Merge pull request #2552 from MicrosoftDocs/main

v-alje · web-flow · commit 8d0b994ab7d6 · 2025-01-28T10:03:22.000-08:00
01/28/2025 AM Publishing
diff --git a/articles/ai-foundry/model-inference/concepts/deployment-types.md b/articles/ai-foundry/model-inference/concepts/deployment-types.md
@@ -31,12 +31,13 @@ To learn more about deployment options for Azure OpenAI models see [Azure OpenAI
 
 Models from third-party model providers with pay-as-you-go billing (collectively called Models-as-a-Service), makes models available in Azure AI model inference under **standard** deployments with a Global processing option (`Global-Standard`). 
 
-Models-as-a-Service offers regional deployment options under [Serverless API endpoints](../../../ai-studio/how-to/deploy-models-serverless.md) in Azure AI Foundry. Prompts and outputs are processed within the geography specified during deployment. However, those deployments can't be accessed using the Azure AI model inference endpoint in Azure AI Services.
-
 ### Global-Standard
 
 Global deployments leverage Azure's global infrastructure to dynamically route traffic to the data center with best availability for each request. Global standard provides the highest default quota and eliminates the need to load balance across multiple resources. Data stored at rest remains in the designated Azure geography, while data may be processed for inferencing in any Azure location. Learn more about [data residency](https://azure.microsoft.com/explore/global-infrastructure/data-residency/).
 
+> [!NOTE]
+> Models-as-a-Service offers regional deployment options under [Serverless API endpoints](../../../ai-studio/how-to/deploy-models-serverless.md) in Azure AI Foundry. Prompts and outputs are processed within the geography specified during deployment. However, those deployments can't be accessed using the Azure AI model inference endpoint in Azure AI Services.
+
 ## Control deployment options
 
 Administrators can control which model deployment types are available to their users by using Azure Policies. Learn more about [How to control AI model deployment with custom policies](../../../ai-studio/how-to/custom-policy-model-deployment.md).
diff --git a/articles/ai-foundry/model-inference/faq.yml b/articles/ai-foundry/model-inference/faq.yml
@@ -5,7 +5,7 @@ metadata:
   description: Get answers to the most popular questions about Azure AI model inference
   #services: cognitive-services
   manager: nitinme
-  ms.service: azure-ai-models
+  ms.service: azure-ai-model-inference
   ms.topic: faq
   ms.date: 1/21/2025
   ms.author: fasantia
diff --git a/articles/ai-foundry/model-inference/index.yml b/articles/ai-foundry/model-inference/index.yml
@@ -6,7 +6,7 @@ summary: Azure AI model inference provides access to the most powerful models av
 metadata:
   title: Azure AI model inference documentation - Quickstarts, How-to's, API Reference - Azure AI Foundry | Microsoft Docs
   description: Learn how to use flagship models available in the Azure AI model catalog from the key model providers in the industry, including OpenAI, Microsoft, Meta, Mistral, Cohere, G42, and AI21 Labs.
-  ms.service: azure-ai-models
+  ms.service: azure-ai-model-inference
   ms.custom:
   ms.topic: landing-page
   author: mrbullwinkle
diff --git a/articles/ai-services/agents/includes/quickstart-csharp.md b/articles/ai-services/agents/includes/quickstart-csharp.md
@@ -38,6 +38,12 @@ dotnet add package Azure.AI.Projects
 dotnet add package Azure.Identity
 ```
 
+Next, to authenticate your API requests and run the program, use the [az login](/cli/azure/authenticate-azure-cli-interactively) command to sign into your Azure subscription.
+
+```azurecli
+az login
+```
+
 Use the following code to create and run an agent. To run this code, you will need to create a connection string using information from your project. This string is in the format:
 
 `<HostName>;<AzureSubscriptionId>;<ResourceGroup>;<ProjectName>`
@@ -56,6 +62,7 @@ For example, your connection string may look something like:
 
 Set this connection string as an environment variable named `PROJECT_CONNECTION_STRING`.
 
