⚡ The Library to Build and Auto-optimize LLM Applications ⚡

All Documentation | Models | Retrievers | Agents | LLM evaluation | Trainer & Optimizers

For AI researchers, product teams, and software engineers who want to learn the AI way.

Quick Start

Install AdalFlow with pip:

pip install adalflow

Please refer to the full installation guide for more details. Package changelog.

• Try the Building Quickstart in Colab to see how AdalFlow can build the task pipeline, including Chatbot, RAG, agent, and structured output.
• Try the Optimization Quickstart to see how AdalFlow can optimize the task pipeline.

Research

[Jan 2025] Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting

• LLM Applications as auto-differentiation graphs
• Token-efficient and better performance than DsPy

Collaborations

We work closely with the VITA Group at University of Texas at Austin, under the leadership of Dr. Atlas Wang, alongside Dr. Junyuan Hong, who provides valuable support in driving project initiatives.

For collaboration, contact Li Yin.

Why AdalFlow

1. Say goodbye to manual prompting: AdalFlow provides a unified auto-differentiative framework for both zero-shot optimization and few-shot prompt optimization. Our research, LLM-AutoDiff and Learn-to-Reason Few-shot In Context Learning, achieve the highest accuracy among all auto-prompt optimization libraries.
2. Switch your LLM app to any model via a config: AdalFlow provides Model-agnostic building blocks for LLM task pipelines, ranging from RAG, Agents to classical NLP tasks.

A trained DeepSeek R1 LLaMA70B(r1 distilled) is even better than GPT-o1 without training.

Further reading: Use Cases

Light, Modular, and Model-Agnostic Task Pipeline

LLMs are like water; AdalFlow help you quickly shape them into any applications, from GenAI applications such as chatbots, translation, summarization, code generation, RAG, and autonomous agents to classical NLP tasks like text classification and named entity recognition.

AdalFlow has two fundamental, but powerful, base classes: Component for the pipeline and DataClass for data interaction with LLMs. The result is a library with minimal abstraction, providing developers with maximum customizability.

You have full control over the prompt template, the model you use, and the output parsing for your task pipeline.

Many providers and models accessible via the same interface:

All available model providers

Further reading: How We Started, Design Philosophy and Class hierarchy.

Unified Framework for Auto-Optimization

To optimize your pipeline, simply define a Parameter and pass it to AdalFlow's Generator. You use PROMPT for prompt tuning via textual gradient descent and DEMO for few-shot demonstrations.

We let you diagnose, visualize, debug, and train your pipeline.

Trainable Task Pipeline

Just define it as a Parameter and pass it to AdalFlow's Generator.

AdalComponent & Trainer

AdalComponent acts as the 'interpreter' between task pipeline and the trainer, defining training and validation steps, optimizers, evaluators, loss functions, backward engine for textual gradients or tracing the demonstrations, the teacher generator.

Documentation

AdalFlow full documentation available at adalflow.sylph.ai:

• How We Started
• Introduction
• Full installation guide
• Design philosophy
• Class hierarchy
• Tutorials
• Supported Models
• Supported Retrievers
• API reference

AdalFlow: A Tribute to Ada Lovelace

AdalFlow is named in honor of Ada Lovelace, the pioneering female mathematician who first recognized that machines could go beyond mere calculations. As a team led by a female founder, we aim to inspire more women to pursue careers in AI.

Community & Contributors

The AdalFlow is a community-driven project, and we welcome everyone to join us in building the future of LLM applications.

Join our Discord community to ask questions, share your projects, and get updates on AdalFlow.

To contribute, please read our Contributor Guide.

Contributors

Acknowledgements

Many existing works greatly inspired AdalFlow library! Here is a non-exhaustive list:

• 📚 PyTorch for design philosophy and design pattern of Component, Parameter, Sequential.
• 📚 Micrograd: A tiny autograd engine for our auto-differentiative architecture.
• 📚 Text-Grad for the Textual Gradient Descent text optimizer.
• 📚 DSPy for inspiring the __{input/output}__fields in our DataClass and the bootstrap few-shot optimizer.
• 📚 OPRO for adding past text instructions along with its accuracy in the text optimizer.
• 📚 PyTorch Lightning for the AdalComponent and Trainer.