New AutoGen Architecture Preview#3600
Merged
Merged
Conversation
* WIP refactor instantiation context * finish up changes * Update python/src/agnext/core/_agent_runtime.py Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * Update python/src/agnext/core/_agent_runtime.py Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * add warning --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* add Azure Active Directory auth for samples * Update README
* Validate desc, DRY * Update python/src/agnext/core/_base_agent.py --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
…323) * add notebooks for documentation * Merge remote-tracking branch 'origin/main' into ekzhu-notebooks * Add install * Add to checks
* use myst_nb for notebook docs; refactor docs to separate concepts and code tutorial * Get started tutorial * fix types
Add gpt-4o-2024-08-06
* Initial work porting webarena to async * Perhaps resolved some of the eval() issues.
* Doc: multi-agent design pattern * Fix warnings. * mypy * fix type * chore: Remove unused import and checkpoint code in langgraph_agent.py
* Re-added multimodality to mdconvert. * Fixed formatting.
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Rename fields in agent metadata * team one fixes * another fix
* Revised prompts to match autogen experiments. * Handle sh code blocks * Move executor prompt into coder.py * Fixed formatting.
* add checks for notebooks * format * Fix mypy * format --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* check ledger formatting * format file * format file * rename agent metadata field 'name'-->'type' --------- Co-authored-by: Enhao Zhang <t-enhaozhang@microsoft.com>
* Add cookbook for openai assistant agent. Reformat * update index * add requests * type requests
Co-authored-by: Kosta Petan <Kosta.Petan@microsoft.com>
* Fixed numerous issues with orchestrator, related to 342' * Refined prompts, and added max wall-clock time to orchestrators. * Fixed formatting.
… running from magentic. (#348)
* Remove commented code * Removed unused code * Add try except to catch json decode error --------- Co-authored-by: afourney <adam.fourney@gmail.com>
* Azure container code execution * fix check errors. Remove unnecessary file * add TokenProvider class * update deps * addressing PR comments * update docstring * switch to aiohttp * fix client timeout
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* update readme * Add change log
* Python host runtime impl * update * ignore proto generated files * move worker runtime to application * Move example to samples * Fix import * fix * update * server client * better shutdown * fix doc conf * add type
* Add proto files and add github action to block PR if changes to proto files required. * remove action
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* remove subscription on client disconnect in worker runtime * address PR feedback * remove outdated comment * remove public properties * fix mypy issue * address PR feedback --------- Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
…l events (#3665) * Move tool to agent; refactor logging in agentchat * Update notebook
* remove merging primitive from .editorconfig and gitignore * use file scope namespace * remove file-scope name * fix format
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Fixing the HelloWorld sample and some refactoring of .NET code, adding App and Host classes in client and runtime.
* rebase and address PR comments * address PR feedback
* Selector group chat that uses LLM to select the next speaker * Merge remote-tracking branch 'origin/staging' into selector-groupchat * Add allow_repeated_speaker option * Add test for allowed_repeated_speaker=True * Example for selector group chat * format * Rename and index * title for notebook * Merge remote-tracking branch 'origin/staging' into selector-groupchat
* update docs on agent chat. * add langchain support * fix formatting issues * Update python/packages/autogen-core/docs/src/agentchat-user-guide/index.md Co-authored-by: gagb <gagb@users.noreply.github.com> * Update python/packages/autogen-core/docs/src/agentchat-user-guide/index.md Co-authored-by: gagb <gagb@users.noreply.github.com> * add company reseach and literature review examples with tools * format fixes * format and type fixes * add selector groupchat to agentchat index page * rename quick start as code exec * type fixes * format fix * Remove blank cell from notebooks --------- Co-authored-by: gagb <gagb@users.noreply.github.com> Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Set logging of internal messages to debug * Fix worker runtime tests
* migrate code executor and tests * update extras * update dependencies and examples * fix imports * fix uv lock * add code_executor to toctree --------- Co-authored-by: Leonardo Pinheiro <lpinheiro@microsoft.com> Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Style updates for website * tab styling
* Update PR link in blog post (#3602) * Update PR link in blog post * Update index.mdx * Create CI to tag issues with needs triage (#3605) * Update issue templates (#3610) * Update config.yml * Delete .github/ISSUE_TEMPLATE.md * Delete .github/ISSUE_TEMPLATE/general_issue.yml * Update feature_request.yml * Update feature_request.yml * Update feature_request.yml * Update feature_request.yml * Update bug_report.yml * Update .github/ISSUE_TEMPLATE/bug_report.yml Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * Update .github/ISSUE_TEMPLATE/config.yml Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * Update bug_report.yml * Update config.yml --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * termination condition * Termination condition * termination condition in group chat manager * Update module import * Fix logging * Clean up * Fix doc string --------- Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* add service defaults to Host * add otel to app host * ran format * remove HelloAgents * moving things around to fit the folder structure/naming conventions --------- Co-authored-by: Xiaoyun Zhang <bigmiao.zhang@gmail.com>
add more docs for .NET sample
* Add extension to handle pydantic docs * Docs tweaks --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* Add more FAQs to readme * Update README.md Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * Update README.md Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> * Update README.md --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com> Co-authored-by: Ryan Sweet <rysweet@microsoft.com>
* Refactor logging in agentchat * fix notebook --------- Co-authored-by: Jack Gerrits <jack@jackgerrits.com> Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
20 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Blog post
Please use discussion for feedback, comments, or questions.