+
 ```csharp
 // Copyright (c) Microsoft Corporation. All rights reserved.
 // Licensed under the MIT License.
diff --git a/articles/ai-services/agents/includes/quickstart-python-openai.md b/articles/ai-services/agents/includes/quickstart-python-openai.md
@@ -41,6 +41,12 @@ pip install azure-identity
 pip install openai
 ```
 
+Next, to authenticate your API requests and run the program, use the [az login](/cli/azure/authenticate-azure-cli-interactively) command to sign into your Azure subscription.
+
+```azurecli
+az login
+```
+
 Use the following code to create and run an agent. To run this code, you will need to create a connection string using information from your project. This string is in the format:
 
 `<HostName>;<AzureSubscriptionId>;<ResourceGroup>;<ProjectName>`
diff --git a/articles/ai-services/agents/includes/quickstart-python.md b/articles/ai-services/agents/includes/quickstart-python.md
@@ -38,6 +38,11 @@ Run the following commands to install the python packages.
 pip install azure-ai-projects
 pip install azure-identity
 ```
+Next, to authenticate your API requests and run the program, use the [az login](/cli/azure/authenticate-azure-cli-interactively) command to sign into your Azure subscription.
+
+```azurecli
+az login
+```
 
 Use the following code to create and run an agent. To run this code, you will need to create a connection string using information from your project. This string is in the format:
 
@@ -115,7 +120,7 @@ with project_client:
     print(f"Messages: {messages}")
 
     # Get the last message from the sender
-    last_msg = messages.get_last_text_message_by_sender("assistant")
+    last_msg = messages.get_last_text_message_by_role("assistant")
     if last_msg:
         print(f"Last Message: {last_msg.text.value}")
 
diff --git a/articles/ai-services/immersive-reader/how-to-cache-token.md b/articles/ai-services/immersive-reader/how-to-cache-token.md
@@ -61,7 +61,7 @@ public async Task<string> GetTokenAsync()
 
 The `AuthenticationResult` object has an `AccessToken` property, which is the actual token you use when launching the Immersive Reader using the SDK. It also has an `ExpiresOn` property that denotes when the token expires. Before launching the Immersive Reader, you can check whether the token is expired, and acquire a new token only if it expired.
 
-## Using Node.JS
+## Using Node.js
 
 Add the [request](https://www.npmjs.com/package/request) npm package to your project. Use the following code to acquire a token, using the authentication values you got when you [created the Immersive Reader resource](./how-to-create-immersive-reader.md).
 
diff --git a/articles/search/hybrid-search-how-to-query.md b/articles/search/hybrid-search-how-to-query.md
@@ -226,7 +226,7 @@ POST https://{{search-service-name}}.search.windows.net/indexes/{{index-name}}/d
 
 ## Semantic hybrid search
 
-Assuming that you [enabled semantic ranker](semantic-how-to-enable-disable.md) and your index definition includes a [semantic configuration](semantic-how-to-query-request.md), you can formulate a query that includes vector search and keyword search, with semantic ranking over the merged result set. Optionally, you can add captions and answers. 
+Assuming that you [have semantic ranker](semantic-how-to-enable-disable.md) and your index definition includes a [semantic configuration](semantic-how-to-query-request.md), you can formulate a query that includes vector search and keyword search, with semantic ranking over the merged result set. Optionally, you can add captions and answers. 
 
 Whenever you use semantic ranking with vectors, make sure `k` is set to 50. Semantic ranker uses up to 50 matches as input. Specifying less than 50 deprives the semantic ranking models of necessary inputs.
 
diff --git a/articles/search/index.yml b/articles/search/index.yml
@@ -5,7 +5,7 @@ summary: Information retrieval at scale for vector and text content in tradition
 metadata:
   title: Azure AI Search documentation
   description: Information retrieval at scale for vector and text content in traditional or generative search scenarios.
-  ms.service: service
+  ms.service: azure-ai-search
   ms.custom:
     - ignite-2023
     - ignite-2024
diff --git a/articles/search/search-manage-rest.md b/articles/search/search-manage-rest.md
@@ -229,7 +229,7 @@ PATCH https://management.azure.com/subscriptions/{{subscriptionId}}/resourcegrou
 
