@@ -16,7 +16,7 @@ ms.custom: ignite-2023, build-2024, ignite-2024
 
 # What is Azure OpenAI in Azure AI Foundry portal?
 
-Azure OpenAI Service provides REST API access to OpenAI's powerful language models. Azure OpenAI Studio was previously where you went to access and work with the Azure OpenAI Service. This studio is now integrated into Azure AI Foundry portal. 
+Azure OpenAI Service provides REST API access to OpenAI's powerful language models. Azure OpenAI Studio was previously where you went to access and work with the Azure OpenAI Service. This studio is now integrated into [Azure AI Foundry portal](https://ai.azure.com). 
 
 ## Access Azure OpenAI Service in Azure AI Foundry portal
 

@@ -9,8 +9,8 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: conceptual
-ms.date: 11/21/2024
-ms.reviewer: sgilley
+ms.date: 02/21/2025
+ms.reviewer: meerakurup
 ms.author: sgilley
 author: sdgilley
 ---
@@ -31,30 +31,30 @@ As another example, you can [create a connection](../how-to/connections-add.md)
 
 ## Connections to non-Microsoft services
 
-Azure AI Foundry supports connections to non-Microsoft services, including the following:
-- The [API key connection](../how-to/connections-add.md) handles authentication to your specified target on an individual basis. This is the most common non-Microsoft connection type.
-- The [custom connection](../how-to/connections-add.md) allows you to securely store and access keys while storing related properties, such as targets and versions. Custom connections are useful when you have many targets that or cases where you wouldn't need a credential to access. LangChain scenarios are a good example where you would use custom service connections. Custom connections don't manage authentication, so you'll have to manage authentication on your own.
+Azure AI Foundry supports connections to non-Microsoft services, including:
+- The [API key connection](../how-to/connections-add.md) handles authentication to your specified target on an individual basis. API key is the most common non-Microsoft connection type.
+- The [custom connection](../how-to/connections-add.md) allows you to securely store and access keys while storing related properties, such as targets and versions. Custom connections are useful when you have many targets that or cases where you wouldn't need a credential to access. LangChain scenarios are a good example where you would use custom service connections. Custom connections don't manage authentication, so you have to manage authentication on your own.
 
 ## Connections to datastores
 
 > [!IMPORTANT]
-> Data connections cannot be shared across projects. They are created exclusively in the context of one project. 
+> Data connections can't be shared across projects. They're created exclusively in the context of one project. 
 
 Creating a data connection allows you to access external data without copying it to your project. Instead, the connection provides a reference to the data source.
 
 A data connection offers these benefits:
 
 - A common, easy-to-use API that interacts with different storage types including Microsoft OneLake, Azure Blob, and Azure Data Lake Gen2.
 - Easier discovery of useful connections in team operations.
-- For credential-based access (service principal/SAS/key), Azure AI Foundry connection secures credential information. This way, you won't need to place that information in your scripts.
+- Credential-based access (service principal/SAS/key). Azure AI Foundry connection secures credential information so you don't need to place that information in your scripts.
 
 When you create a connection with an existing Azure storage account, you can choose between two different authentication methods:
 
 - **Credential-based**: Authenticate data access with a service principal, shared access signature (SAS) token, or account key. Users with *Reader* project permissions can access the credentials.
 - **Identity-based**: Use your Microsoft Entra ID or managed identity to authenticate data access.
 
     > [!TIP]
-    > When using an identity-based connection, Azure role-based access control (Azure RBAC) is used to determine who can access the connection. You must assign the correct Azure RBAC roles to your developers before they can use the connection. For more information, see [Scenario: Connections using Microsoft Entra ID](rbac-ai-studio.md#scenario-connections-using-microsoft-entra-id-authentication).
+    > When you use an identity-based connection, Azure role-based access control (Azure RBAC) determines who can access the connection. You must assign the correct Azure RBAC roles to your developers before they can use the connection. For more information, see [Scenario: Connections using Microsoft Entra ID](rbac-ai-studio.md#scenario-connections-using-microsoft-entra-id-authentication).
 
 
 The following table shows the supported Azure cloud-based storage services and authentication methods:
@@ -82,7 +82,7 @@ A Uniform Resource Identifier (URI) represents a storage location on your local
 
 ## Key vaults and secrets
 
-Connections allow you to securely store credentials, authenticate access, and consume data and information.  Secrets associated with connections are securely persisted in the corresponding Azure Key Vault, adhering to robust security and compliance standards. As an administrator, you can audit both shared and project-scoped connections on a hub level (link to connection rbac). 
+Connections allow you to securely store credentials, authenticate access, and consume data and information.  Secrets associated with connections are securely persisted in the corresponding Azure Key Vault, adhering to robust security and compliance standards. As an administrator, you can audit both shared and project-scoped connections on a hub level. 
 
 Azure connections serve as key vault proxies, and interactions with connections are direct interactions with an Azure key vault. Azure AI Foundry connections store API keys securely, as secrets, in a key vault. The key vault [Azure role-based access control (Azure RBAC)](./rbac-ai-studio.md) controls access to these connection resources. A connection references the credentials from the key vault storage location for further use. You won't need to directly deal with the credentials after they're stored in the hub's key vault. You have the option to store the credentials in the YAML file. A CLI command or SDK can override them. We recommend that you avoid credential storage in a YAML file, because a security breach could lead to a credential leak.  
 

@@ -86,7 +86,7 @@ The configurability feature allows customers to adjust the settings, separately
 
 <sup>1</sup> For Azure OpenAI models, only customers who have been approved for modified content filtering have full content filtering control, including configuring content filters at severity level high only or turning off content filters. Apply for modified content filters via these forms: [Azure OpenAI Limited Access Review: Modified Content Filters](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUMlBQNkZMR0lFRldORTdVQzQ0TEI5Q1ExOSQlQCN0PWcu), and [Modified Abuse Monitoring](https://customervoice.microsoft.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbR7en2Ais5pxKtso_Pz4b1_xUOE9MUTFMUlpBNk5IQlZWWkcyUEpWWEhGOCQlQCN0PWcu).
 
-Customers are responsible for ensuring that applications integrating Azure OpenAI comply with the [Code of Conduct](/legal/cognitive-services/openai/code-of-conduct?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext). 
+Customers are responsible for ensuring that applications integrating Azure OpenAI comply with the [Code of Conduct](/legal/ai-code-of-conduct?context=%2Fazure%2Fai-services%2Fopenai%2Fcontext%2Fcontext). 
 
