Resolve merge conflict: move new Azure OpenAI TOC structure to SDK + API Reference section

Author: sdgilley

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

@@ -6,10 +6,10 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 07/17/2025
+ms.date: 08/01/2025
 author: aahill
 ms.author: aahi
-ms.custom: azure-ai-agents
+ms.custom: azure-ai-agents, references_regions
 ---
 
 # Azure AI Foundry Agent Service file search tool
@@ -30,6 +30,11 @@ File search augments agents with knowledge from outside its model, such as propr
 
 ### Usage support
 
+> [!NOTE]
+> The file search tool is currently unavailable in the following regions:
+>    * Italy north
+>    * Brazil south
+
 |Azure AI foundry support  | Python SDK |	C# SDK | JavaScript SDK | REST API | Basic agent setup | Standard agent setup |
 |---------|---------|---------|---------|---------|---------|---------|
 | ✔️  | ✔️ | ✔️ | ✔️ | ✔️ | File upload only | File upload and using  bring-your-own blob storage | 
@@ -74,7 +79,7 @@ Vector store objects give the file search tool the ability to search your files.
 Similarly, these files can be removed from a vector store by either:
 
 * Deleting the vector store file object or,
-* By deleting the underlying file object, which removes the file it from all vector_store and code_interpreter configurations across all agents and threads in your organization
+* By deleting the underlying file object, which removes the file from all vector_store and code_interpreter configurations across all agents and threads in your organization
 
 The maximum file size is 512 MB. Each file should contain no more than 5,000,000 tokens per file (computed automatically when you attach a file).
 

articles/ai-foundry/agents/how-to/tools/file-search.md

@@ -6,7 +6,7 @@ services: cognitive-services
 manager: nitinme
 ms.service: azure-ai-agent-service
 ms.topic: how-to
-ms.date: 05/12/2025
+ms.date: 08/01/2025
 author: aahill
 ms.author: aahi
 ms.reviewer: fosteramanda
@@ -15,7 +15,7 @@ ms.custom: azure-ai-agents
 
 # Create a new network-secured environment with user-managed identity
 
-Azure AI Foundry Agent Service offers **Standard Setup with private networking** environment setup, allowing you to bring your own (BYO) private virtual network. This set up creates an isolated network environment that lets you securely access data and perform actions while maintaining full control over your network infrastructure. This guide provides a step-by-step walkthrough of the setup process and outlines all necessary requirements.
+Azure AI Foundry Agent Service offers **Standard Setup with private networking** environment setup, allowing you to bring your own (BYO) private virtual network. This setup creates an isolated network environment that lets you securely access data and perform actions while maintaining full control over your network infrastructure. This guide provides a step-by-step walkthrough of the setup process and outlines all necessary requirements.
 
 ## Security features
 
@@ -39,7 +39,7 @@ For customers without an existing virtual network, the Standard Setup with Priva
     - **Exception:** You may connect your Foundry Project to models deployed in a different region (on another AI Foundry or Azure OpenAI resource) by configuring an appropriate AI Services connection on the Project's [capability host](/azure/templates/microsoft.cognitiveservices/accounts/projects/capabilityhosts).
 - **Region availability**:
   - For supported regions for Foundry workspace resources, see: [Azure AI Foundry project region availability](../../reference/region-support.md#azure-ai-foundry-projects).
-  - For supported regions for model deployments, see: [Azure OpenAI model region support](../concepts/model-region-support.md#azure-openai-models).
+  - For supported regions for model deployments, see: [Azure OpenAI model region support](../concepts/model-region-support.md#available-models).
 - **Azure Blob Storage**: using Azure Blob Storage files with the File Search tool isn't supported.
 
 ## Prerequisites
@@ -79,7 +79,7 @@ For customers without an existing virtual network, the Standard Setup with Priva
 ## Configure a new network-secured environment 
 
 > [!NOTE]
-> - Programmatic deployment is required to set up a network-secured environment for Azure AI Foundry Agent Service. Deployment through the Azure portal is currently not supported.
+> - Programmatic deployment is required to setup a network-secured environment for Azure AI Foundry Agent Service. Deployment through the Azure portal is currently not supported.
 > - If you want to delete your Foundry resource and Standard Agent with secured network set-up, delete your AI Foundry resource and virtual network last. Before deleting the virtual network, ensure to delete and [purge](../../../ai-services/recover-purge-resources.md#purge-a-deleted-resource) your AI Foundry resource.
 > - In the Standard Setup, agents use customer-owned, single-tenant resources. You have full control and visibility over these resources, but you incur costs based on your usage.
 
