Merge pull request #6229 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-25 22:04 UTC

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

articles/ai-foundry/agents/how-to/tools/deep-research-samples.md

@@ -24,7 +24,7 @@ The deep research tool is a **code-only release** and available for use using th
 
 |Azure AI foundry portal  | Python SDK |	C# SDK | JavaScript SDK | REST API |Basic agent setup | Standard agent setup |
 |---------|---------|---------|---------|---------|---------|---------|
-|  | ✔️ |  |  |  | ✔️  | ✔️ |
+|  | ✔️ | ✔️ | ✔️ |  | ✔️  | ✔️ |
 
 > [!NOTE]
 > Once the agent is running, some elements of the agent and thread runs can show up in the Azure AI Foundry user interface.

articles/ai-foundry/agents/how-to/tools/deep-research.md

@@ -5,7 +5,7 @@ description: Learn how to generate a synthetic dataset in Azure AI Foundry porta
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.topic: how-to
-ms.date: 05/20/2025
+ms.date: 07/25/2025
 ms.reviewer: vkann
 reviewer: anshirga
 ms.author: ssalgado

articles/ai-foundry/agents/media/tools/deep-research/bing-id.png

@@ -5,7 +5,7 @@ description: Learn about the different model capabilities that are available wit
 author: mrbullwinkle #ChrisHMSFT
 ms.author: mbullwin #chrhoder#
 manager: nitinme
-ms.date: 06/25/2025
+ms.date: 07/24/2025
 ms.service: azure-ai-openai
 ms.topic: conceptual
 ms.custom:
@@ -46,6 +46,21 @@ Azure OpenAI is powered by a diverse set of models with different capabilities a
 
 ### Capabilities
 
+> [!IMPORTANT]
+> There is a known issue impacting all GPT 4.1 series models where large tool/function call definitions exceeding 300,000 tokens will result in failures even though the 1 million token context limit of the models has not been reached.
+>
+> The errors can vary based on API call as well as underlying payload characteristics.
+>
+> **Chat Completions API error messages**:
+>
+> - `Error code: 400 - {'error': {'message': "This model's maximum context length is 300000 tokens. However, your messages resulted in 350564 tokens (100 in the messages, 350464 in the functions). Please reduce the length of the messages or functions.", 'type': 'invalid_request_error', 'param': 'messages', 'code': 'context_length_exceeded'}}`
+>
+> - `Error code: 400 - {'error': {'message': "Invalid 'tools[0].function.description': string too long. Expected a string with maximum length 1048576, but got a string with length 2778531 instead.", 'type': 'invalid_request_error', 'param': 'tools[0].function.description', 'code': 'string_above_max_length'}}`
+>
+> **Responses API error message:**
+>
+> - `Error code: 500 - {'error': {'message': 'The server had an error processing your request. Sorry about that! You can retry your request, or contact us through an Azure support request at: https://go.microsoft.com/fwlink/?linkid=2213926 if you keep seeing this error. (Please include the request ID d2008353-291d-428f-adc1-defb5d9fb109 in your email.)', 'type': 'server_error', 'param': None, 'code': None}}`
+
 |  Model ID  | Description | Context Window | Max Output Tokens | Training Data (up to)  |
 |  --- |  :--- |:--- |:---|:---: |
 | `gpt-4.1` (2025-04-14)   | - Text & image input <br> - Text output <br> - Chat completions API <br>- Responses API <br> - Streaming <br> - Function calling <br> Structured outputs (chat completions)   | - 1,047,576 <br> - 128,000 (provisioned managed deployments) <br> - 300,000 (batch deployments) | 32,768 | May 31, 2024 |

articles/ai-foundry/concepts/concept-synthetic-data.md

@@ -187,7 +187,7 @@ In the following example, replace `output` with the output of the function you w
 ```console
 curl https://YOUR_RESOURCE_NAME.openai.azure.com/openai/threads/thread_abc123/runs/run_123/submit_tool_outputs?api-version=2024-07-01-preview \
   -H "Content-Type: application/json" \
-  -H "api-key: 851c6e0b83744d8c8fc2a07eab098376" \
+  -H "api-key: $AZURE_OPENAI_API_KEY" \
   -d '{
     "tool_outputs": [{
       "tool_call_id": "call_123",

articles/ai-foundry/openai/concepts/models.md

@@ -68,7 +68,7 @@ The exact times and days when Auto-Optimize runs is determined by the Personaliz
 Personalizer uses these reward estimations to decide whether to change the current Learning Settings for others. Each estimation is a distribution curve, with upper and lower 95% confidence bounds. Personalizer will only apply new Learning Settings if:
   * They showed higher average rewards in the evaluation period, AND
   * They have a lower bound of the 95% confidence interval, that is *higher* than the lower bound of the 95% confidence interval of the online Learning Settings.
-This criteria to maximize the reward improvement, while trying to eliminate the probability of future rewards lost is managed by Personalizer and draws from research in [Seldonian algorithms](https://aisafety.cs.umass.edu/overview.html) and AI safety.
+This criteria to maximize the reward improvement, while trying to eliminate the probability of future rewards lost is managed by Personalizer and draws from research in [Seldonian algorithms](https://aisafety.cs.umass.edu/index.html) and AI safety.
 
 #### Limitations of Auto-Optimize
 
@@ -81,4 +81,4 @@ Automatic Optimization Preview is unavailable for Personalizer loops that have e
 * [Offline evaluations](concepts-offline-evaluation.md)
 * [Learning Policy and Settings](concept-active-learning.md)
 * [How To Analyze Personalizer with an Offline Evaluation](how-to-offline-evaluation.md) 
-* [Research in AI Safety](https://aisafety.cs.umass.edu/overview.html) 
+* [Research in AI Safety](https://aisafety.cs.umass.edu/index.html) 

articles/ai-foundry/openai/how-to/assistant-functions.md

@@ -67,7 +67,7 @@ The following preview features were released at the Build 2019 Conference:
 
 ### 2019 Build videos
 
-* [Deliver the Right Experiences & Content like Xbox with Azure AI Personalizer](https://azure.microsoft.com/resources/videos/build-2019-deliver-the-right-experiences-and-content-with-cognitive-services-personalizer/)
+* [Deliver the Right Experiences & Content like Xbox with Azure AI Personalizer](https://www.youtube.com/watch?v=agaJr25Y8Ek)
 
 ## Service updates
 

articles/ai-services/personalizer/concept-auto-optimization.md

@@ -6,8 +6,8 @@ services: machine-learning
 ms.service: azure-machine-learning
 ms.subservice: responsible-ai
 ms.topic:  how-to
-ms.author: scottpolly
-author: s-polly
+ms.author: lagayhar
+author: lgayhardt
 ms.reviewer: mesameki
 ms.date: 03/17/2025
 ms.custom: responsible-ml

articles/ai-services/personalizer/whats-new.md

@@ -5,8 +5,8 @@ description: Use Azure Machine Learning components to build machine learning pip
 services: machine-learning
 ms.service: azure-machine-learning
 ms.subservice: core
-ms.author: scottpolly
-author: s-polly
+ms.author: lagayhar
+author: lgayhardt
 ms.reviewer: keli19
 ms.date: 09/30/2024
 ms.topic: concept-article