x-laravel/embedding — MongoDB Driver

⚠️ This package has been cancelled and is not functional. See CLAUDE.md for details.

MongoDB vector driver for x-laravel/embedding.

How It Works

• Provides MongodbEmbedding — a MongoDB-native Eloquent model that stores vectors as BSON arrays, reads the collection name from embedding.database.table config
• Implements SimilarityDriver — registers as the mongodb driver for MongoDB Atlas Vector Search using $vectorSearch aggregation
• Community MongoDB (without Atlas): vectors are stored natively as BSON arrays; similarity search falls back to PhpDriver automatically

Requirements

• PHP ^8.3 + ext-mongodb
• Laravel ^12.0 | ^13.0
• x-laravel/embedding ^1.0
• mongodb/laravel-mongodb ^4.0
• MongoDB 8.0+ (community) or MongoDB Atlas (for native vector search)

Installation

composer require x-laravel/embedding-mongodb-driver

The MongodbEmbeddingServiceProvider is auto-discovered and registers the mongodb driver automatically.

Setup

1. Configure x-laravel/embedding

Publish the config if you haven't already:

php artisan vendor:publish --tag=embedding-config

Set the MongoDB connection and swap the Embedding model in config/embedding.php:

'database' => [
    'connection' => env('EMBEDDINGS_DATABASE_CONNECTION', 'mongodb'),
    'table'      => env('EMBEDDINGS_DB_TABLE', 'embeddings'),
],

// Swap the default SQL model with the MongoDB-native model
'model' => \XLaravel\Embedding\Driver\Mongodb\Models\MongodbEmbedding::class,

'similarity' => [
    'driver' => env('EMBEDDING_SIMILARITY_DRIVER', 'auto'),
],

2. Configure the MongoDB connection

In config/database.php:

'connections' => [
    'mongodb' => [
        'driver'   => 'mongodb',
        'host'     => env('DB_HOST', '127.0.0.1'),
        'port'     => env('DB_PORT', 27017),
        'database' => env('DB_DATABASE', 'myapp'),
        'username' => env('DB_USERNAME'),
        'password' => env('DB_PASSWORD'),
    ],
],

3. Create the embeddings collection

php artisan migrate

Or publish the migration first:

php artisan vendor:publish --tag=embedding-mongodb-migrations
php artisan migrate

This creates a unique index on (embeddable_type, embeddable_id, slot).

4. MongoDB Atlas Vector Search (optional)

For native DB-level similarity search, create a Vector Search index on the embeddings collection in Atlas with path vector and set the similarity driver:

'similarity' => ['driver' => 'mongodb'],

Note: Without Atlas, similarity search automatically uses PhpDriver (vectors loaded into PHP memory). For large datasets, Atlas Vector Search is strongly recommended.

5. Model

Follow the standard x-laravel/embedding setup. No MongoDB-specific changes are needed on your models.

use XLaravel\Embedding\Attributes\EmbedOn;
use XLaravel\Embedding\Concerns\Embeddable;
use XLaravel\Embedding\Contracts\HasEmbeddings;

#[EmbedOn(['title', 'body'])]
class Post extends Model implements HasEmbeddings
{
    use Embeddable;

    public function toEmbeddingText(): string
    {
        return $this->title.' '.$this->body;
    }
}

Usage

The driver is transparent — use the standard x-laravel/embedding API:

Post::similarToText('web framework', limit: 10);
Post::similarTo($vector, limit: 10, threshold: 0.8);
Post::rankByRelevance($posts, 'web framework');

$post->mostSimilar(limit: 5);
$post->similarityTo($otherPost);

All methods set a similarity_score float attribute on each returned model.

Testing

# Build first (once per PHP version)
DOCKER_BUILDKIT=0 docker compose --profile php83 build

# Run tests
docker compose --profile php83 up
docker compose --profile php84 up
docker compose --profile php85 up

License

This package is open-sourced software licensed under the MIT license.