@@ -119,7 +119,7 @@ The following DNS zones are configured:
 Virtual networks enable you to specify which endpoints can make API calls to your resources. The Azure service automatically rejects API calls from devices outside your defined network. You can establish allowed networks using either formula-based definitions or by creating an exhaustive list of permitted endpoints. This security layer can be combined with other security measures for enhanced protection.
 
 > [!NOTE]
-> If you bring your existing virtual network and subnet with the *Microsoft.App/environments* delegation, the minimize size of your subnet should be /27 (32 addresses). We recommend a subnet size of /24 (256 addresses) and is the default subnet size set in the network secured template. 
+> If you bring your existing virtual network and subnet with the *Microsoft.App/environments* delegation, the minimize size of your subnet should be /27 (32 addresses). We recommend a subnet size of /24 (256 addresses), which is the default subnet size set in the network secured template. 
 
 ### Network rules
 
@@ -169,7 +169,7 @@ Once your template deployment is complete, you can access your Foundry project b
 
 This setup enables AI agents to operate entirely within a dedicated, isolated virtual network. By leveraging private network isolation (BYO VNet), organizations can enforce custom security policies, ensuring that AI agents operate within their trusted infrastructure.    
 
-Our goal is to accelerate the development and deployment of AI agents without compromising critical security requirements. With our bicep and ARM templates, you can quickly set up your agent environment while still maintaining full control over their networking and data.   
+Our goal is to accelerate the development and deployment of AI agents without compromising critical security requirements. With our bicep and ARM templates, you can quickly setup your agent environment while still maintaining full control over their networking and data.   
 
 
 ## What's next?

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

@@ -7,14 +7,23 @@ author: aahill
 ms.author: aahi
 ms.service: azure-ai-agent-service
 ms.topic: overview
-ms.date: 06/26/2025
+ms.date: 08/04/2025
 ms.custom: azure-ai-agents
 ---
 
 # What's new in Azure AI Foundry Agent Service
 
 This article provides a summary of the latest releases and major documentation updates for Azure AI Foundry Agent Service.
 
+## August 2025
+
+### New regional availability
+
+The Azure AI Foundry Agent Sevice is now available in the following [regions](./concepts/model-region-support.md#available-models):
+* Brazil south
+* Germany west central
+* Italy north
+* South central US
 ## June 2025
 
 ### Deep Research tool

articles/ai-foundry/agents/whats-new.md

@@ -6,7 +6,7 @@ author: lgayhardt
 ms.author: lagayhar
 manager: scottpolly
 ms.reviewer: mithigpe
-ms.date: 05/19/2025
+ms.date: 07/31/2025
 ms.service: azure-ai-foundry
 ms.topic: concept-article
 ms.custom:
@@ -32,71 +32,79 @@ This is where evaluators become essential. These specialized tools measure both
 
 Evaluators are specialized tools that measure the quality, safety, and reliability of AI responses. By implementing systematic evaluations throughout the AI development lifecycle, teams can identify and address potential issues before they impact users. The following supported evaluators provide comprehensive assessment capabilities across different AI application types and concerns:
 
+### General purpose
 
-[**RAG (Retrieval Augmented Generation)**:](./evaluation-evaluators/rag-evaluators.md)
+| Evaluator | Purpose | Inputs |
+|--|--|--|
+| Coherence | Measures logical consistency and flow of responses.| Query, response |
+| Fluency | Measures natural language quality and readability. | Response  |
+| QA | Measures comprehensively various quality aspects in question-answering.| Query, context, response, ground truth |
 
-| Evaluator | Purpose |
-|--|--|
-| Retrieval | Measures how effectively the system retrieves relevant information. |
-| Document Retrieval | Measures accuracy in retrieval results given ground truth. |
-| Groundedness | Measures how consistent the response is with respect to the retrieved context. |
-| Groundedness Pro | Measures whether the response is consistent with respect to the retrieved context. |
-| Relevance | Measures how relevant the response is with respect to the query. |
-| Response Completeness | Measures to what extent the response is complete (not missing critical information) with respect to the ground truth. |
+To learn more, see [General purpose evaluators](./evaluation-evaluators/general-purpose-evaluators.md).
 
