// 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);
    }
}