From fc4494a9c6032967f3e44b9ee68d83fd2b8ddbea Mon Sep 17 00:00:00 2001 From: Ryan Sweet Date: Tue, 17 Sep 2024 06:09:30 -0700 Subject: [PATCH] Readme updates for #520 and #525 (#527) * starting #520 - readme improvements * more for #520 * tiny announcement * cleanupheader * simplifying * move announcement to top * rearrange logo * we dont need the logo * bumping the date * added faq addressing #500 --- README.md | 293 ++++++++++++++---------------------------------------- 1 file changed, 72 insertions(+), 221 deletions(-) diff --git a/README.md b/README.md index 37ae4f0ecf83..3a96bd0ac765 100644 --- a/README.md +++ b/README.md @@ -1,150 +1,48 @@ -
- -AutoGen Logo - -![Python Version](https://img.shields.io/badge/3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11%20%7C%203.12-blue) [![PyPI version](https://img.shields.io/badge/PyPI-v0.2.34-blue.svg)](https://pypi.org/project/pyautogen/) -[![NuGet version](https://badge.fury.io/nu/AutoGen.Core.svg)](https://badge.fury.io/nu/AutoGen.Core) +
-[![Downloads](https://static.pepy.tech/badge/pyautogen/week)](https://pepy.tech/project/pyautogen) -[![Discord](https://img.shields.io/discord/1153072414184452236?logo=discord&style=flat)](https://aka.ms/autogen-dc) - -[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40pyautogen)](https://twitter.com/pyautogen) +[![PyPI version](https://img.shields.io/badge/PyPI-v0.2.34-blue.svg)](https://pypi.org/project/pyautogen/) +[![NuGet version](https://badge.fury.io/nu/AutoGen.Core.svg)](https://badge.fury.io/nu/AutoGen.Core)[![Discord](https://img.shields.io/discord/1153072414184452236?logo=discord&style=flat)](https://aka.ms/autogen-dc)[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40pyautogen)](https://twitter.com/pyautogen)
# AutoGen -AutoGen is an open-source framework for building intelligent, agent-based systems using AI. It simplifies the creation of event-driven, distributed, scalable, and resilient AI applications. With AutoGen, you can easily design systems where AI agents collaborate, interact, and perform tasks autonomously or with human oversight. - -AutoGen is built to streamline AI development and research, enabling the use of multiple large language models (LLMs), integrated tools, and advanced multi-agent communication workflows. -You can develop and test your agent systems locally, then seamlessly scale to a distributed cloud environment as your needs grow. - -> [!IMPORTANT] -> *Note for contributors and users*: [microsoft/autogen](https://aka.ms/autogen-gh) is the official repository of AutoGen project and it is under active development and maintenance under MIT license. We welcome contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. We acknowledge the invaluable contributions from our existing contributors, as listed in [contributors.md](./CONTRIBUTORS.md). Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. For further information please also see [Microsoft open-source contributing guidelines](https://github.com/microsoft/autogen?tab=readme-ov-file#contributing). +> [!IMPORTANT] +> *Note for contributors and users*: [microsoft/autogen](https://aka.ms/autogen-gh) is the official repository of AutoGen project and it is under active development and maintenance under MIT license. We welcome contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. We acknowledge the invaluable contributions from our existing contributors, as listed in [contributors.md](./CONTRIBUTORS.md). Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. For further information please also see [Microsoft open-source contributing guidelines](https://github.com/microsoft/autogen?tab=readme-ov-file#contributing). > -> -*Maintainers (Sept 6th, 2024)* - -AutoGen was created out of collaborative [research](https://microsoft.github.io/autogen/docs/Research) from Microsoft, Penn State University, and the University of Washington. - -## Key Features - -- **Asynchronous Messaging**: Agents communicate via asynchronous messages, supporting both event-driven and request/response interaction patterns. -- **Scalable & Distributed**: Design