 
 ## Next steps

@@ -1,24 +1,25 @@
 ---
 title: Fine-tuning in Azure AI Foundry portal
 titleSuffix: Azure AI Foundry
-description: This article introduces fine-tuning of models in Azure AI Foundry portal.
+description: This article explains what fine-tuning is and under what circumstances you should consider doing it.
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - build-2024
   - code01
-ms.topic: conceptual
-ms.date: 10/31/2024
-ms.reviewer: sgilley
+ms.topic: concept-article
+ms.date: 02/21/2025
+ms.reviewer: keli19
 ms.author: sgilley
 author: sdgilley
+#customer intent: As a developer, I want to learn what it means to fine-tune a model.
 ---
 
 # Fine-tune models with Azure AI Foundry
 
-[!INCLUDE [feature-preview](../includes/feature-preview.md)]
+Fine-tuning customizes a pretrained AI model with additional training on a specific task or dataset to improve performance, add new skills, or enhance accuracy. The result is a new, optimized GenAI model based on the provided examples.
 
-Fine-tuning refers to customizing a pre-trained generative AI model with additional training on a specific task or new dataset for enhanced performance, new skills, or improved accuracy. The result is a new, custom GenAI model that's optimized based on the provided examples.
+[!INCLUDE [feature-preview](../includes/feature-preview.md)]
 
 Consider fine-tuning GenAI models to:
 - Scale and adapt to specific enterprise needs
@@ -27,19 +28,20 @@ Consider fine-tuning GenAI models to:
 - Save time and resources with faster and more precise results
 - Get more relevant and context-aware outcomes as models are fine-tuned for specific use cases
 
-[Azure AI Foundry](https://ai.azure.com) offers several models across model providers enabling you to get access to the latest and greatest in the market. You can discover supported models for fine-tuning through our model catalog by using the **Fine-tuning tasks** filter and selecting the model card to learn detailed information about each model. Specific models may be subjected to regional constraints, [view this list for more details](#supported-models-for-fine-tuning). 
+[Azure AI Foundry](https://ai.azure.com) offers several models across model providers enabling you to get access to the latest and greatest in the market. You can discover supported models for fine-tuning through our model catalog by using the **Fine-tuning tasks** filter and selecting the model card to learn detailed information about each model. Specific models might be subjected to regional constraints. [View this list for more details](#supported-models-for-fine-tuning). 
 
 :::image type="content" source="../media/concepts/model-catalog-fine-tuning.png" alt-text="Screenshot of Azure AI Foundry model catalog and filtering by Fine-tuning tasks." lightbox="../media/concepts/model-catalog-fine-tuning.png":::
 
-This article will walk you through use-cases for fine-tuning and how this can help you in your GenAI journey.
+This article walks you through use-cases for fine-tuning and how it helps you in your GenAI journey.
 
 ## Getting started with fine-tuning
 
 When starting out on your generative AI journey, we recommend you begin with prompt engineering and RAG to familiarize yourself with base models and its capabilities. 
 - [Prompt engineering](../../ai-services/openai/concepts/prompt-engineering.md) is a technique that involves designing prompts using tone and style details, example responses, and intent mapping for natural language processing models. This process improves accuracy and relevancy in responses, to optimize the performance of the model.
 - [Retrieval-augmented generation (RAG)](../concepts/retrieval-augmented-generation.md) improves LLM performance by retrieving data from external sources and incorporating it into a prompt. RAG can help businesses achieve customized solutions while maintaining data relevance and optimizing costs.
 
-As you get comfortable and begin building your solution, it's important to understand where prompt engineering falls short and that will help you realize if you should try fine-tuning. 
+As you get comfortable and begin building your solution, it's important to understand where prompt engineering falls short and when you should try fine-tuning.
+
 - Is the base model failing on edge cases or exceptions? 
 - Is the base model not consistently providing output in the right format?
 - Is it difficult to fit enough examples in the context window to steer the model?
@@ -53,26 +55,29 @@ _A customer wants to use GPT-3.5 Turbo to turn natural language questions into q
 
 ### Use cases
 
-Base models are already pre-trained on vast amounts of data and most times you'll add instructions and examples to the prompt to get the quality responses that you're looking for - this process is called "few-shot learning". Fine-tuning allows you to train a model with many more examples that you can tailor to meet your specific use-case, thus improving on few-shot learning. This can reduce the number of tokens in the prompt leading to potential cost savings and requests with lower latency. 
+Base models are already pretrained on vast amounts of data. Most times you add instructions and examples to the prompt to get the quality responses that you're looking for - this process is called "few-shot learning." Fine-tuning allows you to train a model with many more examples that you can tailor to meet your specific use-case, thus improving on few-shot learning. Fine-tuning can reduce the number of tokens in the prompt leading to potential cost savings and requests with lower latency. 
+
+Turning natural language into a query language is just one use case where you can  "_show not tell_" the model how to behave. Here are some other use cases:
 
-Turning natural language into a query language is just one use case where you can  _show not tell_ the model how to behave. Here are some additional use cases:
 - Improve the model's handling of retrieved data
 - Steer model to output content in a specific style, tone, or format
 - Improve the accuracy when you look up information
 - Reduce the length of your prompt
-- Teach new skills (i.e. natural language to code)
+- Teach new skills (that is, natural language to code)
 
-If you identify cost as your primary motivator, proceed with caution. Fine-tuning might reduce costs for certain use cases by shortening prompts or allowing you to use a smaller model. But there may be a higher upfront cost to training, and you have to pay for hosting your own custom model. 
+If you identify cost as your primary motivator, proceed with caution. Fine-tuning might reduce costs for certain use cases by shortening prompts or allowing you to use a smaller model. But there might be a higher upfront cost to training, and you have to pay for hosting your own custom model. 
 
 ### Steps to fine-tune a model
+
 Here are the general steps to fine-tune a model:
-1. Based on your use case, choose a model that supports your task
-2. Prepare and upload training data
-3. (Optional) Prepare and upload validation data
-4. (Optional) Configure task parameters
-5. Train your model. 
-6. Once completed, review metrics and evaluate model. If the results don't meet your benchmark, then go back to step 2.
-7. Use your fine-tuned model
+
+1. Choose a model that supports your task.
+1. Prepare and upload training data.
+1. (Optional) Prepare and upload validation data.
+1. (Optional) Configure task parameters.
+1. Train your model. 
+1. Once completed, review metrics and evaluate model. If the results don't meet your benchmark, then go back to step 2.
+1. Use your fine-tuned model.
 
 It's important to call out that fine-tuning is heavily dependent on the quality of data that you can provide. It's best practice to provide hundreds, if not thousands, of training examples to be successful and get your desired results.
 
