This example shows how to use GeminiChatAgent for image chat with Gemini model.

To run this example, you need to have a project on Google Cloud with access to Vertex AI API. For more information please refer to Google Vertex AI.

Note

You can find the complete sample code here

Step 1: Install AutoGen.Gemini

First, install the AutoGen.Gemini package using the following command:

dotnet add package AutoGen.Gemini

Step 2: Add using statement

using AutoGen.Core;

Step 3: Create a Gemini agent

var projectID = Environment.GetEnvironmentVariable("GCP_VERTEX_PROJECT_ID");

if (projectID is null)
{
    Console.WriteLine("Please set GCP_VERTEX_PROJECT_ID environment variable.");
    return;
}

var geminiAgent = new GeminiChatAgent(
    name: "gemini",
    model: "gemini-1.5-flash-001",
    location: "us-east4",
    project: projectID,
    systemMessage: "You explain image content to user")
    .RegisterMessageConnector()
    .RegisterPrintMessage();

Step 4: Send image to Gemini

var imagePath = Path.Combine("resource", "images", "background.png");
var image = await File.ReadAllBytesAsync(imagePath);
var imageMessage = new ImageMessage(Role.User, BinaryData.FromBytes(image, "image/png"));
var reply = await geminiAgent.SendAsync("what's in the image", [imageMessage]);