Google_GenerativeAI 0.1.13

Google GenerativeAI (Gemini)

• Google GenerativeAI (Gemini)
  • Usage
  • Quick Start
  • Chat Mode
  • Vision
  • Function Calling
  • Credits

Unofficial C# SDK based on Google GenerativeAI (Gemini Pro) REST APIs.

This package includes C# Source Generator which allows you to define functions natively through a C# interface, and also provides extensions that make it easier to call this interface later.
In addition to easy function implementation and readability, it generates Args classes, extension methods to easily pass a functions to API, and extension methods to simply call a function via json and return json.
Currently only System.Text.Json is supported.

Usage

Quick Start

1. Obtain an API key to use with the Google AI SDKs.

2. Install Google_GenerativeAI Nuget Package

Install-Package Google_GenerativeAI

or

dotnet add package Google_GenerativeAI

Write some codes:

 var apiKey = 'Your API Key';

 var model = new GenerativeModel(apiKey);
 //or var model = new GeminiProModel(apiKey)

 var res = await model.GenerateContentAsync("How are you doing?");

Chat Mode

 var apiKey = Environment.GetEnvironmentVariable("Gemini_API_Key", EnvironmentVariableTarget.User);

 var model = new GenerativeModel(apiKey);
 //or var model = new GeminiProModel(apiKey)

 var chat = model.StartChat(new StartChatParams());

 var result = await chat.SendMessageAsync("Write a poem");
 Console.WriteLine("Initial Poem\r\n");
 Console.WriteLine(result);

 var result2 = await chat.SendMessageAsync("Make it longer");
 Console.WriteLine("Long Poem\r\n");
 Console.WriteLine(result2);
 

Vision

var imageBytes = await File.ReadAllBytesAsync("image.png");

var imagePart = new Part()
{
    InlineData = new GenerativeContentBlob()
    {
        MimeType = "image/png",
        Data = Convert.ToBase64String(imageBytes)
    }
};

var textPart = new Part()
{
    Text = "What is in the image?"
};

var parts = new[] { textPart, imagePart };

var apiKey = Environment.GetEnvironmentVariable("Gemini_API_Key", EnvironmentVariableTarget.User);
var visionModel = new GeminiProVision(apiKey);
var result = await visionModel.GenerateContentAsync(parts);

Console.WriteLine(result.Text());

Function Calling

using GenerativeAI;

public enum Unit
{
    Celsius,
    Fahrenheit,
    Imperial
}

public class Weather
{
    public string Location { get; set; } = string.Empty;
    public double Temperature { get; set; }
    public Unit Unit { get; set; }
    public string Description { get; set; } = string.Empty;
}

[GenerativeAIFunctions]
public interface IWeatherFunctions
{
    [Description("Get the current weather in a given location")]
    public Task<Weather> GetCurrentWeatherAsync(
        [Description("The city and state, e.g. San Francisco, CA")] string location,
        Unit unit = Unit.Celsius,
        CancellationToken cancellationToken = default);
}

public class WeatherService : IWeatherFunctions
{
    public Task<Weather> GetCurrentWeatherAsync(string location, Unit unit = Unit.Celsius, CancellationToken cancellationToken = default)
    {
        return Task.FromResult(new Weather
        {
            Location = location,
            Temperature = 22.0,
            Unit = unit,
            Description = "Sunny",
        });
    }
}

 WeatherService service = new WeatherService();
 
 var apiKey = Environment.GetEnvironmentVariable("Gemini_API_Key", EnvironmentVariableTarget.User);

 var model = new GenerativeModel(apiKey);

 // Add Global Functions
 model.AddGlobalFunctions(service.AsGoogleFunctions(), service.AsGoogleCalls())

 var result = await model.GenerateContentAsync("How is the weather in San Francisco today?");
 
 Console.WriteLine(result);

Credits

Thanks to HavenDV for OpenAI SDK