@@ -87,7 +92,6 @@ For more information on fine-tuning using a managed compute (preview), see [Fine
 
 For details about Azure OpenAI models that are available for fine-tuning, see the [Azure OpenAI Service models documentation](../../ai-services/openai/concepts/models.md#fine-tuning-models) or the [Azure OpenAI models table](#fine-tuning-azure-openai-models) later in this guide.
 
-
 For the Azure OpenAI  Service models that you can fine tune, supported regions for fine-tuning include North Central US, Sweden Central, and more.
 
 ### Fine-tuning Azure OpenAI models

@@ -14,7 +14,7 @@ metadata:
   author: sdgilley
 title: Azure AI Foundry frequently asked questions
 summary: |
-  If you can't find answers to your questions in this document, and still need help check the [Azure AI services support options guide](../ai-services/cognitive-services-support-options.md?context=/azure/ai-services/openai/context/context). Azure OpenAI is part of Azure AI services.
+  FAQ for [Azure AI Foundry](https://ai.azure.com). If you can't find answers to your questions in this document, and still need help check the [Azure AI services support options guide](../ai-services/cognitive-services-support-options.md?context=/azure/ai-services/openai/context/context). Azure OpenAI is part of Azure AI services.
 sections:
   - name: General questions
     questions:

@@ -20,7 +20,7 @@ author: sdgilley
 
 [!INCLUDE [feature-preview](../includes/feature-preview.md)]
 
-You need a compute session to run [prompt flows](prompt-flow.md). Use Azure AI Foundry to create and manage prompt flow compute sessions.
+You need a compute session to run [prompt flows](prompt-flow.md). Use [Azure AI Foundry](https://ai.azure.com) to create and manage prompt flow compute sessions.
 
 A prompt flow compute session has computing resources that are required for the application to run, including a Docker image that contains all necessary dependency packages. In addition to flow execution, Azure AI Foundry uses the compute session to ensure the accuracy and functionality of the tools incorporated within the flow when you make updates to the prompt or code content.
 

@@ -18,7 +18,7 @@ author: sdgilley
 
 # Create a project in Azure AI Foundry portal
 
-This article describes how to create an Azure AI Foundry project. A project is used to organize your work and save state while building customized AI apps. 
+This article describes how to create an [Azure AI Foundry](https://ai.azure.com) project. A project is used to organize your work and save state while building customized AI apps. 
 
 Projects are hosted by an Azure AI Foundry hub. If your company has an administrative team that has created a hub for you, you can create a project from that hub. If you are working on your own, you can create a project and a default hub will automatically be created for you.
 

@@ -29,6 +29,18 @@ The Phi-4 family of small language models (SLMs) is a collection of instruction-
 
 The Phi-4 family chat models include the following models:
 
+# [Phi-4-multimodal-instruct](#tab/phi-4-multimodal-instruct)
+
+Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, and generates text outputs. The model underwent an enhancement process, incorporating both supervised fine-tuning, and direct preference optimization to support precise instruction adherence and safety measures.
+
+The Phi-4-multimodal-instruct model comes in the following variant with a 128K token length.
+
+
+The following models are available:
+
+* [Phi-4-multimodal-instruct](https://aka.ms/azureai/landing/Phi-4-multimodal-instruct)
+
+
 # [Phi-4-mini-instruct](#tab/phi-4-mini-instruct)
 
 Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures. 
@@ -155,7 +167,7 @@ print("Model provider name:", model_info.model_provider_name)
 ```
 
 ```console
-Model name: Phi-4-mini-instruct
+Model name: Phi-4-multimodal-instruct
 Model type: chat-completions
 Model provider name: Microsoft
 ```
@@ -176,7 +188,7 @@ response = client.complete(
 ```
 
 > [!NOTE]
-> Phi-4-mini-instruct and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-4-multimodal-instruct, Phi-4-mini-instruct, and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -192,7 +204,7 @@ print("\tCompletion tokens:", response.usage.completion_tokens)
 
 ```console
 Response: As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.
-Model: Phi-4-mini-instruct
+Model: Phi-4-multimodal-instruct
 Usage: 
   Prompt tokens: 19
   Total tokens: 91
@@ -341,6 +353,18 @@ except HttpResponseError as ex:
 
 The Phi-4 family chat models include the following models:
 
+# [Phi-4-multimodal-instruct](#tab/phi-4-multimodal-instruct)
+
+Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, and generates text outputs. The model underwent an enhancement process, incorporating both supervised fine-tuning, and direct preference optimization to support precise instruction adherence and safety measures.
+
+The Phi-4-multimodal-instruct model comes in the following variant with a 128K token length.
+
+
+The following models are available:
+
+* [Phi-4-multimodal-instruct](https://aka.ms/azureai/landing/Phi-4-multimodal-instruct)
+
+
 # [Phi-4-mini-instruct](#tab/phi-4-mini-instruct)
 
 Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures. 
@@ -465,7 +489,7 @@ console.log("Model provider name: ", model_info.body.model_provider_name)
 ```
 
 ```console
-Model name: Phi-4-mini-instruct
+Model name: Phi-4-multimodal-instruct
 Model type: chat-completions
 Model provider name: Microsoft
 ```
@@ -488,7 +512,7 @@ var response = await client.path("/chat/completions").post({
 ```
 
 > [!NOTE]
-> Phi-4-mini-instruct and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-4-multimodal-instruct, Phi-4-mini-instruct, and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -508,7 +532,7 @@ console.log("\tCompletion tokens:", response.body.usage.completion_tokens);
 
 ```console
 Response: As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.
-Model: Phi-4-mini-instruct
+Model: Phi-4-multimodal-instruct
 Usage: 
   Prompt tokens: 19
   Total tokens: 91
@@ -676,6 +700,18 @@ catch (error) {
 
 The Phi-4 family chat models include the following models:
 
+# [Phi-4-multimodal-instruct](#tab/phi-4-multimodal-instruct)
+
+Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, and generates text outputs. The model underwent an enhancement process, incorporating both supervised fine-tuning, and direct preference optimization to support precise instruction adherence and safety measures.
+
+The Phi-4-multimodal-instruct model comes in the following variant with a 128K token length.
+
+
+The following models are available:
+
+* [Phi-4-multimodal-instruct](https://aka.ms/azureai/landing/Phi-4-multimodal-instruct)
+
+
 # [Phi-4-mini-instruct](#tab/phi-4-mini-instruct)
 
 Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures. 
@@ -815,7 +851,7 @@ Console.WriteLine($"Model provider name: {modelInfo.Value.ModelProviderName}");
 ```
 
