jpcaparas/laravel-faker-openai

An opinionated Laravel package that modifies the service container Faker behaviour to allow prompts to be generated with OpenAI

0.1.0 2025-01-09 22:11 UTC

Requires

• php: ^8.2
• fakerphp/faker: ^1.24
• laravel/framework: ^10.0 || ^11.0
• nyholm/psr7: ^1.8
• openai-php/laravel: ^0.10.2
• symfony/http-client: ^7.2

Requires (Dev)

• laravel/pint: ^1.19
• orchestra/testbench: *

MIT

• JP Caparas

README

A Laravel package that extends FakerPHP by adding an AI-powered data generator using OpenAI. This allows you to generate more realistic and context-aware fake data in your Laravel applications.

Installation

Install the package via Composer:

composer require jpcaparas/laravel-faker-openai

The package will automatically register its service provider if you're using Laravel's package auto-discovery.

Configuration

1. Make sure you have your OpenAI API key set in your .env file:

OPENAI_API_KEY=your-api-key-here

1. The package uses gpt-3.5-turbo model by default.

Usage

The package adds a new promptAI() method to the Faker generator. You can use it in several ways:

Basic Usage

$faker = app(\Faker\Generator::class);

// Generate a fake name using AI
$name = $faker->promptAI('name');

// Generate a movie review
$review = $faker->promptAI('movieReview');

// Generate a movie description
$description = $faker->promptAI('movieDescription');

... you can also use the built-in fake() helper:

$name = fake('name');

With Fallback Values

You can provide fallback values that will be used if the AI request fails:

// String fallback
$name = $faker->promptAI('name', 'John Doe');

// Closure fallback
$name = $faker->promptAI('name', fn() => 'John Doe');

Error Handling

By default, errors are logged and the fallback value is returned. You can make it throw exceptions instead:

try {
    $name = $faker->promptAI('name', null, true); // Set throwOnError to true
} catch (\Exception $e) {
    // Handle the error
}

How It Works

The package works by:

1. Intercepting FakerPHP method calls through a prompt
2. Sending them to OpenAI's GPT model
3. Returning AI-generated responses that match FakerPHP's expected output format

Testing

Run the test suite:

composer test

License

MIT