Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/sylphai-inc/adalflow
AdalFlow: The library to build & auto-optimize any LLM tasks.
https://github.com/sylphai-inc/adalflow
agent ai bm25 chatbot faiss framework generative-ai information-retrieval llm machine-learning nlp optimizer python question-answering rag reranker retriever summarization trainer
Last synced: 3 days ago
JSON representation
AdalFlow: The library to build & auto-optimize any LLM tasks.
- Host: GitHub
- URL: https://github.com/sylphai-inc/adalflow
- Owner: SylphAI-Inc
- License: mit
- Created: 2024-04-19T05:05:13.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-09-24T18:41:06.000Z (9 days ago)
- Last Synced: 2024-10-01T00:41:56.349Z (3 days ago)
- Topics: agent, ai, 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: 79 MB
- Stars: 1,398
- Watchers: 16
- Forks: 125
- Open Issues: 26
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
⚡ 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.
# Why AdalFlow
1. Embracing a design pattern similar to PyTorch, AdalFlow is powerful, light, modular, and robust.
AdalFlow provides `Model-agnostic` building blocks to build LLM task pipelines, ranging from RAG, Agents to classical NLP tasks like text classification and named entity recognition. It is easy to get high performance only using manual prompting.
2. AdalFlow provides a unified auto-differentiative framework for both zero-shot prompt optimization and few-shot optimization. It advances existing auto-optimization research, including ``Text-Grad`` and ``DsPy``.
Through our research, ``Text-Grad 2.0`` and ``Learn-to-Reason Few-shot In Context Learning``, AdalFlow ``Trainer`` achieves the highest accuracy while being the most token-efficient.
Here is an optimization demonstration on a text classification task:
Among all libraries, AdalFlow achieved the highest accuracy with manual prompting (starting at 82%) and the highest accuracy after optimization.
Further reading: [Optimize Classification](https://adalflow.sylph.ai/use_cases/classification.html)
## 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.
Further reading: [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop), [Design Philosophy](https://adalflow.sylph.ai/tutorials/lightrag_design_philosophy.html) and [Class hierarchy](https://adalflow.sylph.ai/tutorials/class_hierarchy.html).
## Unified Framework for Auto-Optimization
AdalFlow provides token-efficient and high-performing prompt optimization within a unified framework.
To optimize your pipeline, simply define a ``Parameter`` and pass it to AdalFlow's ``Generator``.
Whether you need to optimize task instructions or run some few-shot demonstrations,
AdalFlow's unified framework offers an easy way to **diagnose**, **visualize**, **debug**, and **train** your pipeline.
This [Dynamic Computation Graph](https://adalflow.sylph.ai/tutorials/trace_graph.html) demonstrates how our auto-differentiation and the dynamic computation graph work.
No need to manually defined nodes and edges, AdalFlow will automatically trace the computation graph for you.
### **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.
# Quick Install
Install AdalFlow with pip:
```bash
pip install adalflow
```
Please refer to the [full installation guide](https://adalflow.sylph.ai/get_started/installation.html) for more details.
# Documentation
AdalFlow full documentation available at [adalflow.sylph.ai](https://adalflow.sylph.ai/):
- [How We Started](https://www.linkedin.com/posts/li-yin-ai_both-ai-research-and-engineering-use-pytorch-activity-7189366364694892544-Uk1U?utm_source=share&utm_medium=member_desktop)
- [Introduction](https://adalflow.sylph.ai/)
- [Full installation guide](https://adalflow.sylph.ai/get_started/installation.html)
- [Design philosophy](https://adalflow.sylph.ai/tutorials/lightrag_design_philosophy.html)
- [Class hierarchy](https://adalflow.sylph.ai/tutorials/class_hierarchy.html)
- [Tutorials](https://adalflow.sylph.ai/tutorials/index.html)
- [Supported Models](https://adalflow.sylph.ai/apis/components/components.model_client.html)
- [Supported Retrievers](https://adalflow.sylph.ai/apis/components/components.retriever.html)
- [API reference](https://adalflow.sylph.ai/apis/index.html)
# 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 do more than just perform calculations. As a female-led team, we aim to inspire more women to enter the AI field.
# Contributors
[](https://github.com/SylphAI-Inc/LightRAG/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``.
# Citation
```bibtex
@software{Yin2024AdalFlow,
author = {Li Yin},
title = {{AdalFlow: The Library for Large Language Model (LLM) Applications}},
month = {7},
year = {2024},
doi = {10.5281/zenodo.12639531},
url = {https://github.com/SylphAI-Inc/AdalFlow}
}
```