tune models using managed compute (preview)](../how-to/fine-tune-managed-compute.md)
-- [Fine-tune an Azure OpenAI model in Azure AI Foundry portal](../../ai-services/openai/how-to/fine-tuning.md?context=/azure/ai-studio/context/context)
+- [Fine-tune an Azure OpenAI model in Azure AI Foundry portal](../openai/how-to/fine-tuning.md?context=/azure/ai-studio/context/context)
 - [Fine-tune models using serverless API deployment](../how-to/fine-tune-serverless.md)