gemini-api-php/laravel

Gemini API client for Laravel

v0.3.0 2023-12-27 03:38 UTC

Requires

• php: ^8.1
• gemini-api-php/client: ^1.3.1
• illuminate/support: ^9.0 || ^10.0 || ^11.0
• psr/container: ^1.0 || ^2.0
• psr/http-client: ^1.0

Requires (Dev)

• guzzlehttp/guzzle: ^7.8.1
• guzzlehttp/psr7: ^2.0
• laravel/framework: ^9.0 || ^10.0 || ^11.0
• laravel/pint: ^1.13.6
• pestphp/pest: ^2.27.0
• pestphp/pest-plugin-arch: ^2.4.1
• phpstan/phpstan: ^1.10.47
• symfony/var-dumper: ^6.4.0|^7.0.1

MIT

• Erdem Köse

• php
• api
• client
• google
• sdk
• laravel
• ai
• Gemini
• gemini pro
• gemini pro vision

README

Gemini API Client for Laravel

Gemini API Client for Laravel allows you to use the Google's generative AI models, like Gemini Pro and Gemini Pro Vision in your Laravel application.

Supports PHP 8.1 and Laravel v9, v10.

This library is not developed or endorsed by Google.

• Erdem Köse - github.com/erdemkose

Table of Contents

• Installation
• Configuration
• How to use
  • Text Generation
  • Text Generation using Image File
  • Text Generation using Image Data
  • Chat Session (Multi-Turn Conversations)
  • Chat Session with History
  • Text Embeddings
  • Tokens counting
  • Listing models
  • Accessing the underlying Gemini API client
• Credits

Installation

You need an API key to gain access to Google's Gemini API. Visit Google AI Studio to get an API key.

First step is to install the Gemini API Client for Laravel with Composer.

composer require gemini-api-php/laravel

Configuration

There are two ways to configure the client.

Environment variables

You can set the GEMINI_API_KEY environment variable with the API key you obtained from Google AI studio.

Add the following line into your .env file.

GEMINI_API_KEY='YOUR_GEMINI_API_KEY'

Configuration file

You can also run the following command to create a configuration file in your applications config folder.

php artisan vendor:publish --provider=GeminiAPI\Laravel\ServiceProvider

Now you can edit the config/gemini.php file to configure the Gemini API client.

How to use

Text Generation

use GeminiAPI\Laravel\Facades\Gemini;

print Gemini::generateText('PHP in less than 100 chars');
// PHP: A server-side scripting language used to create dynamic web applications.
// Easy to learn, widely used, and open-source.

Text Generation Using Image File

use GeminiAPI\Laravel\Facades\Gemini;

print Gemini::generateTextUsingImageFile(
    'image/jpeg',
    'elephpant.jpg',
    'Explain what is in the image',
);
// The image shows an elephant standing on the Earth.
// The elephant is made of metal and has a glowing symbol on its forehead.
// The Earth is surrounded by a network of glowing lines.
// The image is set against a starry background.

Text Generation Using Image Data

use GeminiAPI\Laravel\Facades\Gemini;

print Gemini::generateTextUsingImage(
    'image/jpeg',
    base64_encode(file_get_contents('elephpant.jpg')),
    'Explain what is in the image',
);
// The image shows an elephant standing on the Earth.
// The elephant is made of metal and has a glowing symbol on its forehead.
// The Earth is surrounded by a network of glowing lines.
// The image is set against a starry background.

Chat Session (Multi-Turn Conversations)

use GeminiAPI\Laravel\Facades\Gemini;

$chat = Gemini::startChat();

print $chat->sendMessage('Hello World in PHP');
// echo "Hello World!";
// This code will print "Hello World!" to the standard output.

print $chat->sendMessage('in Go');
// fmt.Println("Hello World!")
// This code will print "Hello World!" to the standard output.

Chat Session with History

use GeminiAPI\Laravel\Facades\Gemini;

$history = [
    [
        'message' => 'Hello World in PHP',
        'role' => 'user',
    ],
    [
        'message' => <<<MESSAGE
            echo "Hello World!";

            This code will print "Hello World!" to the standard output.
            MESSAGE,
        'role' => 'model',
    ],
];
$chat = Gemini::startChat($history);

print $chat->sendMessage('in Go');
// fmt.Println("Hello World!")
// This code will print "Hello World!" to the standard output.

Text Embeddings

use GeminiAPI\Laravel\Facades\Gemini;

print_r(Gemini::embedText('PHP in less than 100 chars'));
// [
//    [0] => 0.041395925
//    [1] => -0.017692696
//    ...
// ]

Tokens counting

use GeminiAPI\Laravel\Facades\Gemini;

print Gemini::countTokens('PHP in less than 100 chars');
// 10

Listing models

use GeminiAPI\Laravel\Facades\Gemini;

print_r(Gemini::listModels());
//[
//  [0] => GeminiAPI\Resources\Model Object
//    (
//      [name] => models/gemini-pro
//      [displayName] => Gemini Pro
//      [description] => The best model for scaling across a wide range of tasks
//      ...
//    )
//  [1] => GeminiAPI\Resources\Model Object
//    (
//      [name] => models/gemini-pro-vision
//      [displayName] => Gemini Pro Vision
//      [description] => The best image understanding model to handle a broad range of applications
//      ...
//    )
//]

Accessing the underlying Gemini API client

use GeminiAPI\Laravel\Facades\Gemini;

$client = Gemini::client();

Credits

This project was inspired by the great work of OpenAI PHP for Laravel and OpenAI PHP client.

We gratefully acknowledge the contributions of OpenAI PHP and its team.