One year ago, we launched AutoGen, a programming framework designed to build agentic AI systems. The release of AutoGen sparked massive interest within the developer community. As an early release, it provided us with a unique opportunity to engage deeply with users, gather invaluable feedback, and learn from a diverse range of use cases and contributions. By listening and engaging with the community, we gained insights into what people were building or attempting to build, how they were approaching the creation of agentic systems, and where they were struggling. This experience was both humbling and enlightening, revealing significant opportunities for improvement in our initial design, especially for power users developing production-level applications with AutoGen.
Through engagements with the community, we learned many lessons:
These learnings, along with many others from other agentic efforts across Microsoft, prompted us to take a step back and lay the groundwork for a new direction. A few months ago, we started dedicating time to distilling these learnings into a roadmap for the future of AutoGen. This led to the development of AutoGen 0.4, a complete redesign of the framework from the foundation up. AutoGen 0.4 embraces the actor model of computing to support distributed, highly scalable, event-driven agentic systems. This approach offers many advantages, such as:
Today, we are delighted to share our progress and invite everyone to collaborate with us and provide feedback to evolve AutoGen and help shape the future of multi-agent systems.
As the first step, we are opening this pull request into the main branch with the current state of development of 0.4. After approximately a week, we plan to merge this into main and continue development. There's still a lot left to do before 0.4 is ready for release though, so keep in mind this is a work in progress.
Starting in AutoGen 0.4, the project will have three main libraries:
Core
The core API of AutoGen is built following the actor model. It supports asynchronous message passing between agents and event-based workflows. Start here if you are building scalable, event-driven agentic systems. Agents in the core layer handle and produce typed messages, using either direct messaging, which functions like RPC, or via broadcasting to topics, which is pub-sub. Agents can be distributed and implemented in different programming languages, while still communicating with one another.
AgentChat
AgentChat API is task driven and at a high level like AutoGen 0.2. It allows you to define conversational agents, compose them into teams, and then use them to solve tasks. AgentChat itself is built on the core layer, but it abstracts away much of its low-level system concepts. Start here if you just want to focus on multi-agents and workflows while not worrying about scalability and deep integration with existing software. For workflows that don’t fit into the API provided by AgentChat, target just core instead.
Extensions
The extension package contains implementations of the core interfaces using third-party systems, such as OpenAI model client and Azure code executors. Besides the built-in extensions, the package accommodates community-contributed extensions through namespace sub-packages. We are looking forward to seeing your contributions.
AutoGen 0.2
AutoGen 0.2 is still available, developed and maintained out of the 0.2 branch. For everyone looking for a stable version, we recommend continuing to use 0.2 for the time being. It can be installed using:
This new package name was used to align with the new packages that will come with 0.4:
autogen-core,autogen-agentchat, andautogen-ext.Lastly, we will be using GitHub Discussion as the official community forum for the new version and, going forward, all discussions related to the AutoGen project. We look forward to meeting you there.
- AutoGen Team