 ```console
-Model name: Phi-4-mini-instruct
+Model name: Phi-4-multimodal-instruct
 Model type: chat-completions
 Model provider name: Microsoft
 ```
@@ -837,7 +873,7 @@ Response<ChatCompletions> response = client.Complete(requestOptions);
 ```
 
 > [!NOTE]
-> Phi-4-mini-instruct and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-4-multimodal-instruct, Phi-4-mini-instruct, and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -853,7 +889,7 @@ Console.WriteLine($"\tCompletion tokens: {response.Value.Usage.CompletionTokens}
 
 ```console
 Response: As of now, it's estimated that there are about 7,000 languages spoken around the world. However, this number can vary as some languages become extinct and new ones develop. It's also important to note that the number of speakers can greatly vary between languages, with some having millions of speakers and others only a few hundred.
-Model: Phi-4-mini-instruct
+Model: Phi-4-multimodal-instruct
 Usage: 
   Prompt tokens: 19
   Total tokens: 91
@@ -1023,6 +1059,18 @@ catch (RequestFailedException ex)
 
 The Phi-4 family chat models include the following models:
 
+# [Phi-4-multimodal-instruct](#tab/phi-4-multimodal-instruct)
+
+Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, and generates text outputs. The model underwent an enhancement process, incorporating both supervised fine-tuning, and direct preference optimization to support precise instruction adherence and safety measures.
+
+The Phi-4-multimodal-instruct model comes in the following variant with a 128K token length.
+
+
+The following models are available:
+
+* [Phi-4-multimodal-instruct](https://aka.ms/azureai/landing/Phi-4-multimodal-instruct)
+
+
 # [Phi-4-mini-instruct](#tab/phi-4-mini-instruct)
 
 Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures. 
@@ -1113,7 +1161,7 @@ The response is as follows:
 
