Ragged is actively under development. It is working and can be used, but we do not yet consider it production ready because its API is still rapidly changing. We expect Ragged to be production ready by some time in July 2024.
Introduction
ragged
simplifies the usage of Large Language Models (LLMs). It offers an easy-to-use interface that supports both promise-based and event-driven inference.
Why ragged?
LLMs currently offer non-standard APIs. ragged
simplifies APIs for the frontend and backend by exposing a common interface that will eventually work across all LLMs.
Roadmap
Currently in development, ragged
is designed to provide a unified facade for interacting with various LLM APIs, including OpenAI, Cohere, and Anthropic, supporting diverse interaction patterns like text-to-text, speech-to-text, text-to-speech, text-to-image, and image-to-text.