Contributor Guide#
Welcome to the AdalFlow community! We’re building the most user-friendly, modular, and powerful library for building and auto-optimizing LLM applications, from Chatbots and RAGs to Agents. Think of AdalFlow for LLM applications and prompt engineering as the PyTorch/TensorFlow/JAX equivalent for AI modeling.
The goal of the library is to provide basic and fundamental building blocks to create advanced applications with auto-optimization out of the box. As we mature, we anticipate that more RAG, memory-based chatbots, or agent frameworks will be built on top of AdalFlow’s building blocks, such as retriever and generator. We highly suggest you read our design principle before you start contributing.
We greatly appreciate all contributions, from bug fixes to new features, and value every contributor. However, we must be selective to ensure our library remains reliable for users. We hope your contributions go beyond listing your name on the repo—our goal is for you to learn, grow your skills, support your favorite projects, and give back to the community!
The goal of this guide is to design the best process for maintaining the quality of our library while enabling the community to make meaningful contributions. It took us three months to set up this contributor guide, as we first tested the process with early contributors. We are determined to make AdalFlow as great and legendary as PyTorch.
This guide covers the overall contributing process, along with development essentials for environment setup, coding, testing, and documentation.
Here’s to the future of LLM applications!
By Li Yin.
Contributor Guide