agent-framework/dotnet/samples/02-agents/Agents/Agent_Step08_UsingImages/Program.cs

// 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";

// WARNING: DefaultAzureCredential is convenient for development but requires careful consideration in production.
// In production, consider using a specific credential (e.g., ManagedIdentityCredential) to avoid
// latency issues, unintended credential probing, and potential security risks from fallback mechanisms.
var agent = new AzureOpenAIClient(new Uri(endpoint), new DefaultAzureCredential())
    .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 session = await agent.CreateSessionAsync();

await foreach (var update in agent.RunStreamingAsync(message, session))
{
    Console.WriteLine(update);
}