test

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

@@ -0,0 +1,20 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFrameworks>net10.0</TargetFrameworks>
+
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Azure.AI.OpenAI" />
+    <PackageReference Include="Azure.Identity" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\..\src\Microsoft.Agents.AI.OpenAI\Microsoft.Agents.AI.OpenAI.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 Azure.AI.OpenAI;
+using Azure.Identity;
+using Microsoft.Extensions.AI;
+using OpenAI.Chat;
+using ChatMessage = Microsoft.Extensions.AI.ChatMessage;
+
+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)
+    .AsAIAgent(
+        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 = await agent.GetNewThreadAsync();
+
+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
+