 ```json
 {
-    "model_name": "Phi-4-mini-instruct",
+    "model_name": "Phi-4-multimodal-instruct",
     "model_type": "chat-completions",
     "model_provider_name": "Microsoft"
 }
@@ -1139,7 +1187,7 @@ The following example shows how you can create a basic chat completions request
 ```
 
 > [!NOTE]
-> Phi-4-mini-instruct and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
+> Phi-4-multimodal-instruct, Phi-4-mini-instruct, and Phi-4 don't support system messages (`role="system"`). When you use the Azure AI model inference API, system messages are translated to user messages, which is the closest capability available. This translation is offered for convenience, but it's important for you to verify that the model is following the instructions in the system message with the right level of confidence.
 
 The response is as follows, where you can see the model's usage statistics:
 
@@ -1149,7 +1197,7 @@ The response is as follows, where you can see the model's usage statistics:
     "id": "0a1234b5de6789f01gh2i345j6789klm",
     "object": "chat.completion",
     "created": 1718726686,
-    "model": "Phi-4-mini-instruct",
+    "model": "Phi-4-multimodal-instruct",
     "choices": [
         {
             "index": 0,
@@ -1206,7 +1254,7 @@ You can visualize how streaming generates content:
     "id": "23b54589eba14564ad8a2e6978775a39",
     "object": "chat.completion.chunk",
     "created": 1718726371,
-    "model": "Phi-4-mini-instruct",
+    "model": "Phi-4-multimodal-instruct",
     "choices": [
         {
             "index": 0,
@@ -1229,7 +1277,7 @@ The last message in the stream has `finish_reason` set, indicating the reason fo
     "id": "23b54589eba14564ad8a2e6978775a39",
     "object": "chat.completion.chunk",
     "created": 1718726371,
-    "model": "Phi-4-mini-instruct",
+    "model": "Phi-4-multimodal-instruct",
     "choices": [
         {
             "index": 0,
@@ -1280,7 +1328,7 @@ Explore other parameters that you can specify in the inference client. For a ful
     "id": "0a1234b5de6789f01gh2i345j6789klm",
     "object": "chat.completion",
     "created": 1718726686,
-    "model": "Phi-4-mini-instruct",
+    "model": "Phi-4-multimodal-instruct",
     "choices": [
         {
             "index": 0,

@@ -1,58 +1,59 @@
 ---
 title: How to get started with an AI template
 titleSuffix: Azure AI Foundry
-description: This article provides instructions on how to get started with an AI template.
+description: This article provides instructions on how to use an AI template to get started with Azure AI Foundry.
 manager: scottpolly
 ms.service: azure-ai-foundry
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 01/02/2025
-ms.reviewer: dantaylo
+ms.date: 02/20/2025
+ms.reviewer: varundua
 ms.author: sgilley
 author: sdgilley
+#customer intent: As a developer, I want to jump start my journey with an AI template.
 ---
 
-# How to get started with an AI template
+# 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.
 
 [!INCLUDE [feature-preview](../../includes/feature-preview.md)]
 
-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.
+## Prerequisites
 
-> [!TIP]
-> Discover the latest templates in our curated [AZD templates collection](https://aka.ms/azd-ai-templates). Deploy them with a single command ```azd up``` using the [Azure Developer CLI](/azure/developer/azure-developer-cli/). 
+- [Azure subscription](https://azure.microsoft.com/free)
+- An [Azure AI Foundry project](../create-projects.md).
 
 ## Start with a sample application
 
-Start with our sample applications! Choose the right template for your needs, then refer to the README in any of the following Azure Developer CLI enabled templates for more instructions and information.
+1. Go to [Azure AI Foundry portal](https://ai.azure.com).
+1. Open your project in Azure AI Foundry portal.
+1. On the left menu, select **Code** (preview).
+1. Find the solution template you want to use.
+1. Select **Open in Github** to view the entire sample application.
+1. Or, clone the repository to your local machine with the provided command.
+1. In some cases, you can also view a step-by-step tutorial that explains the AI code.
 
-### [Python](#tab/python)
+## Explore the sample application
 
-| Template      | App host | Tech stack | Description |
-| ----------- | ----------| ----------- | ------------|
-| [Azure AI Basic Template with Python](https://github.com/azure-samples/azureai-basic-python) | [Azure AI Foundry online endpoints](/azure/machine-learning/concept-endpoints-online) | [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure OpenAI Service](../../../ai-services/openai/overview.md), Bicep | The app serves as a straightforward example of integrating Azure AI Services within a basic prompt-based application. This template walks you through building a simple chat app that utilizes models and prompts. The template also covers setting up the necessary infrastructure for the app, including creating an Azure AI Foundry Hub, configuring projects, and provisioning essential resources such as Azure AI Service, Azure Container Apps, Cognitive Search, and more. <br>You can build, deploy, and test it with a single command.  |
-| [Contoso Chat Retail copilot with Azure AI Foundry](https://github.com/Azure-Samples/contoso-chat) | [Azure Container Apps](/azure/container-apps/overview) | [Azure Cosmos DB](/azure/cosmos-db/index-overview), [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure OpenAI Service](../../../ai-services/openai/overview.md), [Azure AI Search](/azure/search/search-what-is-azure-search), Bicep  | A retailer conversation agent that can answer questions grounded in your product catalog and customer order history. This template uses a retrieval augmented generation architecture with cutting-edge models for chat completion, chat evaluation, and embeddings. Build, evaluate, and deploy, an end-to-end solution with a single command. | 
-| [Process Automation: speech to text and summarization with Azure AI Foundry](https://github.com/Azure-Samples/summarization-openai-python-prompflow) | [Azure AI Foundry online endpoints](/azure/machine-learning/concept-endpoints-online) | [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure OpenAI Service](../../../ai-services/openai/overview.md), [Azure AI speech to text service](../../../ai-services/speech-service/index-speech-to-text.yml), Bicep  | An app for workers to report issues via text or speech, translating audio to text, summarizing it, and specify the relevant department. | 
-| [Multi-Modal Creative Writing copilot with Dalle](https://github.com/Azure-Samples/agent-openai-python-prompty) | [Azure AI Foundry online endpoints](/azure/machine-learning/concept-endpoints-online) | [Azure AI Search](/azure/search/search-what-is-azure-search), [Azure OpenAI Service](../../../ai-services/openai/overview.md), Bicep | demonstrates how to create and work with AI agents. The app takes a topic and instruction input and then calls a research agent, writer agent, and editor agent. |  
-| [Assistant API Analytics Copilot with Python and Azure AI Foundry](https://github.com/Azure-Samples/assistant-data-openai-python-promptflow) | [Azure AI Foundry online endpoints](/azure/machine-learning/concept-endpoints-online) |  [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure AI Search](/azure/search/search-what-is-azure-search), [Azure OpenAI Service](../../../ai-services/openai/overview.md), Bicep| A data analytics chatbot based on the Assistants API. The chatbot can answer questions in natural language, and interpret them as queries on an example sales dataset. |