complex, distributed agent networks that can operate across organizational boundaries. -- **Modular & Extensible**: Customize your system with pluggable components, including custom agents, memory services, tool registries, and model libraries. -- **Cross-Language Support**: Interoperate agents across different programming languages. Currently supports Python and .NET, with more languages coming soon. -- **Observability & Debugging**: Built-in tools for tracking, tracing, and debugging agent interactions and workflows. - +> -*Maintainers (Sept 6th, 2024)* -## Getting Started - -The current stable release of autogen is autogen 0.2 You can find it here: *TODO: insert link* - -The version you are looking at is a new architecture for autogen 0.5. - -We are in the early stages of development for this new architecture, but we are excited to share our progress with you. - -We are looking for feedback and contributions to help shape the future of this project. - -Your best place to start is the [Documentation](https://microsoft.github.io/agnext). +AutoGen is an open-source framework for building intelligent, agent-based systems using AI. It simplifies the creation of event-driven, distributed, scalable, and resilient AI applications. With AutoGen, you can easily design systems where AI agents collaborate, interact, and perform tasks autonomously or with human oversight. -- [Documentation](http://microsoft.github.io/agnext) for the core concepts and Python API references (.NET coming). -- [Python README](https://github.com/microsoft/agnext/tree/main/python/README.md) for how to develop and test the Python package. -- [Python Examples](https://github.com/microsoft/agnext/tree/main/python/packages/autogen-core/samples) for examples of how to use the Python package and multi-agent patterns. -- [.NET](https://github.com/microsoft/agnext/tree/main/dotnet) -- [.NET Examples](https://github.com/microsoft/agnext/tree/main/dotnet/samples) +* [Installation](#install) +* [Features](#features) +* [Using Autogen](#using-autogen) +* [Roadmap](#roadmap) -## News +AutoGen is built to streamline AI development and research, enabling the use of multiple large language models (LLMs), integrated tools, and advanced multi-agent communication workflows. +You can develop and test your agent systems locally, then seamlessly scale to a distributed cloud environment as your needs grow. -:fire: **September 16, 2024**: AutoGen 0.5 is a new architecture for autogen! This new version is in preview release and being developed in the open over the next several weeks as we refine the documentation, samples, and work with our users on evolving this new version. 🚀 +:fire: **September 18, 2024**: AutoGen 0.5 is a new architecture for autogen! This new version is in preview release and being developed in the open over the next several weeks as we refine the documentation, samples, and work with our users on evolving this new version. 🚀 - Autogen 0.5 represents a rearchitecutre of the system to make it more scalable, resilient, and interoperable across multiple programming languages. - It is designed to be more modular and extensible, with a focus on enabling a wide range of applications and use cases. - This redeign features a full .NET SDK and python SDKs, with more languages to come in the future. Agents may be written in either language and interoperate with one another over a common messaging protocol using the CloudEvents standard. -:tada: June 6, 2024: WIRED publishes a new article on AutoGen: [Chatbot Teamwork Makes the AI Dream Work](https://www.wired.com/story/chatbot-teamwork-makes-the-ai-dream-work/) based on interview with [Adam Fourney](https://github.com/afourney). +# Install -:tada: June 4th, 2024: Microsoft Research Forum publishes new update and video on [AutoGen and Complex Tasks](https://www.microsoft.com/en-us/research/video/autogen-update-complex-tasks-and-agents/) presented by [Adam Fourney](https://github.com/afourney). - -:tada: May 29, 2024: DeepLearning.ai launched a new short course [AI Agentic Design Patterns with