v0.2.16

Highlights

• Nested chats are made easier by register_nested_chats. Nested chats allow AutoGen agents to use other agents as their inner monologue before replying to other agents. Example of using nested chat to compose a super-agent based on multi-agent conversation.
• Blog for FSM-based group chat with user-specified agent transitions.
• Docker-based jupyter executor.
• Support removing function calls in ConversableAgent.
• Improvement in hook methods.
• Bug fix for DALLE agent.
• Improvement in doc & test.

Thanks to @qingyun-wu @joshkyh @freedeaths @jackgerrits @skzhang1 @RohitRathore1 @BeibinLi @shreyas36 @gunnarku @abhaymathur21 @victordibia and all the other contributors!

What's Changed

• Update agentchat_custom_model.ipynb by @shreyas90999 in #1768
• Blog regarding finite-state machine by @joshkyh in #1622
• Adding register_nested_chats to make nested chat easier by @qingyun-wu in #1753
• Support functions removing in ConversableAgent by @skzhang1 in #1786
• Don't require notebooks to have all imports at top by @jackgerrits in #1803
• hook-list are updated to accept a sender argument by @RohitRathore1 in #1799
• make default model of a constant class variable by @RohitRathore1 in #1780
• Debug: Resolve the DALLE Agent's self.client error. by @BeibinLi in #1798
• Add shebang functionality to tests by @gunnarku in #1784
• Implement docker based jupyter executor by @jackgerrits in #1794
• Add function generator and validator to gallery by @abhaymathur21 in #1807
• Extend process_notebooks for testing by @jackgerrits in #1789
• Update bug_report.yml [Invite users to explicitly state what model they are using that resulted in the issue] by @victordibia in #1811
• bug fix and cleanup for 0.2.16 by @sonichi in #1827

New Contributors

• @shreyas90999 made their first contribution in #1768

Full Changelog: v0.2.15...v0.2.16

v0.2.15

Highlights

• Async version of multiple dependent chats. Example.
• Improvement in chat control:
  • Allow sending introductions in the beginning of group chat for participants to know each other's role.
  • Allow setting max turns when initiating chats.
• Improvement and bug fix in:
  • custom message processing methods: allow processing messages before sending, such as displaying in a custom frontend.
  • multimodal agent: use PIL image internally.
  • code execution: command line executor, powershell etc.
  • long context handling.
  • GPT Assistant Agent: compatibility with azure openai.
  • AutoGenBench.
  • Documentation.

Thanks to @randombet @afourney @qingyun-wu @BeibinLi @jackgerrits @abhaymathur21 @skzhang1 @gunnarku @AaronWard @thinkall @dkirsche @RohitRathore1 @LinxinS97 @IANTHEREAL and all the other contributors!

What's Changed

• update ecosystem by @skzhang1 in #1624
• Check for missing dependencies before building the website by @gunnarku in #1678
• Allow limiting the maximum number of turns in initiate_chat and initiate_chats by @qingyun-wu in #1703
• Update example page by @qingyun-wu in #1698
• use str for hook key by @sonichi in #1711
• Add agent robot example to gallery by @AaronWard in #1718
• Use PIL Image internally for the Multimodal Agent by @BeibinLi in #1124
• Fix issue 1440 by applying new function registration decorator by @thinkall in #1661
• Command line code sanitation by @AaronWard in #1627
• news update by @sonichi in #1720
• fix web formats by @skzhang1 in #1728
• Updated code_utils.py & local_commandline_code_executor.py (powershell to pwsh) by @abhaymathur21 in #1710
• fix some docstring issues affecting rendering by @jackgerrits in #1739
• Refactor transform_messages by @dkirsche in #1631
• Async version of multiple sequential chat by @randombet in #1724
• Allow None for sender field in CoversableAgent.generate_reply by @RohitRathore1 in #1725
• [AutoBuild] fix test error by @LinxinS97 in #1750
• Updating code_utils.py to solve issue #1747 by @abhaymathur21 in #1758
• Add sidebar for notebooks page by @jackgerrits in #1766
• Use jupyer-kernel-gateway for ipython executor by @jackgerrits in #1748
• Handle azure_deployment Parameter Issue in GPTAssistantAgent to Maintain Compatibility with OpenAIWrapper by @IANTHEREAL in #1721
• Groupchat send introductions by @afourney in #961
• Version 0.0.2 of Autogenbench by @afourney in #1548
• process message before send by @sonichi in #1783

New Contributors

• @dkirsche made their first contribution in #1631
• @RohitRathore1 made their first contribution in #1725

Full Changelog: v0.2.14...v0.2.15

v0.2.14

Highlights

• Enhancement to sequential chats programming
  • support custom summary method
  • allow the chats to be initiated by different agents
  • example
• Improvement to GPTAssistantAgent
  • respect termination and human input mode
  • support Azure assistant API
• Runtime logging is back and advanced! Example
• Improvement to group chat: get nested agents and look up by name
• Doc improvement and bug fix.