-<!-- remove for now
-| Function Calling with Prompty, LangChain, and Pinecone | [Azure AI Foundry online endpoints](/azure/machine-learning/concept-endpoints-online) | [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure OpenAI Service](../../../ai-services/openai/overview.md), [LangChain](https://python.langchain.com/v0.1/docs/get_started/introduction), [Pinecone](https://www.pinecone.io/), Bicep  | Utilize the new Prompty tool, LangChain, and Pinecone to build a large language model (LLM) search agent. This agent with Retrieval-Augmented Generation (RAG) technology is capable of answering user questions based on the provided data by integrating real-time information retrieval with generative responses. | 
-| Function Calling with Prompty, LangChain, and Elastic Search | [Azure AI Foundry online endpoints](/azure/machine-learning/concept-endpoints-online) | [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure OpenAI Service](../../../ai-services/openai/overview.md), [Elastic Search](https://www.elastic.co/elasticsearch), [LangChain](https://python.langchain.com/v0.1/docs/get_started/introduction) , Bicep  | Utilize the new Prompty tool, LangChain, and Elasticsearch to build a large language model (LLM) search agent. This agent with Retrieval-Augmented Generation (RAG) technology is capable of answering user questions based on the provided data by integrating real-time information retrieval with generative responses |
--->
+Once you're looking at the GitHub repository for your sample, refer to the README for more instructions and information on how to deploy your own version of the application.
 
+Instructions vary by sample, but most include how to:
 
-### [C#](#tab/csharp)
+* Open the solution in the location of your choice:
+  * GitHub Codespaces
+  * VS Code Dev Containers
+  * Your local IDE
+* Deploy the application to Azure
+* How to test the app
 
-| Template      | App host | Tech stack | Description |
-| ----------- | ----------| ----------- | -------------- |
-| [Contoso Chat Retail copilot with .NET and Semantic Kernel](https://github.com/Azure-Samples/contoso-chat-csharp-prompty) | [Azure Container Apps](/azure/container-apps/overview) | [Azure Cosmos DB](/azure/cosmos-db/index-overview), [Azure Monitor](/azure/azure-monitor/overview), [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure Container Apps](/azure/container-apps/overview), [Azure AI Search](/azure/search/search-what-is-azure-search), [Azure OpenAI Services](../../../ai-services/openai/overview.md), [Semantic Kernel](/semantic-kernel/overview/?tabs=Csharp), Bicep | A retailer conversation agent that can answer questions grounded in your product catalog and customer order history. This template uses a retrieval augmented generation architecture with cutting-edge models for chat completion, chat evaluation, and embeddings. Build, evaluate, and deploy, an end-to-end solution with a single command. |
-| [Process Automation: speech to text and summarization with .NET and GPT 3.5 Turbo](https://github.com/Azure-Samples/summarization-openai-csharp-prompty) | [Azure Container Apps](/azure/container-apps/overview) | [Azure Managed Identity](/entra/identity/managed-identities-azure-resources/overview), [Azure OpenAI Service](../../../ai-services/openai/overview.md), [Azure AI speech to text service](../../../ai-services/speech-service/index-speech-to-text.yml), Bicep | An app for workers to report issues via text or speech, translating audio to text, summarizing it, and specify the relevant department. |
-
----
+The README also includes information about the application, such as the use case, architecture, and pricing information.
 
+> [!TIP]
+> Discover more templates in our curated [AZD templates collection](https://azure.github.io/ai-app-templates). Deploy them with a single command ```azd up``` using the [Azure Developer CLI](/azure/developer/azure-developer-cli/).
 
 ## Related content
 
-- [Get started building a chat app using the prompt flow SDK](../../quickstarts/get-started-code.md)
-- [Work with projects in VS Code](vscode.md)
-- [Connections in Azure AI Foundry portal](../../concepts/connections.md)
+- [Get started building a chat app using the Azure AI Foundry SDK](../../quickstarts/get-started-code.md)
+- [Develop AI apps using Azure AI services](/azure/developer/ai/)

@@ -16,7 +16,7 @@ author: sdgilley
 
 [!INCLUDE [feature-preview](../../includes/feature-preview.md)]
 
-In this article, you learn how to create the following Azure AI Foundry resources using the Azure Machine Learning SDK and Azure CLI (with machine learning extension):
+In this article, you learn how to create the following [Azure AI Foundry](https://ai.azure.com) resources using the Azure Machine Learning SDK and Azure CLI (with machine learning extension):
 - An Azure AI Foundry hub
 - An Azure AI Services connection
 

@@ -8,7 +8,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: overview
-ms.date: 11/25/2024
+ms.date: 02/27/2025
 ms.reviewer: dantaylo
 ms.author: sgilley
 author: sdgilley
@@ -18,7 +18,7 @@ zone_pivot_groups: programming-languages-sdk-overview
 
 # The Azure AI Foundry SDK
 
-The Azure AI Foundry SDK is a comprehensive toolchain designed to simplify the development of AI applications on Azure. It enables developers to:
+The [Azure AI Foundry](https://ai.azure.com) SDK is a comprehensive toolchain designed to simplify the development of AI applications on Azure. It enables developers to:
 
 - Access popular models from various model providers through a single interface
 - Easily combine together models, data, and AI services to build AI-powered applications
@@ -111,7 +111,7 @@ Not yet available in C#.
 
 Copy the **Project connection string** from the **Overview** page of the project and update the connections string value above.
 
-Once you have created the project client, you can use the client for the capabilities in the following sections.
+Once you create the project client, you can use the client for the capabilities in the following sections.
 
 ::: zone pivot="programming-language-python"
 
@@ -127,7 +127,7 @@ Be sure to check out the [reference](https://aka.ms/aifoundrysdk/reference) and
 
 ## Azure OpenAI Service
 
-The [Azure OpenAI Service](../../../ai-services/openai/overview.md) provides access to OpenAI's models including the GPT-4o, GPT-4o mini, GPT-4, GPT-4 Turbo with Vision, DALLE-3, Whisper, and Embeddings model series with the data residency, scalability, safety, security and enterprise capabilities of Azure.
+The [Azure OpenAI Service](../../../ai-services/openai/overview.md) provides access to OpenAI's models including the GPT-4o, GPT-4o mini, GPT-4, GPT-4 Turbo with Vision, DALLE-3, Whisper, and Embeddings model series with the data residency, scalability, safety, security, and enterprise capabilities of Azure.
 
 If you have code that uses the OpenAI SDK, you can easily target your code to use the Azure OpenAI service. First, install the OpenAI SDK:
 
@@ -233,9 +233,9 @@ To learn more about using the Azure AI inferencing client, check out the [Azure
 
 ::: zone pivot="programming-language-python"
 
-## Prompt Templates
+## Prompt templates
 
-The inferencing client supports for creating prompt messages from templates.  The template allows you to dynamically generate prompts using inputs that are available at runtime.
