Merge pull request #6148 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-21 22:04 UTC

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

articles/ai-foundry/openai/how-to/fine-tune-test.md

@@ -48,7 +48,7 @@ resource_group = "<YOUR_RESOURCE_GROUP_NAME>"
 resource_name = "<YOUR_AZURE_OPENAI_RESOURCE_NAME>"
 model_deployment_name = "gpt41-mini-candidate-01" # custom deployment name that you will use to reference the model when making inference calls.
 
-deploy_params = {'api-version': "2024-10-21"} 
+deploy_params = {'api-version': "2025-04-01-preview"} 
 deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}
 
 deploy_data = {
@@ -90,7 +90,7 @@ The following example shows how to use the REST API to create a model deployment
 
 
 ```bash
-curl -X POST "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>api-version=2024-10-21" \
+curl -X POST "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>api-version=2025-04-01-preview" \
   -H "Authorization: Bearer <TOKEN>" \
   -H "Content-Type: application/json" \
   -d '{
@@ -180,7 +180,7 @@ print(response.choices[0].message.content)
 ## [REST](#tab/rest)
 
 ```bash
-curl $AZURE_OPENAI_ENDPOINT/openai/deployments/<deployment_name>/chat/completions?api-version=2024-10-21 \
+curl $AZURE_OPENAI_ENDPOINT/openai/deployments/<deployment_name>/chat/completions?api-version=2025-04-01-preview \
   -H "Content-Type: application/json" \
   -H "api-key: $AZURE_OPENAI_API_KEY" \
   -d '{"messages":[{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Does Azure OpenAI support customer managed keys?"},{"role": "assistant", "content": "Yes, customer managed keys are supported by Azure OpenAI."},{"role": "user", "content": "Do other Azure AI services support this too?"}]}'
@@ -203,7 +203,7 @@ To use the [Deployments - Delete REST API](/rest/api/aiservices/accountmanagemen
 Below is the REST API example to delete a deployment:
 
 ```bash
-curl -X DELETE "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>api-version=2024-10-21" \
+curl -X DELETE "https://management.azure.com/subscriptions/<SUBSCRIPTION>/resourceGroups/<RESOURCE_GROUP>/providers/Microsoft.CognitiveServices/accounts/<RESOURCE_NAME>/deployments/<MODEL_DEPLOYMENT_NAME>api-version=2025-04-01-preview" \
   -H "Authorization: Bearer <TOKEN>"
 ```
 

articles/ai-foundry/openai/how-to/latency.md

@@ -5,7 +5,7 @@ description: Learn about performance and latency with Azure OpenAI
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
-ms.date: 07/02/2025
+ms.date: 07/21/2025
 author: mrbullwinkle 
 ms.author: mbullwin
 recommendations: false
@@ -90,13 +90,16 @@ Latency varies based on what model you're using. For an identical request, expec
 
 When you send a completion request to the Azure OpenAI endpoint, your input text is converted to tokens that are then sent to your deployed model. The model receives the input tokens and then begins generating a response. It's an iterative sequential process, one token at a time. Another way to think of it is like a for loop with `n tokens = n iterations`. For most models, generating the response is the slowest step in the process.  
 
-At the time of the request, the requested generation size (max_tokens parameter) is used as an initial estimate of the generation size. The compute-time for generating the full size is reserved by the model as the request is processed. Once the generation is completed, the remaining quota is released. Ways to reduce the number of tokens:
+At the time of the request, the requested generation size (`max_tokens` parameter) is used as an initial estimate of the generation size. The compute-time for generating the full size is reserved by the model as the request is processed. Once the generation is completed, the remaining quota is released. Ways to reduce the number of tokens:
 - Set the `max_tokens` parameter on each call as small as possible.
 - Include stop sequences to prevent generating extra content.
 - Generate fewer responses: The best_of & n parameters can greatly increase latency because they generate multiple outputs. For the fastest response, either don't specify these values or set them to 1.
 
 In summary, reducing the number of tokens generated per request reduces the latency of each request.
 
+> [!NOTE]
+> `max_tokens` only changes the length of a response and in some cases might truncate it. The parameter doesn't change the quality of the response.
+
 ### Streaming
 Setting `stream: true` in a request makes the service return tokens as soon as they're available, instead of waiting for the full sequence of tokens to be generated. It doesn't change the time to get all the tokens, but it reduces the time for first response. This approach provides a better user experience since end-users can read the response as it is generated. 
 

articles/ai-foundry/responsible-ai/agents/transparency-note.md

@@ -81,7 +81,7 @@ Key features of Azure AI Agent Service include:
 
 ### Agent Catalog 
 
-Azure AI Foundry Agent Service offers a range of different Agent code samples that can get you started toward building Agents for your specific use case needs. Each Agent code sample should be deployed with [risk management considerations](#considerations-when-choosing-a-use-case) in mind. See the [list of Agent code samples](/azure/ai-services/agents/how-to/agent-catalog#view-all-available-code-samples) currently available.  
+Azure AI Foundry Agent Service offers a range of different Agent code samples that can get you started toward building Agents for your specific use case needs. Each Agent code sample should be deployed with [risk management considerations](#considerations-when-choosing-a-use-case) in mind. See the [list of Agent code samples](/azure/ai-foundry/agents/overview#agent-catalog) currently available.  
 
