Merge pull request #5816 from MicrosoftDocs/main

Merged by Learn.Build PR Management system

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

articles/ai-foundry/how-to/develop/ai-template-get-started.md

@@ -7,14 +7,14 @@ ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 05/05/2025
+ms.date: 07/01/2025
 ms.reviewer: varundua
 ms.author: sgilley
 author: sdgilley
 #customer intent: As a developer, I want to jump start my journey with an AI template.
 ---
 
-# Get started with an AI template (Preview)
+# Get started with an AI template
 
 Streamline your code-first development with prebuilt, task-specific Azure AI templates. Benefit from using the latest features and best practices from Microsoft Azure AI, with popular frameworks like LangChain, prompt flow, and Semantic Kernel in multiple languages.
 
@@ -24,12 +24,10 @@ Available templates include:
 * [Get started with AI agents](https://github.com/Azure-Samples/get-started-with-ai-agents)
 * [Unlock insights from conversational data](https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator)
 
-[!INCLUDE [feature-preview](../../includes/feature-preview.md)]
-
 ## Prerequisites
 
 - [Azure subscription](https://azure.microsoft.com/free)
-- An [Azure AI Foundry project](../create-projects.md).
+- Either a [!INCLUDE [fdp-project-name](../../includes/fdp-project-name.md)](../create-projects.md?pivots=fdp-project) or a [!INCLUDE [hub-project-name](../../includes/hub-project-name.md)](../create-projects.md?pivots=hub-project).
 
 ## Start with a sample application
 

articles/ai-foundry/how-to/develop/sdk-overview.md

@@ -8,7 +8,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: how-to
-ms.date: 05/07/2025
+ms.date: 07/01/2025
 ms.reviewer: dantaylo
 ms.author: sgilley
 author: sdgilley
@@ -40,7 +40,6 @@ The Azure AI Foundry SDK is a set of client libraries and services designed to w
     az login
     ```
 
-
 ## Unified Projects client library
 
 The Azure AI Foundry Projects client library is a unified library that enables you to use multiple client libraries together by connecting to a single project endpoint.
@@ -89,8 +88,6 @@ The Azure AI Foundry Projects client library is a unified library that enables y
         .buildClient();
     ```
 
-
-
 ::: zone-end
 
 ::: zone pivot="programming-language-javascript"

articles/ai-foundry/includes/deploy-model.md

@@ -17,9 +17,9 @@ To work with a model, you first deploy it into a project.
 1. Sign in to [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs).
 1. Studio remembers where you were last, so what you do next depends on where you are:
 
-    * If you're new to Azure AI Foundry, select **Create an agent**. Add a name for your project and select **Create**.
     * If you see a list of projects, select the one you want to use.  You can use either a [!INCLUDE [hub-project-name](hub-project-name.md)] or a [!INCLUDE [fdp-project-name](fdp-project-name.md)].
     * If you're already in a project and want to use a new one, select **Azure AI Foundry** in the top left corner, then select **Create new** to create the new project.
+    * If you're new to Azure AI Foundry and don't have any projects, use [Quickstart: Get started with Azure AI Foundry](../quickstarts/get-started-code.md) instead of this article.
 
 1. Select **Model catalog** from the left pane.
 

articles/ai-services/speech-service/voice-live.md

@@ -176,9 +176,12 @@ You're charged separately for the training and model hosting of:
 
 Tokens are the units that generative AI models use to process input and generate output. 
 
-You can estimate the cost with Voice Live API based on audio length as follows:
-- Each second of input audio is approximately 10 tokens.
-- Each second of output audio is approximately 20 tokens.
+You can estimate token usage for different model families with the Voice Live API based on audio length. The following token calculations apply to each model family:
+
+| Model family | Input audio (tokens per second) | Output audio (tokens per second) |
+| ----- | ----- | ----- |
+| Azure OpenAI models | ~10 tokens | ~20 tokens |
+| Phi models | ~12.5 tokens | ~20 tokens |
 
 You're also charged for cached audio and text inputs, including the prompt and the context of the conversations. 
 

articles/search/search-indexer-howto-access-private.md

@@ -10,7 +10,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 05/28/2025
+ms.date: 07/01/2025
 ---
 
 # Make outbound connections through a shared private link
@@ -28,14 +28,15 @@ Shared private link is a premium feature that's billed by usage. When you set up
 
 Azure AI Search makes outbound calls to other Azure resources in the following scenarios:
 
++ Knowledge agent connections to Azure OpenAI for agentic retrieval workflows
 + Indexer or query connections to Azure OpenAI, Azure AI Vision, or the Azure AI Foundry model catalog for vectorization
 + Indexer connections to supported data sources
 + Indexer (skillset) connections to Azure Storage for caching enrichments, debug session sate, or writing to a knowledge store
 + Indexer (skillset) connections to Azure AI services for billing purposes
 + Encryption key requests to Azure Key Vault
 + Custom skill requests to Azure Functions or similar resource
 
-Shared private links only work for Azure-to-Azure connections. If you're connecting to OpenAI or another external model, the connection must be over the public internet.
+Shared private links only work for Azure-to-Azure connections. If you're connecting to OpenAI or another external model provider, the connection must be over the public internet.
 
 Shared private links are for operations and data accessed through a [private endpoint](/azure/private-link/private-endpoint-overview) for Azure resources or clients that run in an Azure virtual network.
 
@@ -51,7 +52,7 @@ Once you set up the private link, it's used automatically whenever the search se
 
 There are two scenarios for using [Azure Private Link](/azure/private-link/private-link-overview) and Azure AI Search together.
 
-+ Scenario one: create a shared private link when an *outbound* (indexer) connection to Azure requires a private connection.
++ Scenario one: create a shared private link when an *outbound* (indexer or knowledge agent) connection to Azure requires a private connection.
 
 + Scenario two: [configure search for a private *inbound* connection](service-create-private-endpoint.md) from clients that run in a virtual network.
 
@@ -80,6 +81,7 @@ When evaluating shared private links for your scenario, remember these constrain
   | Indexers without skillsets | Basic and higher | None | None |
   | Skillsets with embedding skills ([integrated vectorization](vector-search-integrated-vectorization.md)) | Basic and higher | [High capacity regions](search-limits-quotas-capacity.md#partition-storage-gb) | [After April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date) |
   | Skillsets using other [built-in](cognitive-search-predefined-skills.md) or custom skills | Standard 1 (S1) and higher | None | [After April 3, 2024](search-how-to-upgrade.md#check-your-service-creation-or-upgrade-date) |
+  | Knowledge agents calling Azure OpenAI for query planning or passing search results | Basic and higher | None | None |
 
 + Permissions on both Azure AI Search and the Azure resource: