Weave Code
Ai Docker Model Runner Platform Laravel Package
symfony/ai-docker-model-runner-platform
Docker Model Runner platform bridge for Symfony AI, connecting your applications to locally running Docker-hosted AI models through the Docker Model Runner API.
Docker Model Runner Platform is a Symfony AI bridge that connects your application to Docker Model Runner, enabling local AI model inference managed entirely through Docker—no external API provider required.
- Seamless PlatformInterface integration for Symfony AI agents and chat features
- Run and query models locally via the Docker Model Runner API
- Configurable base URL and model selection
- Keeps inference on your own infrastructure for privacy and cost control
Ideal for development and self-hosted setups where you want a consistent Symfony AI experience backed by Docker-managed models.
Frequently asked questions about Ai Docker Model Runner Platform
- What is symfony/ai-docker-model-runner-platform used for?
- It is a Symfony AI platform bridge that connects to Docker Model Runner and lets PHP applications call locally hosted models through Docker's OpenAI-compatible API. It fits into the Symfony AI provider abstraction so you can route chat or embedding requests to Docker-managed models. In a Laravel app it is typically bound into the service container rather than used as a full Laravel-native AI SDK.
- Can I use this package in a Laravel application?
- Yes, but it is a Symfony AI package, not a Laravel-specific wrapper. You can install it with Composer and bind the Symfony AI ModelClient or provider services into Laravel's container. Expect to write a small service provider or adapter to expose configuration, streaming, and error handling in Laravel style.
- How do I install symfony/ai-docker-model-runner-platform?
- Install it with Composer alongside the required Symfony AI components, for example composer require symfony/ai-docker-model-runner-platform. Check the main Symfony AI monorepo for the exact platform and HTTP client dependencies. In Laravel, commit the composer.json and composer.lock changes and register any needed bindings in a service provider.
- What PHP and Laravel versions are required?
- The bridge follows Symfony AI and Symfony 7.x constraints, which generally require PHP 8.2 or newer. It can be used in Laravel applications that meet those PHP and Symfony component constraints. Check the package composer.json for the current minimum versions before upgrading older Laravel projects.
- How do I configure Docker Model Runner endpoints in Laravel?
- Configure Docker Model Runner and its API endpoint outside Laravel, then provide the base URL or client configuration expected by the Symfony AI platform. Store environment-specific values in Laravel's .env and map them into your service provider bindings. Avoid hard-coding Docker hosts or model names so local Sail, CI, and production environments can differ.
- Does the package support streaming responses?
- The Symfony AI platform supports streaming through DeltaInterface, and this Docker Model Runner bridge can expose streamed model output. In Laravel you can wrap that in a StreamedResponse or forward chunks to a WebSocket or Echo channel. Validate how your chosen Docker model and OpenAI-compatible endpoint handle streaming before relying on it in production.
- How are token usage and cost tracking handled?
- Recent Symfony AI TokenUsage objects include the originating model along with prompt and completion token counts. The package does not provide a native price book, so Laravel applications must own a model-to-price table and the cost arithmetic. A common pattern is a listener that persists model, tokens, user, and route data to an Eloquent table.
- How do I test Laravel code that uses this bridge?
- Depend on an interface such as a ModelClient contract rather than the concrete Docker Model Runner client, then bind a fake or mock in Laravel's test container. This lets you assert requests, streamed chunks, and token usage without running Docker Model Runner. Add a small integration test against Docker Model Runner for configuration and API compatibility checks.
- Is it suitable for production Laravel applications?
- It can be suitable for teams already running Docker Model Runner or Laravel Sail and wanting local or on-premise model calls without Kubernetes. Production readiness depends on your Docker Model Runner deployment, model performance, error handling, and observability. Because the package is part of Symfony AI, track its release notes and version constraints closely.
- How does it compare to Ollama or native Laravel AI packages?
- This bridge specifically targets Docker Model Runner and Docker's OpenAI-compatible API, while Ollama bridges target Ollama's runtime and native Laravel AI packages may offer tighter Blade or Eloquent integration. Choose this package when Docker Model Runner is already your model runtime or when you want Symfony AI's provider abstraction. If you need Laravel-first facades and helpers, compare maintenance and feature coverage before adopting it.
Weaver
How can I help you explore Laravel packages today?