AutoGen](https://www.deeplearning.ai/short-courses/ai-agentic-design-patterns-with-autogen), made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators [Chi Wang](https://github.com/sonichi) and [Qingyun Wu](https://github.com/qingyun-wu). - -:tada: May 24, 2024: Foundation Capital published an article on [Forbes: The Promise of Multi-Agent AI](https://www.forbes.com/sites/joannechen/2024/05/24/the-promise-of-multi-agent-ai/?sh=2c1e4f454d97) and a video [AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang](https://www.youtube.com/watch?v=RLwyXRVvlNk). - -:tada: May 13, 2024: [The Economist](https://www.economist.com/science-and-technology/2024/05/13/todays-ai-models-are-impressive-teams-of-them-will-be-formidable) published an article about multi-agent systems (MAS) following a January 2024 interview with [Chi Wang](https://github.com/sonichi). - -:tada: May 11, 2024: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://openreview.net/pdf?id=uAjxFFing2) received the best paper award at the [ICLR 2024 LLM Agents Workshop](https://llmagents.github.io/). - -:tada: Apr 26, 2024: [AutoGen.NET](https://microsoft.github.io/autogen-for-net/) is available for .NET developers! Thanks [XiaoYun Zhang](https://www.linkedin.com/in/xiaoyun-zhang-1b531013a/) - -:tada: Apr 17, 2024: Andrew Ng cited AutoGen in [The Batch newsletter](https://www.deeplearning.ai/the-batch/issue-245/) and [What's next for AI agentic workflows](https://youtu.be/sal78ACtGTc?si=JduUzN_1kDnMq0vF) at Sequoia Capital's AI Ascent (Mar 26). - -:tada: Mar 3, 2024: What's new in AutoGen? 📰[Blog](https://microsoft.github.io/autogen/blog/2024/03/03/AutoGen-Update); 📺[Youtube](https://www.youtube.com/watch?v=j_mtwQiaLGU). - -:tada: Mar 1, 2024: the first AutoGen multi-agent experiment on the challenging [GAIA](https://huggingface.co/spaces/gaia-benchmark/leaderboard) benchmark achieved the No. 1 accuracy in all the three levels. - - - -:tada: Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023). - - - - - -:tada: Nov 8, 2023: AutoGen is selected into [Open100: Top 100 Open Source achievements](https://www.benchcouncil.org/evaluation/opencs/annual.html) 35 days after spinoff from [FLAML](https://github.com/microsoft/FLAML). - - - - - - - - - -:tada: Mar 29, 2023: AutoGen is first created in [FLAML](https://github.com/microsoft/FLAML). - - - - - -## Roadmaps - -- [AutoGen 0.2] - This is the current stable release of AutoGen. We will continue to accept bug fixes and minor enhancements to this version. -- [AutoGen 0.5] - This is the first release of the new event-driven architecture. This release is still in preview. We will be focusing on stability of the interfaces, documentation, tutorials, samples, and a collection of base agents from which you can inherit. We are also working on compatibility interfaces for those familiar with prior versions of AutoGen. -- [future] - We are excited to work with our community to define the future of AutoGen. We are looking for feedback and contributions to help shape the future of this project.Here are some major planned items: - - [ ] Add support for more languages - - [ ] Add support for more base agents and patterns - - [ ] Add compatibility with Bot Framework Activity Protocol - -## Quickstart - -The easiest way to start playing is -1. Click below to use the GitHub Codespace - - [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/microsoft/autogen?quickstart=1) - - 2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration. - 3. Start playing with the notebooks! +
-*NOTE*: OAI_CONFIG_LIST_sample lists GPT-4 as the default model, as this represents our current recommendation, and is known to work well with AutoGen. If you use a model other than GPT-4, you may need to revise various system prompts (especially if using weaker models like GPT-3.5-turbo). Moreover, if you use models other than those hosted by OpenAI or Azure, you may incur additional risks related to alignment and safety. Proceed with caution if updating this default. +[(See Installation docs formore details)](https://microsoft.github.io/autogen/docs/Installation) -

