Merge pull request #5458 from MicrosoftDocs/main

6/10/2025 AM Publish

Author: Taojunshen

articles/ai-foundry/foundry-local/reference/reference-rest.md

@@ -78,9 +78,6 @@ _---Standard OpenAI Properties---_
       The arguments to pass to the function.
 - `metadata` (object, optional)  
   A dictionary of metadata key-value pairs.
-
-_---Additional Foundry Local Properties---_
-
 - `top_k` (number, optional)  
   The number of highest probability vocabulary tokens to keep for top-k-filtering.
 - `random_seed` (integer, optional)  
@@ -432,10 +429,32 @@ Sets the active GPU device.
 
 Downloads a model to local storage.
 
+> [!NOTE]
+> Model downloads can take significant time, especially for large models. We recommend setting a high timeout for this request to avoid premature termination.
+
 **Request Body:**
 
-- `model` (string)  
-  The model name to download.
+- `model` (`WorkspaceInferenceModel` object)  
+  - `Uri` (string)  
+    The model URI to download.
+  - `Name` (string)
+    The model name.
+  - `ProviderType` (string, optional)  
+    The provider type (e.g., `"AzureFoundryLocal"`,`"HuggingFace"`).
+  - `Path` (string, optional)  
+    The remote path where the model is located stored. For example, in a Hugging Face repository, this would be the path to the model files.
+  - `PromptTemplate` (`Dictionary<string, string>`, optional)  
+    Contains:
+    - `system` (string, optional)  
+      The template for the system message.
+    - `user` (string, optional)
+      The template for the user's message.
+    - `assistant` (string, optional)  
+      The template for the assistant's response.
+    - `prompt` (string, optional)  
+      The template for the user-assistant interaction.
+  - `Publisher` (string, optional)  
+      The publisher of the model.
 - `token` (string, optional)  
   Authentication token for protected models (GitHub or Hugging Face).
 - `progressToken` (object, optional)  
@@ -467,12 +486,22 @@ During download, the server streams progress updates in the format:
 
 - Request body
 
-  ```json
-  {
-    "model": "Phi-4-mini-instruct-generic-cpu",
-    "ignorePipeReport": true
+```json
+{
+  "model":{
+    "Uri": "azureml://registries/azureml/models/Phi-4-mini-instruct-generic-cpu/versions/4",
+    "ProviderType": "AzureFoundryLocal",
+    "Name": "Phi-4-mini-instruct-generic-cpu",
+    "Publisher": "",
+    "promptTemplate" : {
+      "system": "<|system|>{Content}<|end|>",
+      "user": "<|user|>{Content}<|end|>", 
+      "assistant": "<|assistant|>{Content}<|end|>", 
+      "prompt": "<|user|>{Content}<|end|><|assistant|>"
+    }
   }
-  ```
+}
+```
 
 - Response stream
 

articles/ai-services/agents/how-to/tools/sharepoint-samples.md

@@ -0,0 +1,97 @@
+---
+title: 'How to use the SharePoint tool'
+titleSuffix: Azure AI Foundry
+description: Find examples on how to ground agents with SharePoint.
+services: cognitive-services
+manager: nitinme
+ms.service: azure-ai-agent-service
+ms.topic: how-to
+ms.date: 06/05/2025
+author: aahill
+ms.author: aahi
+ms.custom: azure-ai-agents-code
+zone_pivot_groups: selection-sharepoint
+---
+
+# How to use the SharePoint tool
+
+Use this article to find step-by-step instructions and code samples for using the SharePoint tool in Azure AI Foundry Agent Service.
+
+## Create an agent
+
+Follow the [REST API Quickstart](../../quickstart.md?pivots=rest-api#api-call-information) to set the right values for the environment variables `AGENT_TOKEN`, `AZURE_AI_FOUNDRY_PROJECT_ENDPOINT` and `API_VERSION`.
+
+```bash
+curl --request POST \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/assistants?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+        "instructions": "You are a helpful agent.",
+        "name": "my-agent",
+        "model": "gpt-4o",
+        "tools": [
+          {
+            "type": "sharepoint_grounding",
+            "sharepoint_grounding": {
+                "connections": [
+                    {
+                        "connection_id": "/subscriptions/<sub-id>/resourceGroups/<your-rg-name>/providers/Microsoft.CognitiveServices/accounts/<your-ai-services-name>/projects/<your-project-name>/connections/<your-sharepoint-connection-name>"
+                    }
+                ]
+            }
+          }
+        ]
+      }'
+```
+
+## Create a thread
+
+```bash
+curl --request POST \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/threads?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d ''
+```
+
+### Add a user question to the thread
+
+```bash
+curl --request POST \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/threads/thread_abc123/messages?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+      "role": "user",
+      "content": "What is the weather in Seattle?"
+    }'
+```
+
+## Run the thread
+
+```bash
+curl --request POST \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/threads/thread_abc123/runs?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "assistant_id": "asst_abc123",
+  }'
+```
+
+## Retrieve the status of the run
+
+```bash
+curl --request GET \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/threads/thread_abc123/runs/run_abc123?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN"
+```
+
+## Retrieve the agent response
+
+```bash
+curl --request GET \
+  --url $AZURE_AI_FOUNDRY_PROJECT_ENDPOINT/threads/thread_abc123/messages?api-version=$API_VERSION \
+  -H "Authorization: Bearer $AGENT_TOKEN"
+```