+### Textual similarity
 
-[**Agents (preview):**](./evaluation-evaluators/agent-evaluators.md)
+| Evaluator | Purpose | Inputs |
+|--|--|--|
+| Similarity | AI-assisted textual similarity measurement. | Query, context, ground truth |
+| F1 Score | Harmonic mean of precision and recall in token overlaps between response and ground truth. | Response, ground truth |
+| BLEU | Bilingual Evaluation Understudy score for translation quality measures overlaps in n-grams between response and ground truth. | Response, ground truth |
+| GLEU | Google-BLEU variant for sentence-level assessment measures overlaps in n-grams between response and ground truth. | Response, ground truth |
+| ROUGE | Recall-Oriented Understudy for Gisting Evaluation measures overlaps in n-grams between response and ground truth. | Response, ground truth |
+| METEOR | Metric for Evaluation of Translation with Explicit Ordering measures overlaps in n-grams between response and ground truth. | Response, ground truth |
 
-| Evaluator | Purpose |
-|--|--|
-| Intent Resolution | Measures how accurately the agent identifies and addresses user intentions.|
-| Task Adherence | Measures how well the agent follows through on identified tasks. |
-| Tool Call Accuracy | Measures how well the agent selects and calls the correct tools to.|
+To learn more, see [Textual similarity evaluators](./evaluation-evaluators/textual-similarity-evaluators.md)
 
+### RAG (retrieval augmented generation)
 
-[**General Purpose:**](./evaluation-evaluators/general-purpose-evaluators.md)
+| Evaluator | Purpose | Inputs |
+|--|--|--|
+| Retrieval | Measures how effectively the system retrieves relevant information. | Query , context |
+| Document Retrieval | Measures accuracy in retrieval results given ground truth. | Ground truth , retrieved documents,  |
+| Groundedness | Measures how consistent the response is with respect to the retrieved context. |  Query (optional), context, response |
+| Groundedness Pro | Measures whether the response is consistent with respect to the retrieved context. | Query, context, response |
+| Relevance | Measures how relevant the response is with respect to the query. | Query, response|
+| Response Completeness | Measures to what extent the response is complete (not missing critical information) with respect to the ground truth. | Response, ground truth |
 
-| Evaluator | Purpose |
-|--|--|
-| Fluency | Measures natural language quality and readability. |
-| Coherence | Measures logical consistency and flow of responses.|
-| QA | Measures comprehensively various quality aspects in question-answering.|
+To learn more, see [Retrieval-augmented Generation (RAG) evaluators](./evaluation-evaluators/rag-evaluators.md).
 
+### Safety and security (preview)
 
-[**Safety and Security (preview):**](./evaluation-evaluators/risk-safety-evaluators.md)
+| Evaluator | Purpose | Inputs |
+|--|--|--|
+| Hate and Unfairness | Identifies biased, discriminatory, or hateful content. | Query, response |
+| Sexual | Identifies inappropriate sexual content. | Query, response |
+| Violence | Detects violent content or incitement. | Query, response |
+| Self-Harm | Detects content promoting or describing self-harm.| Query, response |
+| Content Safety | Comprehensive assessment of various safety concerns. | Query, response |
+| Protected Materials | Detects unauthorized use of copyrighted or protected content. | Query, response |
+| Code Vulnerability | Identifies security issues in generated code. |  Query, response |
+| Ungrounded Attributes | Detects fabricated or hallucinated information inferred from user interactions. | Query, context, response |
 
-| Evaluator | Purpose |
-|--|--|
-| Violence | Detects violent content or incitement. |
-| Sexual | Identifies inappropriate sexual content. |
-| Self-Harm | Detects content promoting or describing self-harm.|
-| Hate and Unfairness | Identifies biased, discriminatory, or hateful content. |
-| Ungrounded Attributes | Detects fabricated or hallucinated information inferred from user interactions. |
-| Code Vulnerability | Identifies security issues in generated code. |
-| Protected Materials | Detects unauthorized use of copyrighted or protected content. |
-| Content Safety | Comprehensive assessment of various safety concerns. |
+To learn more, see [Risk and safety evaluators](./evaluation-evaluators/risk-safety-evaluators.md).
 
+### Agents (preview)
 
-[**Textual Similarity:**](./evaluation-evaluators/textual-similarity-evaluators.md)
+| Evaluator | Purpose | Inputs |
+|--|--|--|
+| Intent Resolution | Measures how accurately the agent identifies and addresses user intentions.| Query, response |
+| Task Adherence | Measures how well the agent follows through on identified tasks. | Query, response, tool definitions (optional) |
+| Tool Call Accuracy | Measures how well the agent selects and calls the correct tools to.| Query, either response or tool calls, tool definitions |
 
-| Evaluator | Purpose |
-|--|--|
-| Similarity | AI-assisted textual similarity measurement. |
-| F1 Score | Harmonic mean of precision and recall in token overlaps between response and ground truth. |
-| BLEU | Bilingual Evaluation Understudy score for translation quality measures overlaps in n-grams between response and ground truth. |
-| GLEU | Google-BLEU variant for sentence-level assessment measures overlaps in n-grams between response and ground truth. |
-| ROUGE | Recall-Oriented Understudy for Gisting Evaluation measures overlaps in n-grams between response and ground truth. |
-| METEOR | Metric for Evaluation of Translation with Explicit Ordering measures overlaps in n-grams between response and ground truth. |
+To learn more, see [Agent evaluators](./evaluation-evaluators/agent-evaluators.md).
 
