Axflow is a modular TypeScript framework for robust AI apps. Includes models SDK, axgen for connecting data to LLMs, axeval for output quality, and more. Empowers code-first flexibility & control.
Axflow is a modular TypeScript framework for building robust AI apps. Includes React hooks and utilities for streaming, modules to connect data to LLMs, evaluate outputs, serve models, and more.
Axflow is an open-source TypeScript framework for building robust natural language AI applications. It provides developers with a modular, code-first approach to seamlessly leverage large language models (LLMs).
- @axflow/models🤖 - An SDK with React hooks and utilities to integrate LLMs into apps and enable streaming responses. It makes building AI frontends intuitive.
- axgen⚙️ - Connect your data sources and documents to LLMs to generate outputs like summaries, answers, translations, etc.
- axeval📈 - Evaluate the quality of LLM outputs using customizable metrics for your use case.
- extract📥 - Load, transform, and chunk documents from any source to prepare data for LLMs efficiently.
- serve🚀 - Serve any LLM with options like throttling, analytics, and logging.
- finetune🔧 - Fine-tune LLMs on your own datasets.
Axflow emphasizes flexibility and control for developers through its modular, code-first approach. It deconstructs complex LLM workflows into intuitive building blocks you can adopt incrementally.
Whether you want to build custom NLP-powered apps 📱 or scale existing ones to the next level, Axflow provides the components to make it happen faster with TypeScript.
- 🧩 Modularity - Axflow is intentionally designed as modular components that can be adopted incrementally. This means you only take the parts you need, avoiding bundle bloat. It also enables easily swapping components, like models or data connectors, with no code change.
- ⚡️ Speed - Between modular and reusable components like prompts and data helpers and integrated eval for rapid iteration, Axflow accelerates building production-grade LLM apps 3-5x faster than coding from scratch.
- 🔌 Flexibility - Axflow uses interface-driven development to change underlying implementations without breaking contracts. This means you can connect new data sources, swap model backends, or exchange deploy environments with no code change.
- 👥 Community - Axflow is open source with a public roadmap so you can collaborate alongside top engineers and researchers to push boundaries in industrialized AI.
- 🛡️Reliability - Modules like axeval enforce test-driven development for model quality, while integration foundations promote stability for enterprise reliability and governance.
In summary, Axflow unlocks order-of-magnitude leverage for AI engineers through modular, scalable building blocks.
- 👷🏽♀️ Builders: Nicholas Charriere, Ben Reinhart
- 👩🏽💻 Contributors: 3
- 💫 GitHub Stars: 993
- 🍴 Forks: 40
- 👁️ Watch: 10
- 🪪 License: MIT
🧙🏽 Follow The AI Engineer for daily insights tailored to AI engineers and subscribe to our newsletter. We are the AI community for hackers!