- - ↑ Back to Top ↑ - -

+
-## [Installation](https://microsoft.github.io/autogen/docs/Installation) -### Option 1. Install and Run AutoGen in Docker +#### Option 1. Install and Run AutoGen in Docker Find detailed instructions for users [here](https://microsoft.github.io/autogen/docs/installation/Docker#step-1-install-docker), and for developers [here](https://microsoft.github.io/autogen/docs/Contribute#docker-for-development). -### Option 2. Install AutoGen Locally +#### Option 2. Install AutoGen Locally AutoGen requires **Python version >= 3.8, < 3.13**. It can be installed from pip: @@ -167,13 +65,31 @@ Even if you are installing and running AutoGen locally outside of docker, the re For LLM inference configurations, check the [FAQs](https://microsoft.github.io/autogen/docs/FAQ#set-your-api-endpoints). -

- - ↑ Back to Top ↑ - -

+# Features + +- **Asynchronous Messaging**: Agents communicate via asynchronous messages, supporting both event-driven and request/response interaction patterns. +- **Scalable & Distributed**: Design complex, distributed agent networks that can operate across organizational boundaries. +- **Modular & Extensible**: Customize your system with pluggable components, including custom agents, memory services, tool registries, and model libraries. +- **Cross-Language Support**: Interoperate agents across different programming languages. Currently supports Python and .NET, with more languages coming soon. +- **Observability & Debugging**: Built-in tools for tracking, tracing, and debugging agent interactions and workflows. + +# Using Autogen + +The current stable release of autogen is autogen 0.2 You can find it here: *TODO: insert link* -## Documentation +The version you are looking at is a new architecture for autogen 0.5. + +We are in the early stages of development for this new architecture, but we are excited to share our progress with you. + +We are looking for feedback and contributions to help shape the future of this project. + +Your best place to start is the [Documentation](https://microsoft.github.io/agnext). + +- [Documentation](http://microsoft.github.io/agnext) for the core concepts and Python API references (.NET coming). +- [Python README](https://github.com/microsoft/agnext/tree/main/python/README.md) for how to develop and test the Python package. +- [Python Examples](https://github.com/microsoft/agnext/tree/main/python/packages/autogen-core/samples) for examples of how to use the Python package and multi-agent patterns. +- [.NET](https://github.com/microsoft/agnext/tree/main/dotnet) +- [.NET Examples](https://github.com/microsoft/agnext/tree/main/dotnet/samples) You can find detailed documentation about AutoGen [here](https://microsoft.github.io/autogen/). @@ -185,119 +101,52 @@ In addition, you can find: - [Contributing guide](https://microsoft.github.io/autogen/docs/Contribute) -- [Roadmap](https://github.com/orgs/microsoft/projects/989/views/3) - -

