Merge branch 'main' into release-blob-backup

Author: v-alje

articles/ai-services/language-service/conversational-language-understanding/concepts/best-practices.md

@@ -75,7 +75,13 @@ If you require the learned component, make sure that *ticket quantity* is only r
 
 ## Addressing model inconsistencies
 
-If your model is overly sensitive to small grammatical changes, like casing or diacritics, you can systematically manipulate your dataset directly in the Language Studio. To use these features, click on the Settings tab on the left toolbar and locate the **Advanced project settings** section. First, you can ***Enable data transformation for casing***, which normalizes the casing of utterances when training, testing, and implementing your model. If you've migrated from LUIS, you might recognize that LUIS did this normalization by default. To access this feature via the API, set the `"normalizeCasing"` parameter to `true`. See an example below:
+If your model is overly sensitive to small grammatical changes, like casing or diacritics, you can systematically manipulate your dataset directly in the Language Studio. To use these features, click on the Settings tab on the left toolbar and locate the **Advanced project settings** section. 
+
+:::image type="content" source="../media/advanced-project-settings.png" alt-text="A screenshot showing an example of the advanced project settings." lightbox="../media/advanced-project-settings.png":::
+
+First, you can ***Enable data transformation for casing***, which normalizes the casing of utterances when training, testing, and implementing your model. If you've migrated from LUIS, you might recognize that LUIS did this normalization by default. To access this feature via the API, set the `"normalizeCasing"` parameter to `true`. See an example below:
+
+
 
 ```json
 {

articles/ai-services/language-service/conversational-language-understanding/media/advanced-project-settings.png

@@ -801,6 +801,8 @@ items:
     href: tutorials/use-kubernetes-service.md
   - name: Use language in power automate flows
     href: tutorials/power-automate.md
+  - name: Use language in prompt flow
+    href: tutorials/prompt-flow.md
   - name: 🆕 Native document support
     items:
     - name: 🆕 Use native documents for language processing

articles/ai-services/language-service/media/prompt-flow/prompt-flow-wizard.png

@@ -0,0 +1,73 @@
+---
+title: Use Language in Azure prompt flow
+description: Learn how to use Azure AI Language in prompt flow.
+author: jboback
+ms.author: jboback
+ms.service: azure-ai-language
+ms.topic: how-to
+ms.date: 07/09/2024
+---
+
+# Use Language in Azure prompt flow
+
+> [!IMPORTANT]
+> Some of the features described in this article might only be available in preview. This preview is provided without a service-level agreement, and we don't recommend it for production workloads. Certain features might not be supported or might have constrained capabilities. For more information, see [Supplemental Terms of Use for Microsoft Azure Previews](https://azure.microsoft.com/support/legal/preview-supplemental-terms/).
+
+[Prompt flow in Azure AI Studio](../../../ai-studio/how-to/prompt-flow.md) is a development tool designed to streamline the entire development cycle of AI applications powered by Large Language Models (LLMs). You can explore and quickly start to use and fine-tune various natural language processing capabilities from Azure AI Language, reducing your time to value and deploying solutions with reliable evaluation.
+
+This tutorial teaches you how to use Language in prompt flow utilizing [Azure AI Studio](https://ai.azure.com).                            
+
+## Prerequisites
+
+- An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>.
+
+- Access granted to Azure OpenAI in the desired Azure subscription.
+
+     Currently, access to this service is granted only by application. You can apply for access to Azure OpenAI by completing the form at <a href="https://aka.ms/oai/access" target="_blank">https://aka.ms/oai/access</a>. Open an issue on this repo to contact us if you have an issue.
+
+- You need an Azure AI Studio hub or permissions to create one. Your user role must be **Azure AI Developer**, **Contributor**, or **Owner** on the hub. For more information, see [hubs](../../../ai-studio/concepts/ai-resources.md) and [Azure AI roles](../../../ai-studio/concepts/rbac-ai-studio.md).
+     - If your role is **Contributor** or **Owner**, you can [create a hub in this tutorial](#create-a-project-in-azure-ai-studio). 