 ### Extensibility capabilities 
 
@@ -129,7 +129,7 @@ Azure AI Agent Service is **flexible and use-case agnostic.** This presents mult
 * **Education: Assisting with Research and Reference Gathering:** A teacher relies on an agent to gather age-appropriate articles and resources from reputable sources for a planetary science lesson; the teacher verifies the materials for factual accuracy and adjusts them to fit the curriculum, ensuring students receive trustworthy content.
 * **Manufacturing: Inventory Oversight and Task Scheduling:** A factory supervisor deploys an agent to monitor inventory levels, schedule restocking when supplies run low, and optimize shift rosters; management confirms the agent’s suggestions and retains final decision-making authority.
 
-Agent code samples have specific intended uses that are configurable by developers to carefully build upon, implement, and deploy agents. See [list of Agent code samples](/azure/ai-services/agents/how-to/agent-catalog#view-all-available-code-samples).
+Agent code samples have specific intended uses that are configurable by developers to carefully build upon, implement, and deploy agents. See [list of Agent code samples](/azure/ai-foundry/agents/overview#agent-catalog).
 
 
 #### Considerations when choosing a use case

articles/ai-foundry/responsible-ai/computer-vision/image-analysis-characteristics-and-limitations.md

@@ -70,8 +70,8 @@ For information see [Image requirements](/azure/ai-services/computer-vision/over
 
 ## Next steps
 
-* [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-transparency-note)
-* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-guidance-for-integration)
+* [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-transparency-note)
+* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-guidance-for-integration)
 * [Image Analysis Overview](/azure/ai-services/computer-vision/overview-image-analysis)
 * [QuickStart your Image Analysis use case development](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library)
-* [Data, privacy, and security for Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-data-privacy-security)
+* [Data, privacy, and security for Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-data-privacy-security)

articles/ai-foundry/responsible-ai/computer-vision/image-analysis-data-privacy-security.md

@@ -75,7 +75,7 @@ For additional security best practices and information, visit [Azure AI services
 
 ## Next steps
 
-* [Characteristics and limitations](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-characteristics-and-limitations)
-* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-guidance-for-integration)
+* [Characteristics and limitations](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-characteristics-and-limitations)
+* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-guidance-for-integration)
 * [Quickstart your Image Analysis use case development](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library)
-* [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-transparency-note)
+* [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-transparency-note)

articles/ai-foundry/responsible-ai/computer-vision/image-analysis-guidance-for-integration.md

@@ -44,9 +44,9 @@ A successful privacy approach empowers individuals with information, and provide
 * Don't share any data without explicit consent from affected stakeholders or data owners, and minimize the data that is shared.
 
 ## Next steps
-* [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-transparency-note)
-* [Characteristics and limitations](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-characteristics-and-limitations)
-* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-guidance-for-integration)
+* [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-transparency-note)
+* [Characteristics and limitations](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-characteristics-and-limitations)
+* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-guidance-for-integration)
 * [QuickStart your Image Analysis use case development](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library)
-* [Data, privacy, and security for Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-data-privacy-security)
+* [Data, privacy, and security for Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-data-privacy-security)
 

articles/ai-foundry/responsible-ai/computer-vision/image-analysis-transparency-note.md

@@ -196,7 +196,7 @@ This section discusses Image Analysis and key considerations for using this tech
 
 You can report feedback on the content filtering system [through support](/azure/ai-services/cognitive-services-support-options).
 
-To ensure you have properly mitigated risks in your application, you should evaluate all potential harms carefully, follow guidance in the [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-transparency-note) and add scenario-specific mitigation as needed.
+To ensure you have properly mitigated risks in your application, you should evaluate all potential harms carefully, follow guidance in the [Transparency Note](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-transparency-note) and add scenario-specific mitigation as needed.
 
 ### Recommendations for preserving privacy
 
@@ -272,7 +272,7 @@ Based on the model's performance, you need to decide if the model is appropriate
 
 ## Next steps
 
-* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-guidance-for-integration)
+* [Responsible deployment of Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-guidance-for-integration)
 * [Image Analysis Overview](/azure/ai-services/computer-vision/overview-image-analysis)
 * [QuickStart your Image Analysis use case development](/azure/ai-services/computer-vision/quickstarts-sdk/image-analysis-client-library)
-* [Data, privacy, and security for Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/imageanalysis-data-privacy-security)
+* [Data, privacy, and security for Image Analysis](/azure/ai-foundry/responsible-ai/computer-vision/image-analysis-data-privacy-security)

articles/ai-foundry/responsible-ai/face/characteristics-and-limitations.md

@@ -40,7 +40,7 @@ You can use the [Fairness Assessment Sample Notebook](https://go.microsoft.com/f
 
 ## How accurate is the facial liveness detection model? 
 
-The facial liveness detection solution from Microsoft is conformant to [ISO/IEC 30107-3:2017 – Biometric presentation attack detection – Part 3: Testing and reporting](https://webstore.ansi.org/standards/iso/isoiec301072017-1662258) standard as validated by iBeta level 1 and level 2 conformance testing. 
+The facial liveness detection solution from Microsoft achieved a 0% penetration rate in [iBeta Level 1 and Level 2 Presentation Attack Detection (PAD) tests](https://servicetrust.microsoft.com/DocumentPage/ea3fa18f-3940-4c0b-aa96-41cb50898aee), conducted by a NIST/NVLAP-accredited laboratory and conformant to the [ISO/IEC 30107-3 PAD international standard](https://www.iso.org/standard/79520.html).
 
 ## Tradeoffs