Skip to content

Latest commit

 

History

History
117 lines (87 loc) · 3.64 KB

README.md

File metadata and controls

117 lines (87 loc) · 3.64 KB

Create embeddings for your Eloquent models to use with OpenAI

Latest Version on Packagist GitHub Tests Action Status GitHub Code Style Action Status Total Downloads

OpenAI's text embeddings measure the relatedness of text strings. Using this package you can save embeddings automatically for your Eloquent model in a PostgreSQL vector database. To use the embeddings in your AI requests to the OpenAI API endpoints.

Installation

You can install the package via composer:

composer require vormkracht10/laravel-embeddings

You can publish and run the migrations with:

php artisan vendor:publish --tag="laravel-embeddings-migrations"
php artisan migrate

You can publish the config file with:

php artisan vendor:publish --tag="laravel-embeddings-config"

This is the contents of the published config file:

return [
    'enabled' => env('EMBEDDINGS_ENABLED', true),
    'driver' => env('EMBEDDINGS_DRIVER', 'null'), // 'null' / 'openai'
    'queue' => true,
    'database' => [
        'connection' => env('EMBEDDINGS_DATABASE_CONNECTION', 'pgsql'),
        'table' => env('EMBEDDINGS_DB_TABLE', 'embeddings'),
    ],
    'openai' => [
        'key' => env('OPENAI_API_KEY'),
        'model' => env('OPENAI_EMBEDDING_MODEL', 'text-embedding-ada-002')
    ],

    /*
    |--------------------------------------------------------------------------
    | Chunk Sizes
    |--------------------------------------------------------------------------
    |
    | These options allow you to control the maximum chunk size when you are
    | mass importing data into the embed engine. This allows you to fine
    | tune each of these chunk sizes based on the power of the servers.
    |
    */
    'chunk' => [
        'embeddable' => 500,
        'unembeddable' => 500,
    ],
];

Fill in the following env variables

EMBEDDINGS_DRIVER=openai
OPENAI_API_KEY=

Usage

// Add the Embeddable trait to your Model(s).
class MyModel {
    use Embeddable {
        \Laravel\Scout\Searchable::usesSoftDelete insteadof \Vormkracht10\Embedding\Embeddable;
    }
}

// You can override the embeddable content
class MyModel {
    // ...
    public function toEmbeddableString()
    {
        return strip_tags(implode(', ', $this->toArray()));
    }
}

Testing

composer test

Changelog

Please see CHANGELOG for more information on what has changed recently.

Contributing

Please see CONTRIBUTING for details.

Security Vulnerabilities

Please review our security policy on how to report security vulnerabilities.

Credits

License

The MIT License (MIT). Please see License File for more information.