+The inferencing client supports creating prompt messages from templates. The template allows you to dynamically generate prompts using inputs that are available at runtime.
 
 To use prompt templates, install the `azure-ai-inference` package:
 
@@ -356,7 +356,7 @@ To learn more about using Azure AI Search, check out [Azure AI Search documentat
 
 ## Azure AI Agent Service
 
-Azure AI Agent Service is a fully managed service designed to empower developers to securely build, deploy, and scale high-quality, and extensible AI agents. Using an extensive ecosystem of models, tools and capabilities from OpenAI, Microsoft, and third-party providers, [Azure AI Agent Service](/azure/ai-services/agents) enables building agents for a wide range of generative AI use cases.
+Azure AI Agent Service is a fully managed service designed to empower developers to securely build, deploy, and scale high-quality, and extensible AI agents. To enable building agents for a wide range of generative AI use cases, [Azure AI Agent Service](/azure/ai-services/agents) uses an extensive ecosystem of models, tools and capabilities from OpenAI, Microsoft, and third-party providers.
 
 ## Evaluation
 
@@ -393,7 +393,7 @@ To learn more, check out [Evaluation using the SDK](evaluate-sdk.md).
 
 ::: zone pivot="programming-language-csharp"
 
-An Azure AI evaluation package is not yet available for C#. For a sample on how to use Prompty and Semantic Kernel for evaluation, see the [contoso-chat-csharp-prompty](https://github.com/Azure-Samples/contoso-chat-csharp-prompty/blob/main/src/ContosoChatAPI/ContosoChat.Evaluation.Tests/Evalutate.cs) sample.
+An Azure AI evaluation package isn't yet available for C#. For a sample on how to use Prompty and Semantic Kernel for evaluation, see the [contoso-chat-csharp-prompty](https://github.com/Azure-Samples/contoso-chat-csharp-prompty/blob/main/src/ContosoChatAPI/ContosoChat.Evaluation.Tests/Evalutate.cs) sample.
 
 ::: zone-end
 
@@ -428,41 +428,43 @@ if application_insights_connection_string:
 
 ::: zone pivot="programming-language-csharp"
 
-Tracing is not yet integrated into the projects package. For instructions on how to instrument and log traces from the Azure AI Inferencing package, see [azure-sdk-for-dotnet](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/ai/Azure.AI.Inference/samples/Sample8_ChatCompletionsWithOpenTelemetry.md).
+Tracing isn't yet integrated into the projects package. For instructions on how to instrument and log traces from the Azure AI Inferencing package, see [azure-sdk-for-dotnet](https://github.com/Azure/azure-sdk-for-net/blob/main/sdk/ai/Azure.AI.Inference/samples/Sample8_ChatCompletionsWithOpenTelemetry.md).
 
 ::: zone-end
 
-## Related content
+## Other services and frameworks
 
-Below are some helpful links to other services and frameworks that you can use with the Azure AI Foundry SDK.
+The following sections provide helpful links to other services and frameworks that you can use with the Azure AI Foundry SDK.
 
 ### Azure AI Services
 
-Client libraries:
+* Client libraries:
 
-* [Azure AI services SDKs](../../../ai-services/reference/sdk-package-resources.md?context=/azure/ai-studio/context/context)
-* [Azure AI services REST APIs](../../../ai-services/reference/rest-api-resources.md?context=/azure/ai-studio/context/context) 
+    * [Azure AI services SDKs](../../../ai-services/reference/sdk-package-resources.md?context=/azure/ai-studio/context/context)
+    * [Azure AI services REST APIs](../../../ai-services/reference/rest-api-resources.md?context=/azure/ai-studio/context/context) 
 
-Management libraries:
-* [Azure AI Services Python Management Library](/python/api/overview/azure/mgmt-cognitiveservices-readme)
-* [Azure AI Search Python Management Library](/python/api/azure-mgmt-search/azure.mgmt.search)
+* Management libraries:
+
+    * [Azure AI Services Python Management Library](/python/api/overview/azure/mgmt-cognitiveservices-readme)
+    * [Azure AI Search Python Management Library](/python/api/azure-mgmt-search/azure.mgmt.search)
 
 ### Frameworks
 
-Azure Machine Learning
+* Azure Machine Learning
+
+    * [Azure Machine Learning Python SDK (v2)](/python/api/overview/azure/ai-ml-readme)
+    * [Azure Machine Learning CLI (v2)](/azure/machine-learning/how-to-configure-cli)
+    * [Azure Machine Learning REST API](/rest/api/azureml) 
 
-* [Azure Machine Learning Python SDK (v2)](/python/api/overview/azure/ai-ml-readme)
-* [Azure Machine Learning CLI (v2)](/azure/machine-learning/how-to-configure-cli)
-* [Azure Machine Learning REST API](/rest/api/azureml) 
+* Prompt flow
 
-Prompt flow
+    * [Prompt flow SDK](https://microsoft.github.io/promptflow/how-to-guides/quick-start.html)
+    * [pfazure CLI](https://microsoft.github.io/promptflow/reference/pfazure-command-reference.html)
+    * [pfazure Python library](https://microsoft.github.io/promptflow/reference/python-library-reference/promptflow-azure/promptflow.azure.html)
 
-* [Prompt flow SDK](https://microsoft.github.io/promptflow/how-to-guides/quick-start.html)
-* [pfazure CLI](https://microsoft.github.io/promptflow/reference/pfazure-command-reference.html)
-* [pfazure Python library](https://microsoft.github.io/promptflow/reference/python-library-reference/promptflow-azure/promptflow.azure.html)
+* Semantic Kernel
+    * [Semantic Kernel Overview](/semantic-kernel/overview/)
 
-Semantic Kernel
- * [Semantic Kernel Overview](/semantic-kernel/overview/)
-Agentic frameworks
+* Agentic frameworks
 
-* [LlamaIndex](llama-index.md)
+    * [LlamaIndex](llama-index.md)

@@ -20,7 +20,7 @@ author: sdgilley
 
 [!INCLUDE [feature-preview](../../includes/feature-preview.md)]
 
-Azure AI Foundry supports developing in VS Code - Desktop and Web. In each scenario, your VS Code instance is remotely connected to a prebuilt custom container running on a virtual machine, also known as a compute instance.
+[Azure AI Foundry](https://ai.azure.com) supports developing in VS Code - Desktop and Web. In each scenario, your VS Code instance is remotely connected to a prebuilt custom container running on a virtual machine, also known as a compute instance.
 
 ## Launch VS Code from Azure AI Foundry
 

@@ -84,7 +84,7 @@ Gretel | Not available | Gretel-Navigator
 Healthcare AI family Models | MedImageParse<BR>  MedImageInsight<BR>  CxrReportGen<BR>  Virchow<BR>  Virchow2<BR>  Prism<BR>  BiomedCLIP-PubMedBERT<BR>  microsoft-llava-med-v1.5<BR>  m42-health-llama3-med4<BR>  biomistral-biomistral-7b<BR>  microsoft-biogpt-large-pub<BR>  microsoft-biomednlp-pub<BR>  stanford-crfm-biomedlm<BR>  medicalai-clinicalbert<BR>  microsoft-biogpt<BR>  microsoft-biogpt-large<BR>  microsoft-biomednlp-pub<BR> | Not Available
 JAIS | Not available | jais-30b-chat
 Meta Llama family models | Llama-3.3-70B-Instruct<BR> Llama-3.2-3B-Instruct<BR>  Llama-3.2-1B-Instruct<BR>  Llama-3.2-1B<BR>  Llama-3.2-90B-Vision-Instruct<BR>  Llama-3.2-11B-Vision-Instruct<BR>  Llama-3.1-8B-Instruct<BR>  Llama-3.1-8B<BR>  Llama-3.1-70B-Instruct<BR>  Llama-3.1-70B<BR>  Llama-3-8B-Instruct<BR>  Llama-3-70B<BR>  Llama-3-8B<BR>  Llama-Guard-3-1B<BR>  Llama-Guard-3-8B<BR>  Llama-Guard-3-11B-Vision<BR>  Llama-2-7b<BR>  Llama-2-70b<BR>  Llama-2-7b-chat<BR>  Llama-2-13b-chat<BR>  CodeLlama-7b-hf<BR>  CodeLlama-7b-Instruct-hf<BR>  CodeLlama-34b-hf<BR>  CodeLlama-34b-Python-hf<BR>  CodeLlama-34b-Instruct-hf<BR>  CodeLlama-13b-Instruct-hf<BR>  CodeLlama-13b-Python-hf<BR>  Prompt-Guard-86M<BR>  CodeLlama-70b-hf<BR> | Llama-3.3-70B-Instruct<BR> Llama-3.2-90B-Vision-Instruct<br>  Llama-3.2-11B-Vision-Instruct<br>  Llama-3.1-8B-Instruct<br>  Llama-3.1-70B-Instruct<br>  Llama-3.1-405B-Instruct<br>  Llama-3-8B-Instruct<br>  Llama-3-70B-Instruct<br>  Llama-2-7b<br>  Llama-2-7b-chat<br>  Llama-2-70b<br>  Llama-2-70b-chat<br>  Llama-2-13b<br>  Llama-2-13b-chat<br>