+     - If your role is **Azure AI Developer**, the hub must already be created. 
+
+- Your subscription needs to be below your [quota limit](../../../ai-studio/how-to/quota.md) to deploy a new flow in this tutorial.
+
+## Create a project in Azure AI Studio
+
+Your project is used to organize your work and save state. 
+
+[!INCLUDE [Create project](../../../ai-studio/includes/create-projects.md)]
+
+## Using Azure AI Language via the prompt flow gallery
+
+You can create an Azure AI Language flow by either cloning the samples available in the gallery or creating a flow from scratch. If you already have flow files in local or file share, you can also import the files to create a flow. For the purposes of this tutorial we'll be using the prebuilt **Analyze Conversations** flow.
+
+To create a prompt flow from the gallery in Azure AI Studio:
+
+1. Sign in to Azure AI Studio and select your project.
+
+1. From the collapsible left menu, select Prompt flow.
+
+1. Select + Create.
+
+1. Find the **Analyze Conversations** tile in the gallery and select *Clone*.
+
+1. In the right sidebar, name the folder and click the **Clone** button.
+
+1. After the process is complete, you'll be taken to the prompt flow wizard. Click **Start Compute Session** in the upper right hand corner to begin. The various parts of the wizard are out lined below:
+
+    :::image type="content" source="../media/prompt-flow/prompt-flow-wizard.png" alt-text="Screenshot of the prompt flow wizard page with each part of the tool numbered." lightbox="../media/prompt-flow/prompt-flow-wizard.png":::
+
+    1. A graph view of your flow.
+    1. Files in your flow. Click the arrow to expand this section.
+    1. Azure AI Language tools in the "More tools" dropdown menu, which you can add capabilities that you need for your flow. There are more tools that you can add from LLM, Prompt, and Python menu. This menu is only accessible after the compute session has started.
+    1. Configure your output.
+    1. Configure steps (or tools) in the flow.
+    1. Run, evaluate, and deploy your flow.
+
+1. Once you've configured everything to your liking, press the run button in the upper right hand corner.
+
+## Related content
+
+* [Azure AI Language homepage](https://aka.ms/azure-language)
+* [Azure AI Language product demo videos](https://aka.ms/language-videos)
+* [Explore Azure AI Language in Azure AI Studio](https://aka.ms/AzureAiLanguage)

articles/ai-services/language-service/toc.yml

@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
 description: Learn about the different model capabilities that are available with Azure OpenAI.
 ms.service: azure-ai-openai
 ms.topic: conceptual
-ms.date: 07/08/2024
+ms.date: 07/18/2024
 ms.custom: references_regions, build-2023, build-2023-dataai, refefences_regions
 manager: nitinme
 author: mrbullwinkle #ChrisHMSFT
@@ -18,7 +18,7 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
 
 | Models | Description |
 |--|--|
-| [GPT-4o & GPT-4 Turbo **NEW**](#gpt-4o-and-gpt-4-turbo) | The latest most capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
+| [GPT-4o & GPT-4 Turbo](#gpt-4o-and-gpt-4-turbo) | The latest most capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
 | [GPT-4](#gpt-4) | A set of models that improve on GPT-3.5 and can understand and generate natural language and code. |
 | [GPT-3.5](#gpt-35) | A set of models that improve on GPT-3 and can understand and generate natural language and code. |
 | [Embeddings](#embeddings-models) | A set of models that can convert text into numerical vector form to facilitate text similarity. |
@@ -28,7 +28,21 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
 
 ## GPT-4o and GPT-4 Turbo
 
-GPT-4o is the latest model from OpenAI. GPT-4o integrates text and images in a single model, enabling it to handle multiple data types simultaneously. This multimodal approach enhances accuracy and responsiveness in human-computer interactions. GPT-4o matches GPT-4 Turbo in English text and coding tasks while offering superior performance in non-English languages and vision tasks, setting new benchmarks for AI capabilities.
+GPT-4o integrates text and images in a single model, enabling it to handle multiple data types simultaneously. This multimodal approach enhances accuracy and responsiveness in human-computer interactions. GPT-4o matches GPT-4 Turbo in English text and coding tasks while offering superior performance in non-English languages and vision tasks, setting new benchmarks for AI capabilities.
+
+### Early access playground
+
