https://github.com/sylphai-inc/adalflow

AdalFlow: The library to build & auto-optimize LLM applications.
https://github.com/sylphai-inc/adalflow

agent ai auto-prompting bm25 chatbot faiss framework generative-ai information-retrieval llm machine-learning nlp optimizer python question-answering rag reranker retriever summarization trainer

Last synced: 19 days ago
JSON representation

AdalFlow: The library to build & auto-optimize LLM applications.

• Host: GitHub
• URL: https://github.com/sylphai-inc/adalflow
• Owner: SylphAI-Inc
• License: mit
• Created: 2024-04-19T05:05:13.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-03-26T15:22:05.000Z (about 2 months ago)
• Last Synced: 2025-04-09T22:05:37.851Z (about 1 month ago)
• Topics: agent, ai, auto-prompting, bm25, chatbot, faiss, framework, generative-ai, information-retrieval, llm, machine-learning, nlp, optimizer, python, question-answering, rag, reranker, retriever, summarization, trainer
• Language: Python
• Homepage: http://adalflow.sylph.ai/
• Size: 101 MB
• Stars: 2,915
• Watchers: 22
• Forks: 256
• Open Issues: 34
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        




    





    


     ⚡ Say Goodbye to Manual Prompting and Vendor Lock-In ⚡

    




    

        

    





    


        View Documentation

        

    




    

        

    

    

        

    

    

        

    

    

        

    

    

        

    

    

        

    

      

        

    







AdalFlow is a PyTorch-like library to build and auto-optimize any LM workflows, from Chatbots, RAG,  to Agents.



# 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.



  





  



View [Documentation](https://adalflow.sylph.ai)

# Quick Start

Install AdalFlow with pip:

```bash

pip install adalflow

```

View [Quickstart](https://colab.research.google.com/drive/1_YnD4HshzPRARvishoU4IA-qQuX9jHrT?usp=sharing): Learn AdalFlow end-to-end experience in 15 mins.

# Research

[Jan 2025] [Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting](https://arxiv.org/abs/2501.16673)

- 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](https://vita-group.github.io/), under the leadership of [Dr. Atlas Wang](https://www.ece.utexas.edu/people/faculty/atlas-wang), alongside [Dr. Junyuan Hong](https://jyhong.gitlab.io/), who provides valuable support in driving project initiatives.

For collaboration, contact [Li Yin](https://www.linkedin.com/in/li-yin-ai/).

# Documentation

AdalFlow full documentation available at [adalflow.sylph.ai](https://adalflow.sylph.ai/):

# AdalFlow: A Tribute to Ada Lovelace

AdalFlow is named in honor of [Ada Lovelace](https://en.wikipedia.org/wiki/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](https://discord.gg/ezzszrRZvT) community to ask questions, share your projects, and get updates on AdalFlow.

To contribute, please read our [Contributor Guide](https://adalflow.sylph.ai/contributor/index.html).

# Contributors

[![contributors](https://contrib.rocks/image?repo=SylphAI-Inc/AdalFlow&max=2000)](https://github.com/SylphAI-Inc/AdalFlow/graphs/contributors)

# Acknowledgements

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

- 📚 [PyTorch](https://github.com/pytorch/pytorch/) for design philosophy and design pattern of ``Component``, ``Parameter``, ``Sequential``.

- 📚 [Micrograd](https://github.com/karpathy/micrograd): A tiny autograd engine for our auto-differentiative architecture.

- 📚 [Text-Grad](https://github.com/zou-group/textgrad) for the ``Textual Gradient Descent`` text optimizer.

- 📚 [DSPy](https://github.com/stanfordnlp/dspy) for inspiring the ``__{input/output}__fields`` in our ``DataClass`` and the bootstrap few-shot optimizer.

- 📚 [OPRO](https://github.com/google-deepmind/opro) for adding past text instructions along with its accuracy in the text optimizer.

- 📚 [PyTorch Lightning](https://github.com/Lightning-AI/pytorch-lightning) for the ``AdalComponent`` and ``Trainer``.