-Microsoft Phi family models | Phi-3-mini-4k-Instruct <br> Phi-3-mini-128k-Instruct <br> Phi-3-small-8k-Instruct <br> Phi-3-small-128k-Instruct <br> Phi-3-medium-4k-instruct <br> Phi-3-medium-128k-instruct <br> Phi-3-vision-128k-Instruct <br> Phi-3.5-mini-Instruct <br> Phi-3.5-vision-Instruct <br> Phi-3.5-MoE-Instruct <br> Phi-4 <br> Phi-4-mini-instruct | Phi-3-mini-4k-Instruct <br> Phi-3-mini-128k-Instruct <br> Phi-3-small-8k-Instruct <br> Phi-3-small-128k-Instruct <br> Phi-3-medium-4k-instruct <br> Phi-3-medium-128k-instruct <br> <br> Phi-3.5-mini-Instruct <br> Phi-3.5-vision-Instruct <br> Phi-3.5-MoE-Instruct <br> Phi-4 <br> Phi-4-mini-instruct
+Microsoft Phi family models | Phi-3-mini-4k-Instruct <br> Phi-3-mini-128k-Instruct <br> Phi-3-small-8k-Instruct <br> Phi-3-small-128k-Instruct <br> Phi-3-medium-4k-instruct <br> Phi-3-medium-128k-instruct <br> Phi-3-vision-128k-Instruct <br> Phi-3.5-mini-Instruct <br> Phi-3.5-vision-Instruct <br> Phi-3.5-MoE-Instruct <br> Phi-4 <br> Phi-4-mini-instruct <br> Phi-4-multimodal-instruct | Phi-3-mini-4k-Instruct <br> Phi-3-mini-128k-Instruct <br> Phi-3-small-8k-Instruct <br> Phi-3-small-128k-Instruct <br> Phi-3-medium-4k-instruct <br> Phi-3-medium-128k-instruct <br> <br> Phi-3.5-mini-Instruct <br> Phi-3.5-vision-Instruct <br> Phi-3.5-MoE-Instruct <br> Phi-4 <br> Phi-4-mini-instruct <br> Phi-4-multimodal-instruct
 Mistral family models | mistralai-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x22B-Instruct-v0-1 <br> mistral-community-Mixtral-8x22B-v0-1 <br> mistralai-Mixtral-8x7B-v01 <br> mistralai-Mistral-7B-Instruct-v0-2 <br> mistralai-Mistral-7B-v01 <br> mistralai-Mixtral-8x7B-Instruct-v01 <br> mistralai-Mistral-7B-Instruct-v01 | Mistral-large (2402) <br> Mistral-large (2407) <br> Mistral-small <br> Ministral-3B <br> Mistral-NeMo
 Nixtla | Not available | TimeGEN-1
 

@@ -61,7 +61,7 @@ Llama 3.1 405B Instruct  | [Microsoft Managed countries/regions](/partner-center
 
 | Model | Offer Availability Region  | Hub/Project Region for Deployment  | Hub/Project Region for Fine tuning  |
 |---------|---------|---------|---------|
-Phi-4 <br>  Phi-4-mini-instruct    | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3  | Not available       |
+Phi-4 <br>  Phi-4-mini-instruct <br>  Phi-4-multimodal-instruct    | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3  | Not available       |
 Phi-3.5-vision-Instruct     | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3  | Not available       |
 Phi-3.5-MoE-Instruct     | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3  | East US 2       |
 Phi-3.5-Mini-Instruct     | Not applicable | East US <br> East US 2 <br> North Central US <br> South Central US <br> Sweden Central <br> West US <br> West US 3  | East US 2  | East US 2       |

@@ -16,7 +16,7 @@ author: sdgilley
 
 [!INCLUDE [feature-preview](../includes/feature-preview.md)]
 
-In this quickstart, we walk you through setting up your local development environment with the Azure AI Foundry SDK. We write a prompt, run it as part of your app code, trace the LLM calls being made, and run a basic evaluation on the outputs of the LLM.
+In this quickstart, we walk you through setting up your local development environment with the [Azure AI Foundry](https://ai.azure.com) SDK. We write a prompt, run it as part of your app code, trace the LLM calls being made, and run a basic evaluation on the outputs of the LLM.
 
 ## Prerequisites
 

@@ -15,7 +15,7 @@ ms.custom: copilot-learning-hub, ignite-2024
 
 # Tutorial:  Part 2 - Build a custom knowledge retrieval (RAG) app with the Azure AI Foundry SDK
 
-In this tutorial, you use the Azure AI Foundry SDK (and other libraries) to build, configure, and evaluate a chat app for your retail company called Contoso Trek. Your retail company specializes in outdoor camping gear and clothing. The chat app should answer questions about your products and services. For example, the chat app can answer questions such as "which tent is the most waterproof?" or "what is the best sleeping bag for cold weather?".
+In this tutorial, you use the [Azure AI Foundry](https://ai.azure.com) SDK (and other libraries) to build, configure, and evaluate a chat app for your retail company called Contoso Trek. Your retail company specializes in outdoor camping gear and clothing. The chat app should answer questions about your products and services. For example, the chat app can answer questions such as "which tent is the most waterproof?" or "what is the best sleeping bag for cold weather?".
 
 This part two shows you how to enhance a basic chat application by adding [retrieval augmented generation (RAG)](../concepts/retrieval-augmented-generation.md) to ground the responses in your custom data. Retrieval Augmented Generation (RAG) is a pattern that uses your data with a large language model (LLM) to generate answers specific to your data. In this part two, you learn how to:
 

@@ -16,7 +16,7 @@ author: sdgilley
 
 # Tutorial:  Part 1 - Set up project and development environment to build a custom knowledge retrieval (RAG) app with the Azure AI Foundry SDK
 
-In this tutorial, you use the Azure AI Foundry SDK (and other libraries) to build, configure, and evaluate a chat app for your retail company called Contoso Trek. Your retail company specializes in outdoor camping gear and clothing. The chat app should answer questions about your products and services. For example, the chat app can answer questions such as "which tent is the most waterproof?" or "what is the best sleeping bag for cold weather?".
+In this tutorial, you use the [Azure AI Foundry](https://ai.azure.com) SDK (and other libraries) to build, configure, and evaluate a chat app for your retail company called Contoso Trek. Your retail company specializes in outdoor camping gear and clothing. The chat app should answer questions about your products and services. For example, the chat app can answer questions such as "which tent is the most waterproof?" or "what is the best sleeping bag for cold weather?".
 
 This tutorial is part one of a three-part tutorial.  This part one gets you ready to write code in part two and evaluate your chat app in part three. In this part, you:
 

@@ -16,7 +16,7 @@ author: sdgilley
 
 # Tutorial: Part 3 - Evaluate a custom chat application with the Azure AI Foundry SDK
 
-In this tutorial, you use the Azure AI SDK (and other libraries) to  evaluate the chat app you built in [Part 2 of the tutorial series](copilot-sdk-build-rag.md). In this part three, you learn how to:
+In this tutorial, you use the [Azure AI Foundry](https://ai.azure.com) SDK (and other libraries) to  evaluate the chat app you built in [Part 2 of the tutorial series](copilot-sdk-build-rag.md). In this part three, you learn how to:
 
 > [!div class="checklist"]
 > - Create an evaluation dataset

@@ -20,7 +20,7 @@ This article is for people who use screen readers such as [Microsoft's Narrator]
 
 ## Getting oriented in Azure AI Foundry portal 
 
-Most Azure AI Foundry pages are composed of the following landmark structure: 
+Most [Azure AI Foundry](https://ai.azure.com) pages are composed of the following landmark structure: 
 
 - Banner (contains Azure AI Foundry app title, settings, and profile information)
     - Might sometimes contain a breadcrumb navigation element