+Existing Azure OpenAI customers can test out the **NEW GPT-4o mini** model in the **Azure OpenAI Studio Early Access Playground (Preview)**.  
+
+To test the latest model:
+
+> [!NOTE]
+> The GPT-4o mini early access playground is currently only available for resources in **West US3** and **East US**, and is limited to 10 requests every five minutes per subscription. Azure OpenAI content filters are enabled at the default configuration and cannot be modified. GPT-4o mini is a preview model and is currently not available for deployment/direct API access.
+
+1. Navigate to Azure OpenAI Studio at https://oai.azure.com/ and sign-in with credentials that have access to your OpenAI resources.
+2. Select an Azure OpenAI resource in the **West US3** or **East US** regions. If you don't have a resource in one of these regions you will need to [create a resource](../how-to/create-resource.md).
+3. From the main [Azure OpenAI Studio](https://oai.azure.com/) page select the **Early Access Playground (Preview)** button from under the **Get started** section. (This button will only be visible when a resource in **West US3** or **East US** is selected.)
+4. Now you can start asking the model questions just as you would before in the existing [chat playground](../chatgpt-quickstart.md).
 
 ### How do I access the GPT-4o model?
 

articles/ai-services/language-service/tutorials/prompt-flow.md

@@ -10,7 +10,7 @@ ms.custom:
   - ignite-2023
   - references_regions
 ms.topic: whats-new
-ms.date: 07/09/2024
+ms.date: 07/18/2024
 recommendations: false
 ---
 
@@ -20,6 +20,16 @@ This article provides a summary of the latest releases and major documentation u
 
 ## July 2024
 
+### GPT-4o mini preview model available for early access
+
+GPT-4o mini is the latest model from OpenAI [launched on July 18, 2024](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/).
+
+From OpenAI:
+
+*"GPT-4o mini surpasses GPT-3.5 Turbo and other small models on academic benchmarks across both textual intelligence and multimodal reasoning, and supports the same range of languages as GPT-4o. It also demonstrates strong performance in function calling, which can enable developers to build applications that fetch data or take actions with external systems, and improved long-context performance compared to GPT-3.5 Turbo."*
+
+To start testing out the model today in Azure OpenAI, see the [**Azure OpenAI Studio early access playground**](./concepts/models.md#early-access-playground).
+
 ### New Responsible AI default content filtering policy 
 
 The new default content filtering policy `DefaultV2` delivers the latest safety and security mitigations for the GPT model series (text), including:

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

@@ -4,7 +4,8 @@ titleSuffix: Azure Linux AKS Container Host partner solutions
 description: Discover partner-tested solutions that enable you to build, test, deploy, manage, and monitor your AKS environment using Azure Linux Container Host.
 ms.author: schaffererin
 author: schaffererin
-ms.topic: article
+ms.service: azure-kubernetes-service
+ms.topic: conceptual
 ms.custom: linux-related-content
 ms.date: 06/13/2024
 ---

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

@@ -116,7 +116,7 @@ The Dapr extension supports stable versions of Dapr APIs (building blocks).
 | [**Secrets**][dapr-secrets]                           | Stable | Access secrets from your application code or reference secure values in your Dapr components.                                                                   |
 | [**Configuration**][dapr-config]                           | Stable | Retrieve and subscribe to application configuration items for supported configuration. stores.                                                                   |
 
-[!INCLUDE [component-support](../../includes/dapr-in-azure/dapr-support-policy.md)]
+[!INCLUDE [component-support](~/reusable-content/ce-skilling/azure/includes/dapr-in-azure/dapr-support-policy.md)]
 
 ### Clouds/regions
 

articles/aks/azure-linux-aks-partner-solutions.md

@@ -190,7 +190,7 @@ For more information, see the [**Recommended passive-cold failover solution over
 
 AKS sets default limits and quotas for resources and features, including usage restrictions for certain VM SKUs.
 
-[!INCLUDE [container-service-limits](../../includes/container-service-limits.md)]
+[!INCLUDE [container-service-limits](~/reusable-content/ce-skilling/azure/includes/container-service-limits.md)]
 
 For more information, see [AKS service quotas and limits](./quotas-skus-regions.md#service-quotas-and-limits).