articles/ai-services/agents/how-to/tools/sharepoint.md

@@ -0,0 +1,51 @@
+---
+title: 'How to use Microsoft SharePoint content with Azure AI Agent Service'
+titleSuffix: Azure OpenAI
+description: Learn how to ground Azure AI Agents using Microsoft SharePoint content.
+services: cognitive-services
+manager: nitinme
+ms.service: azure-ai-agent-service
+ms.topic: how-to
+ms.date: 06/05/2025
+author: aahill
+ms.author: aahi
+ms.custom: azure-ai-agents
+---
+# Use the Microsoft SharePoint tool (preview)
+
+Integrate your agents with the **Microsoft SharePoint** to chat with your private documents securely. You can connect to your SharePoint site, such as `contoso.sharepoint.com/sites/policies` to ground your Agents with that data. When a user sends a query, the agent will determine if SharePoint should be leveraged or not. If so, it will send a query using the SharePoint tool, which checks if the user has a Microsoft 365 Copilot license and use managed identity to retrieve relevant documents they have access to. The scope of retrieval includes all supported documents in this SharePoint site. Lastly, the agent will generate responses based on retrieved information. With identity passthrough (On-Behalf-Of) authorization, this integration simplifies access to enterprise data in SharePoint while maintaining robust security, ensuring proper access control and enterprise-grade protection. 
+
+## Usage support
+
+|Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |
+|---------|---------|---------|---------|---------|---------|---------|
+| ✔️ | - | - | - | ✔️ | ✔️ | ✔️ |
+
+## Prerequisites
+
+* Developers and end users have Microsoft 365 Copilot license.
+* Developers and end users have at least `Azure AI User` RBAC role. 
+* Developers and end users have at least `READ` access to the SharePoint site.
+
+## Setup  
+
+> [!NOTE]
+> * Supported document types: text data in the following format: `.pdf`, `.docx`, `.ppt`, `.txt`, `.aspx` 
+> * We recommend you start with SharePoint sites that have: a simple folder structure and a small number of short documents. 
+
+1. Create an agent by following the steps in the [quickstart](../../quickstart.md).
+
+1. You can add the SharePoint tool to an agent programatically using the code examples listed at the top of this article, or the Azure AI Foundry portal. If you want to use the portal, in either the **Create and debug** or **Agent playground** screen for your agent, scroll down the setup pane on the right to knowledge. Then select **Add**.
+
+   :::image type="content" source="../../media/tools/knowledge-tools.png" alt-text="A screenshot showing the available tool categories in the Azure AI Foundry portal." lightbox="../../media/tools/knowledge-tools.png":::
+
+1. Select **SharePoint** and follow the prompts to add the tool. You can only add one per agent.
+
+1. Click to add a new connection. Once you have added a connection, you can directly select from existing list.
+   1. To create a new connection, you need to find `site_url` in your SharePoint site. You can add either a SharePoint site or a SharePoint folder. For a SharePoint site, it will look like `https://microsoft.sharepoint.com/teams/<site_name>`. For a SharePoint folder, it will look like `https://microsoft.sharepoint.com/teams/<site_name>/Shared%20documents/<folder_name>`
+
+   1. Then, you can add it to your connection. Make sure you have selected the **is secret** option.
+
+## Next steps
+
+[See the full sample for SharePoint.](https://github.com/Azure/azure-sdk-for-python/blob/main/sdk/ai/azure-ai-projects/samples/agents/sample_agents_sharepoint.py)

articles/ai-services/agents/toc.yml

@@ -93,6 +93,13 @@ items:
               displayName: azure functions, functions
             - name: How to use Azure Functions
               href: how-to/tools/azure-functions-samples.md
+        - name: SharePoint
+          items:
+            - name: Overview
+              href: how-to/tools/sharepoint.md
+              displayName: sharepoint
+            - name: How to use SharePoint
+              href: how-to/tools/sharepoint-samples.md
     - name: Enterprise features
       items: 
         - name: Use your own resources

articles/ai-services/openai/includes/fine-tune-models.md

@@ -26,20 +26,24 @@ ms.custom:
 | `gpt-4o` (2024-08-06) | East US2 <br> North Central US <br> Sweden Central | - | Input: 128,000 <br> Output: 16,384  <br> Training example context length: 65,536 | Oct 2023 | Text & Vision to Text |
 | `gpt-4.1` (2025-04-14) | North Central US <br> Sweden Central | ✅ | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 65,536 | May 2024 | Text & Vision to Text |
 | `gpt-4.1-mini` (2025-04-14) | North Central US <br> Sweden Central | ✅ | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 65,536 | May 2024 | Text to Text |
-| `gpt-4.1-nano` (2025-04-14) | North Central US <br> Sweden Central | ✅ | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 32,768 | May 2024 | Text to Text |
+| `gpt-4.1-nano` (2025-04-14) | North Central US <br> Sweden Central | - | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 32,768 | May 2024 | Text to Text |
 | `o4-mini` (2025-04-16) | East US2 <br> Sweden Central | - | Input: 128,000 <br> Output: 16,384 <br> Training example context length: 65,536 | May 2024 | Text to Text |
 
 > [!NOTE]
 > **Global** training (in Public Preview) provides [more affordable](https://aka.ms/aoai-pricing) training per-token, but does not offer [data residency](https://aka.ms/data-residency). It is currently available to Azure OpenAI resources in the following regions, with more regions coming soon:
 >- Australia East
 >- Brazil South
+>- EastUS2
 >- France Central
 >- Germany West Central
 >- Italy North
 >- Japan East _(no vision support)_
 >- Korea Central
+>- North Central US
 >- Norway East
 >- Poland Central
 >- Southeast Asia
->- Spain Central
 >- South Africa North
+>- Spain Central
+>- Sweden Central
+>- Switzerland West