Download the PHP package benbjurstrom/sqlite-vec-scout without Composer

sqlite-vec driver for Laravel Scout

Use the sqlite-vec extension with Laravel Scout for vector similarity search.

🚀 Quick Start

1. Install the package using composer:

2. Publish the scout config and the package config:

This is the contents of the published sqlite-vec-scout.php config file. By default it contains 3 different indexes, one for OpenAI, one for Google Gemini, and one for testing. The rest of this guide will use the OpenAI index as an example.

3. Set the scout driver to sqlite-vec in your .env file and add your OpenAI API key:

4. Run the scout index command to create a migration file for your embeddings:

5. Update the model you wish to make searchable:

Add the HasEmbeddings and Searchable traits to your model. Additionally add a searchableAs() method that returns the name of your index. Finally implement toSearchableArray() with the content from the model you want converted into an embedding.

🔍 Usage

Create embeddings for your models:

Laravel Scout uses eloquent model observers to automatically keep your search index in sync anytime your Searchable models change.

This package uses this functionality automatically generate embeddings for your models when they are saved or updated; or remove them when your models are deleted.

If you want to manually generate embeddings for existing models you can use the artisan command below. See the Scout documentation for more information.

Search using vector similarity:

You can use the typical Scout syntax to search your models. For example:

Note that the text of your query will be converted into a vector embedding using the model index's configured handler. It's important that the same model is used for both indexing and searching.

Search using existing vectors:

You can also pass an existing embedding vector as a search parameter. This can be useful to find related models. For example:

Evaluate search results:

All search queries will be ordered by similarity to the given input and include the embedding relationship. The value of the nearest neighbor search can be accessed as follows:

The larger the distance the less similar the result is to the input.

🛠Using custom handlers

By default this package uses OpenAI to generate embeddings. To do this it uses the OpenAiHandler class paired with the openai index found in the packages config file.

You can generate embeddings from other providers by adding a custom Handler. A handler is a simple class defined in the HandlerContract that takes a string, a config object, and returns a BenBjurstrom\\SqliteVecScout\\Vector instance.

Whatever api calls or logic is needed to turn a string into a vector should be defined in the handle method of your custom handler.

If you need to pass api keys, embedding dimensions, or any other configuration to your handler you can define them in the config/sqlite-vec-scout.php file.

Installing sqlite-vec locally

The native sqlite-vec extension must be loaded on the same SQLite connection that Laravel uses. The service provider validates this at boot time and will throw a runtime exception if vec0 is unavailable.

sqlite-vec ships as a small SQLite extension that can be compiled from source or installed via language-specific packages. For PHP-specific guidance on compiling binaries with extension loading enabled — including a full static-php-cli build script — read Ben Bjurstrom's guide: https://benbjurstrom.com/sqlite-vec-php.

To see if your current PHP binary can load extensions dynamically run:

When the command prints bool(true), download a vec0 build, expose its full path via SQLITE_VEC_EXTENSION_PATH (or the sqlite-vec-scout.extension_path config key), and the service provider will call PDO::loadExtension() before validating the module. If the command returns bool(false) you must compile sqlite-vec directly into PHP — the blog post above demonstrates how to do this with static-php-cli and ensures the SQLITE_ENABLE_LOAD_EXTENSION flag is set for both sqlite3 and pdo_sqlite.

👏 Credits

• Ben Bjurstrom
• All Contributors

📝 License

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