 ## Disable semantic ranker
 
-Although [semantic ranker isn't enabled](semantic-how-to-enable-disable.md) by default, you could lock down the feature at the service level for greater certainty it can't be used.
+[Semantic ranker is enabled](semantic-how-to-enable-disable.md) by default at the free plan that allows up to 1,000 requests per month at no charge. You can lock down the feature at the service level to prevent usage.
 
 ```http
 ### disable semantic ranker
diff --git a/articles/search/search-manage.md b/articles/search/search-manage.md
@@ -109,7 +109,7 @@ Internally, Microsoft collects telemetry data about your service and the platfor
 
 ### Enable semantic ranker
 
-Semantic ranker is free for the first 1,000 requests per month, but you must opt in to get the free quota. 
+Semantic ranker is free for the first 1,000 requests per month. It's enabled by default on newer services.
 
 In Azure portal, under **Settings** on the leftmost pane, select **Semantic ranker** and then choose the Free plan. For more information, see [Enable semantic ranker](semantic-how-to-enable-disable.md).
 
diff --git a/articles/search/semantic-how-to-enable-disable.md b/articles/search/semantic-how-to-enable-disable.md
@@ -10,20 +10,20 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2023
 ms.topic: how-to
-ms.date: 12/10/2024
+ms.date: 01/28/2025
 ---
 
 # Enable or disable semantic ranker
 
-Semantic ranker is a premium feature billed by usage. By default, semantic ranker is turned off when you create a new search service, but anyone with *Contributor* permissions can enable it. If you don't want anyone enabling it inadvertently, you can [disable it service-wide using the management REST API](#disable-semantic-ranker-using-the-rest-api).
+Semantic ranker is a premium feature billed by usage. By default, semantic ranker is turned on when you create a new billable search service, but anyone with *Contributor* permissions can disable it or change the billing plan. If you don't want anyone to use the feature, you can [disable it service-wide using the management REST API](#disable-semantic-ranker-using-the-rest-api).
 
 ## Check availability
 
 To check if semantic ranker is available in your region, see the [Azure AI Search regions list](search-region-support.md).
 
 ## Enable semantic ranker
 
-Follow these steps to enable [semantic ranker](semantic-search-overview.md) at the service level. Once enabled, it's available to all indexes. You can't turn it on or off for specific indexes.
+Semantic ranker might not be enabled on older services. Follow these steps to enable [semantic ranker](semantic-search-overview.md) at the service level. Once enabled, it's available to all indexes. You can't turn it on or off for specific indexes.
 
 ### [**Azure portal**](#tab/enable-portal)
 
@@ -33,11 +33,11 @@ Follow these steps to enable [semantic ranker](semantic-search-overview.md) at t
 
 1. On the left-navigation pane, select **Settings** > **Semantic ranker**.
 
-1. Select either the **Free plan** or the **Standard plan**. You can switch between the free plan and the standard plan at any time.
+1. Select either the **Free plan** (default) or the **Standard plan**. You can switch between the free plan and the standard plan at any time.
 
    :::image type="content" source="media/semantic-search-overview/semantic-search-billing.png" alt-text="Screenshot of enabling semantic ranking in the Azure portal." border="true":::
 
-The free plan is capped at 1,000 queries per month. After the first 1,000 queries in the free plan, an error message indicates you exhausted your quota on the next semantic query. When quota is exhausted, you should upgrade to the standard plan to continue using semantic ranking.
+The free plan is capped at 1,000 queries per month. After the first 1,000 queries in the free plan, an error message indicates you exhausted your quota on the next semantic query. When quota is exhausted, you can upgrade to the standard plan to continue using semantic ranking.
 
 ### [**REST**](#tab/enable-rest)
 
diff --git a/articles/search/semantic-search-overview.md b/articles/search/semantic-search-overview.md
@@ -129,7 +129,7 @@ The following video provides an overview of the capabilities.
 
 Semantic ranker is available on search services at the Basic and higher tiers, subject to [regional availability](search-region-support.md).
 
-When you enable semantic ranker, choose a pricing plan for the feature:
+When you configure semantic ranker, choose a pricing plan for the feature:
 
 * At lower query volumes (under 1,000 monthly), semantic ranking is free.
 * At higher query volumes, choose the standard pricing plan.
@@ -144,7 +144,7 @@ Charges for semantic ranker are levied when query requests include `queryType=se
 
 1. [Sign in to Azure portal](https://portal.azure.com) to verify your search service is Basic or higher.
 
-1. [Enable semantic ranker and choose a pricing plan](semantic-how-to-enable-disable.md).
+1. [Configure semantic ranker for the search service, choosing a pricing plan](semantic-how-to-enable-disable.md).
 
 1. [Configure semantic ranker in a search index](semantic-how-to-configure.md).
 