+### Azure OpenAI graders (preview)
 
-[**Azure OpenAI Graders (preview):**](./evaluation-evaluators/azure-openai-graders.md)
+| Evaluator | Purpose |  Inputs |
+|--|--|--|
+| Model Labeler| Classifies content using custom guidelines and labels. | Query, response, ground truth |
+| String Checker | Performs flexible text validations and pattern matching. | Response |
+| Text Similarity | Evaluates the quality of text or determine semantic closeness. | Response, ground truth |
+| Model Scorer| Generates numerical scores (customized range) for content based on custom guidelines. | Query, response, ground truth |
 
-| Evaluator | Purpose |
-|--|--|
-| Model Labeler | Classifies content using custom guidelines and labels. |
-| Model Scorer | Generates numerical scores (customized range) for content based on custom guidelines. |
-| String Checker | Performs flexible text validations and pattern matching. |
-| Textual Similarity | Evaluates the quality of text or determine semantic closeness. |
+To learn more, see [Azure OpenAI Graders](./evaluation-evaluators/azure-openai-graders.md).
+
+### Evaluators in the development lifecycle
 
 By using these evaluators strategically throughout the development lifecycle, teams can build more reliable, safe, and effective AI applications that meet user needs while minimizing potential risks.
 

articles/ai-foundry/concepts/observability.md

@@ -7,7 +7,7 @@ ms.author: mopeakande
 manager: scottpolly
 reviewer: santiagxf
 ms.reviewer: fasantia
-ms.date: 07/11/2025
+ms.date: 08/04/2025
 ms.service: azure-ai-model-inference
 ms.topic: how-to
 ms.custom:
@@ -58,6 +58,17 @@ Azure OpenAI in Azure AI Foundry Models offers a diverse set of models with diff
 
 See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=aoai).
 
+### Black Forest Labs models sold directly by Azure
+
+The Black Forest Labs collection of image generation models include FLUX.1 Kontext [pro] for in-context generation and editing and FLUX1.1 [pro] for text-to-image generation. 
+
+| Model  | Type | Capabilities | Project type |
+| ------ | ---- | ------------ | ------------ |
+| [FLUX.1-Kontext-pro](https://ai.azure.com/explore/models/FLUX.1-Kontext-pro/version/1/registry/azureml-blackforestlabs) | Image generation | - **Input:** text and image (5000 tokens and 1 image)  <br /> - **Output:** One Image  <br />  - **Tool calling:** No <br /> - **Response formats**: Image (PNG and JPG) | Foundry, Hub-based |
+| [FLUX-1.1-pro](https://ai.azure.com/explore/models/FLUX-1.1-pro/version/1/registry/azureml-blackforestlabs) | Image generation | - **Input:** text (5000 tokens)  <br /> - **Output:** One Image  <br />  - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) | Hub-based |
+
+
+See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Black+Forest+Labs).
 
 ### DeepSeek models sold directly by Azure
 

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

@@ -45,8 +45,8 @@ import os, json
 from azure.ai.projects import AIProjectClient
 from azure.identity import DefaultAzureCredential
 
-project_client = AIProjectClient.from_connection_string(
-    credential=DefaultAzureCredential(), conn_str=os.environ["PROJECT_CONNECTION_STRING"]
+project_client = AIProjectClient(
+    credential=DefaultAzureCredential(), endpoint=os.environ["PROJECT_ENDPOINT"]
 )
 
 agent = project_client.agents.create_agent(
@@ -95,7 +95,7 @@ project_client.evaluation.create_agent_evaluation(
         thread=thread.id,  
         run=run.id,   
         evaluators=evaluators,
-        appInsightsConnectionString = project_client.telemetry.get_connection_string(),
+        appInsightsConnectionString = project_client.telemetry.get_application_insights_connection_string(),
     )
 )
 
@@ -189,7 +189,7 @@ project_client.evaluation.create_agent_evaluation(
         run=run.id,   
         evaluators=evaluators,  
         samplingConfiguration = sampling_config,  
-        appInsightsConnectionString = project_client.telemetry.get_connection_string(),
+        appInsightsConnectionString = project_client.telemetry.get_application_insights_connection_string(),
     )
 )
 ```