wehub-resource-sync
121 lines
5.2 KiB
C#
121 lines
5.2 KiB
C#
// Copyright (c) Microsoft. All rights reserved.
|
||
|
||
using Microsoft.SemanticKernel;
|
||
using Microsoft.SemanticKernel.ChatCompletion;
|
||
using Resources;
|
||
|
||
namespace ChatCompletion;
|
||
|
||
/// <summary>
|
||
/// This sample shows how to use Google's Gemini Chat Completion model with vision using VertexAI and GoogleAI APIs.
|
||
/// </summary>
|
||
public sealed class Google_GeminiVision(ITestOutputHelper output) : BaseTest(output)
|
||
{
|
||
[Fact]
|
||
public async Task GoogleAIChatCompletionWithVision()
|
||
{
|
||
Console.WriteLine("============= Google AI - Gemini Chat Completion with vision =============");
|
||
|
||
string geminiApiKey = TestConfiguration.GoogleAI.ApiKey;
|
||
string geminiModelId = TestConfiguration.GoogleAI.Gemini.ModelId;
|
||
|
||
if (geminiApiKey is null)
|
||
{
|
||
Console.WriteLine("Gemini credentials not found. Skipping example.");
|
||
return;
|
||
}
|
||
|
||
Kernel kernel = Kernel.CreateBuilder()
|
||
.AddGoogleAIGeminiChatCompletion(
|
||
modelId: geminiModelId,
|
||
apiKey: geminiApiKey)
|
||
.Build();
|
||
|
||
var chatHistory = new ChatHistory("Your job is describing images.");
|
||
var chatCompletionService = kernel.GetRequiredService<IChatCompletionService>();
|
||
|
||
// Load the image from the resources
|
||
await using var stream = EmbeddedResource.ReadStream("sample_image.jpg")!;
|
||
using var binaryReader = new BinaryReader(stream);
|
||
var bytes = binaryReader.ReadBytes((int)stream.Length);
|
||
|
||
chatHistory.AddUserMessage(
|
||
[
|
||
new TextContent("What’s in this image?"),
|
||
// Google AI Gemini API requires the image to be in base64 format, doesn't support URI
|
||
// You have to always provide the mimeType for the image
|
||
new ImageContent(bytes, "image/jpeg"),
|
||
]);
|
||
|
||
var reply = await chatCompletionService.GetChatMessageContentAsync(chatHistory);
|
||
|
||
Console.WriteLine(reply.Content);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task VertexAIChatCompletionWithVision()
|
||
{
|
||
Console.WriteLine("============= Vertex AI - Gemini Chat Completion with vision =============");
|
||
|
||
Assert.NotNull(TestConfiguration.VertexAI.BearerKey);
|
||
Assert.NotNull(TestConfiguration.VertexAI.Location);
|
||
Assert.NotNull(TestConfiguration.VertexAI.ProjectId);
|
||
Assert.NotNull(TestConfiguration.VertexAI.Gemini.ModelId);
|
||
|
||
Kernel kernel = Kernel.CreateBuilder()
|
||
.AddVertexAIGeminiChatCompletion(
|
||
modelId: TestConfiguration.VertexAI.Gemini.ModelId,
|
||
bearerKey: TestConfiguration.VertexAI.BearerKey,
|
||
location: TestConfiguration.VertexAI.Location,
|
||
projectId: TestConfiguration.VertexAI.ProjectId)
|
||
.Build();
|
||
|
||
// To generate bearer key, you need installed google sdk or use google web console with command:
|
||
//
|
||
// gcloud auth print-access-token
|
||
//
|
||
// Above code pass bearer key as string, it is not recommended way in production code,
|
||
// especially if IChatCompletionService will be long lived, tokens generated by google sdk lives for 1 hour.
|
||
// You should use bearer key provider, which will be used to generate token on demand:
|
||
//
|
||
// Example:
|
||
//
|
||
// Kernel kernel = Kernel.CreateBuilder()
|
||
// .AddVertexAIGeminiChatCompletion(
|
||
// modelId: TestConfiguration.VertexAI.Gemini.ModelId,
|
||
// bearerKeyProvider: () =>
|
||
// {
|
||
// // This is just example, in production we recommend using Google SDK to generate your BearerKey token.
|
||
// // This delegate will be called on every request,
|
||
// // when providing the token consider using caching strategy and refresh token logic when it is expired or close to expiration.
|
||
// return GetBearerKey();
|
||
// },
|
||
// location: TestConfiguration.VertexAI.Location,
|
||
// projectId: TestConfiguration.VertexAI.ProjectId);
|
||
|
||
var chatHistory = new ChatHistory("Your job is describing images.");
|
||
var chatCompletionService = kernel.GetRequiredService<IChatCompletionService>();
|
||
|
||
// Load the image from the resources
|
||
await using var stream = EmbeddedResource.ReadStream("sample_image.jpg")!;
|
||
using var binaryReader = new BinaryReader(stream);
|
||
var bytes = binaryReader.ReadBytes((int)stream.Length);
|
||
|
||
chatHistory.AddUserMessage(
|
||
[
|
||
new TextContent("What’s in this image?"),
|
||
// Vertex AI Gemini API supports both base64 and URI format
|
||
// You have to always provide the mimeType for the image
|
||
new ImageContent(bytes, "image/jpeg"),
|
||
// The Cloud Storage URI of the image to include in the prompt.
|
||
// The bucket that stores the file must be in the same Google Cloud project that's sending the request.
|
||
// new ImageContent(new Uri("gs://generativeai-downloads/images/scones.jpg"),
|
||
// metadata: new Dictionary<string, object?> { { "mimeType", "image/jpeg" } })
|
||
]);
|
||
|
||
var reply = await chatCompletionService.GetChatMessageContentAsync(chatHistory);
|
||
|
||
Console.WriteLine(reply.Content);
|
||
}
|
||
}
|