.NET: Adding Image Multi Modality Sample (#688)

* Adding Multi Modal Sample

* Address typos

* Update sample to Azure OpenAI

* Update readme

* Update readme

* Update readme

* Use thread

dotnet/agent-framework-dotnet.slnx

@@ -48,6 +48,7 @@
     <Project Path="samples/GettingStarted/Agents/Agent_Step08_Telemetry/Agent_Step08_Telemetry.csproj" />
     <Project Path="samples/GettingStarted/Agents/Agent_Step09_DependencyInjection/Agent_Step09_DependencyInjection.csproj" />
     <Project Path="samples/GettingStarted/Agents/Agent_Step10_AsMcpTool/Agent_Step10_AsMcpTool.csproj" />
+    <Project Path="samples/GettingStarted/Agents/Agent_Step11_UsingImages/Agent_Step11_UsingImages.csproj" />
   </Folder>
   <Folder Name="/Samples/GettingStarted/AgentWithOpenAI/">
     <File Path="samples/GettingStarted/AgentWithOpenAI/README.md" />

dotnet/samples/GettingStarted/Agents/Agent_Step11_UsingImages/Agent_Step11_UsingImages.csproj

@@ -0,0 +1,22 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>net9.0</TargetFramework>
+    <LangVersion>12</LangVersion>
+
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>disable</ImplicitUsings>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Azure.AI.OpenAI" />
+    <PackageReference Include="Azure.Identity" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Extensions.AI.Agents.OpenAI\Microsoft.Extensions.AI.Agents.OpenAI.csproj" />
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Extensions.AI.Agents\Microsoft.Extensions.AI.Agents.csproj" />
+  </ItemGroup>
+  
+</Project>

dotnet/samples/GettingStarted/Agents/Agent_Step11_UsingImages/Program.cs

@@ -0,0 +1,30 @@
+// Copyright (c) Microsoft. All rights reserved.
+
+// This sample shows how to use Image Multi-Modality with an AI agent.
+
+using System;
+using Azure.AI.OpenAI;
+using Azure.Identity;
+using Microsoft.Extensions.AI;
+using OpenAI;
+
+var endpoint = Environment.GetEnvironmentVariable("AZURE_OPENAI_ENDPOINT") ?? throw new InvalidOperationException("AZURE_OPENAI_ENDPOINT is not set.");
+var deploymentName = System.Environment.GetEnvironmentVariable("AZURE_OPENAI_DEPLOYMENT_NAME") ?? "gpt-4o";
+
+var agent = new AzureOpenAIClient(new Uri(endpoint), new AzureCliCredential())
+    .GetChatClient(deploymentName)
+    .CreateAIAgent(
+        name: "VisionAgent",
+        instructions: "You are a helpful agent that can analyze images");
+
+ChatMessage message = new(ChatRole.User, [
+    new TextContent("What do you see in this image?"),
+    new UriContent("https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", "image/jpeg")
+]);
+
+var thread = agent.GetNewThread();
+
+await foreach (var update in agent.RunStreamingAsync(message, thread))
+{
+    Console.WriteLine(update);
+}

dotnet/samples/GettingStarted/Agents/Agent_Step11_UsingImages/README.md

@@ -0,0 +1,52 @@
+# Using Images with AI Agents
+
+This sample demonstrates how to use image multi-modality with an AI agent. It shows how to create a vision-enabled agent that can analyze and describe images using Azure OpenAI.
+
+## What this sample demonstrates
+
+- Creating a persistent AI agent with vision capabilities
+- Sending both text and image content to an agent in a single message
+- Using `UriContent` to Uri referenced images
+- Processing multimodal input (text + image) with an AI agent
+
+## Key features
+
+- **Vision Agent**: Creates an agent specifically instructed to analyze images
+- **Multimodal Input**: Combines text questions with image uri in a single message
+- **Azure OpenAI Integration**: Uses AzureOpenAI LLM agents
+
+## Prerequisites
+
+Before running this sample, ensure you have:
+
+1. An Azure OpenAI project set up
+2. A compatible model deployment (e.g., gpt-4o)
+3. Azure CLI installed and authenticated
+
+## Environment Variables
+
+Set the following environment variables:
+
+```powershell
+$env:AZURE_OPENAI_ENDPOINT="https://your-resource.openai.azure.com/" # Replace with your Azure OpenAI endpoint
+$env:AZURE_OPENAI_DEPLOYMENT_NAME="gpt-4o" # Replace with your model deployment name (optional, defaults to gpt-4o)
+```
+
+## Run the sample
+
+Navigate to the sample directory and run:
+
+```powershell
+cd Agent_Step11_UsingImages
+dotnet run
+```
+
+## Expected behavior
+
+The sample will:
+
+1. Create a vision-enabled agent named "VisionAgent"
+2. Send a message containing both text ("What do you see in this image?") and a Uri image of a green walk
+3. The agent will analyze the image and provide a description
+4. Clean up resources by deleting the thread and agent
+

dotnet/samples/GettingStarted/Agents/README.md

@@ -36,6 +36,7 @@ Before you begin, ensure you have the following prerequisites:
 |[Telemetry with a simple agent](./Agent_Step08_Telemetry/)|This sample demonstrates how to add telemetry to a simple agent|
 |[Dependency injection with a simple agent](./Agent_Step09_DependencyInjection/)|This sample demonstrates how to add and resolve an agent with a dependency injection container|
 |[Exposing a simple agent as MCP tool](./Agent_Step10_AsMcpTool/)|This sample demonstrates how to expose an agent as an MCP tool|
+|[Using images with a simple agent](./Agent_Step11_UsingImages/)|This sample demonstrates how to use image multi-modality with an AI agent|
 
 ## Running the samples from the console