- - ↑ Back to Top ↑ - -

- -## Related Papers +# Roadmap -[AutoGen Studio](https://www.microsoft.com/en-us/research/publication/autogen-studio-a-no-code-developer-tool-for-building-and-debugging-multi-agent-systems/) +- [AutoGen 0.2] - This is the current stable release of AutoGen. We will continue to accept bug fixes and minor enhancements to this version. +- [AutoGen 0.5] - This is the first release of the new event-driven architecture. This release is still in preview. We will be focusing on stability of the interfaces, documentation, tutorials, samples, and a collection of base agents from which you can inherit. We are also working on compatibility interfaces for those familiar with prior versions of AutoGen. +- [future] - We are excited to work with our community to define the future of AutoGen. We are looking for feedback and contributions to help shape the future of this project.Here are some major planned items: + - [ ] Add support for more languages + - [ ] Add support for more base agents and patterns + - [ ] Add compatibility with Bot Framework Activity Protocol -``` -@inproceedings{dibia2024studio, - title={AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systems}, - author={Victor Dibia and Jingya Chen and Gagan Bansal and Suff Syed and Adam Fourney and Erkang (Eric) Zhu and Chi Wang and Saleema Amershi}, - year={2024}, - booktitle={Pre-Print} -} -``` +# FAQ -[AutoGen](https://aka.ms/autogen-pdf) +### What is AutoGen 0.5? -``` -@inproceedings{wu2023autogen, - title={AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework}, - author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Beibin Li and Erkang Zhu and Li Jiang and Xiaoyun Zhang and Shaokun Zhang and Jiale Liu and Ahmed Hassan Awadallah and Ryen W White and Doug Burger and Chi Wang}, - year={2024}, - booktitle={COLM}, -} -``` +AutoGen 0.5 is a rewrite of autogen from the ground up to create a more robust, scalable, easier to use, x-lang SDK for building AI Agents. -[EcoOptiGen](https://arxiv.org/abs/2303.04673) +### Why are you doing this? -``` -@inproceedings{wang2023EcoOptiGen, - title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference}, - author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah}, - year={2023}, - booktitle={AutoML'23}, -} -``` +We listened to our AutoGen users, learned from what was working, and adapted to fix what wasn't. We brought together wide ranging teams working on many different types of AI Agents and collaborated to design an improved framework with a more flexible programming model and better scaleability. -[MathChat](https://arxiv.org/abs/2306.01337) +### Who should use it? -``` -@inproceedings{wu2023empirical, - title={An Empirical Study on Challenging Math Problem Solving with GPT-4}, - author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang}, - year={2023}, - booktitle={ArXiv preprint arXiv:2306.01337}, -} -``` +This code is still experimental. We encourage adventurous early adopters to please try it out, give us feedback, and contribute. -[AgentOptimizer](https://arxiv.org/pdf/2402.11359) +### I'm using AutoGen 0.2, should I upgrade? -``` -@article{zhang2024training, - title={Training Language Model Agents without Modifying Language Models}, - author={Zhang, Shaokun and Zhang, Jieyu and Liu, Jiale and Song, Linxin and Wang, Chi and Krishna, Ranjay and Wu, Qingyun}, - journal={ICML'24}, - year={2024} -} -``` +If you consider yourself an early adopter, you are comfortable making some changes to your code, and are willing to try it out, then yes. -[StateFlow](https://arxiv.org/abs/2403.11322) -``` -@article{wu2024stateflow, - title={StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows}, - author={Wu, Yiran and Yue, Tianwei and Zhang, Shaokun and Wang, Chi and Wu, Qingyun}, - journal={arXiv preprint arXiv:2403.11322}, - year={2024} -} -``` +### How do I still use AutoGen 0.2? -

- - ↑ Back to Top ↑ - -

+Just keep doing what you were doing before. -## Contributing +### How do I migrate? -This project welcomes contributions and suggestions. Most contributions require you to agree to a -Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us -the rights to use your contribution. For details, visit . +We are working on a migration guide. Until then, see the [documentation]((http://microsoft.github.io/agnext) -If you are new to GitHub, [here](https://opensource.guide/how-to-contribute/#how-to-submit-a-contribution) is a detailed help source on getting involved with development on GitHub. +### What is happening next? When will this release be ready? -When you submit a pull request, a CLA bot will automatically determine whether you need to provide -a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions -provided by the bot. You will only need to do this once across all repos using our CLA. +We are still working on improving the documentation, samples, and enhancing the code. We will prepare a release announcement when these things are completed in the next few weeks. -This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). -For more information, see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or -contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments. +### What is the history of this project? -

- - ↑ Back to Top ↑ - -

+The rearchitecture of autogen came from multiple Microsoft teams coming together to build the next generation of AI agent framework - merging ideas from several predecessor projects. The team decided to bring this work to OSS as an evolutionof autogen in September 2024. -## Contributors Wall - - - +### What are the official channels for support? -

- - ↑ Back to Top ↑ - -

+You can use the same support channels as for AutoGen 0.2 - The GH project[Issues](https://github.com/microsoft/agnext/issues) and [Discord](https://aka.ms/autogen-dc). # Legal Notices @@ -321,3 +170,5 @@ or trademarks, whether by implication, estoppel, or otherwise. ↑ Back to Top ↑

+ +AutoGen was created out of collaborative [research](https://microsoft.github.io/autogen/docs/Research) from Microsoft, Penn State University, and the University of Washington. \ No newline at end of file