Lanarky is a Python web framework designed for building LLM-powered microservices, targeting developers who need to integrate large language models into their applications. It offers an LLM-first, unopinionated approach with built-in streaming support, aiming to simplify the creation of real-time LLM applications without vendor lock-in.

How It Works

Built on FastAPI, Lanarky leverages its speed and modern features. Its core advantage lies in its specialized abstractions for LLM interactions, providing adapters for services like OpenAI's ChatCompletion. This design allows developers to define LLM microservices with minimal code, abstracting away much of the boilerplate associated with API calls and streaming responses over HTTP and WebSockets.

Quick Start & Requirements

• Primary install: pip install lanarky
• Prerequisites: Python 3.9+
• Documentation: lanarky.ajndkr.com

Highlighted Details

• Built on FastAPI for performance and features.
• Supports streaming responses over HTTP and WebSockets.
• Unopinionated design, avoiding vendor lock-in.
• Provides adapters for common LLM providers like OpenAI.

Maintenance & Community

The project is currently in maintenance mode, with no new features planned. Critical bugs and security issues may be addressed, but active development has ceased. The author encourages community contributions.

Licensing & Compatibility

• License: MIT
• Compatibility: Permissive for commercial use and integration with closed-source applications.

Limitations & Caveats

The project is in maintenance mode, meaning active development has stopped, and new features will not be added. While critical bugs may be addressed, users should not expect ongoing feature enhancements or active maintenance.