Thanks to @qingyun-wu @yousonnet @IANTHEREAL @cheng-tan @WaelKarkoub @jackgerrits @bobbravo2 @maxim-saplin @olgavrou @gagb @FarshidShafia @gunnarku @Xtrah and all the other contributors!

What's Changed

• Rewrite and consolidate configuration docs by @jackgerrits in #1581
• Adding callable summary_method support and enhancements to initiate_chats by @qingyun-wu in #1628
• remove print config list by @sonichi in #1637
• return None instead of tuple in _generate_oai_reply_from_client by @sonichi in #1644
• [README] remove duplicated line by @bobbravo2 in #1646
• add autogen.initiate_chats by @qingyun-wu in #1638
• add GPTAssistantAgent is_termination_msg valid by @yousonnet in #1642
• FAQ, highlight the correct package name is pyautogen by @maxim-saplin in #1665
• Update gallery grid to flow better across screen sizes by @jackgerrits in #1652
• update dotnet workflow by @LittleLittleCloud in #1669
• Fix custom client registration by @olgavrou in #1653
• Update Transparency FAQs by @gagb in #1672
• Update agent_chat.md by @FarshidShafia in #1677
• Update notebook contrib guidance, update a few notebooks for site by @jackgerrits in #1651
• Validate the OpenAI API key format by @gunnarku in #1635
• Logging by @cheng-tan in #1146
• Validate llm_config passed to ConversableAgent (issue #1522) by @gunnarku in #1654
• do model check properly by @sonichi in #1686
• support azure assistant api by @IANTHEREAL in #1616
• Feature: Get Nested Agents in a GroupChat by @WaelKarkoub in #1636
• bug fix: logging test may fail if some config fails by @cheng-tan in #1695
• Update Azure OpenAI API version to 2024-02-15-preview by @Xtrah in #1692

New Contributors

• @bobbravo2 made their first contribution in #1646
• @yousonnet made their first contribution in #1642
• @FarshidShafia made their first contribution in #1677
• @gunnarku made their first contribution in #1635
• @WaelKarkoub made their first contribution in #1636

Full Changelog: v0.2.13...v0.2.14

v0.2.13

Highlights

• New extensible agent capability for long context handling. Example
• New extensible code execution interface and stateful executors. Examples upcoming.
• Documentation improvement and bug fix.
• Improvement in web surfer.

Thanks to @gagb @ekzhu @jackgerrits @mrwadams @LittleLittleCloud @olgavrou @davorrunje and all the other contributors!

What's Changed

• Add quarto install to Contribute.md by @jackgerrits in #1585
• Fix a couple of tiny issues in blog posts by @jackgerrits in #1578
• Fix typo in title by @mrwadams in #1594
• Fix: check response usage is not None by @olgavrou in #1599
• add other language drop down link to AutoGen website by @LittleLittleCloud in #1573
• Proxy PR for Long Context Capability 1513 by @gagb in #1591
• Hide table of contents on notebooks page by @jackgerrits in #1600
• Code executors by @ekzhu in #1405
• Refactoring web surfer to use function decorators by @davorrunje in #1435
• add long context handling notebook by @sonichi in #1618

New Contributors

• @mrwadams made their first contribution in #1594

Full Changelog: v0.2.12...v0.2.13

v0.2.12

Highlights

• Introducing AutoAnny: A New Discord Bot Built with AutoGen
• Enhancing Multiple sequential chats, a newly introduced interface that allows one to program a sequence of chats and carry previous chat results to new chats
• Allowing SocietyOfMind agents to work with function
• Documentation and usability improvements

Thanks to @gagb @afourney @jackgerrits @sonichi @joshkyh @amihalik and all the other contributors.

What's Changed

• Allow SocietyOfMind agent to work with function calling and tools. by @afourney in #1569
• Error handling in getting LLM-based summary by @qingyun-wu in #1567
• Quick Fix on the Google Colab Link by @joshkyh in #1571
• Update devcontainer.json with copilot extension by @gagb in #1556
• Introducing AutoAnny: A New Discord Bot Built with AutoGen by @gagb in #1501
• Using a more robust "reflection_with_llm" summary method by @qingyun-wu in #1575
• Expose filter_config function by @jackgerrits in #1582
• Adding max_tokens to autogenstudio LLMConfig by @amihalik in #1574
• Add mypy config to pyproject.toml by @jackgerrits in #1543
• Add more descriptive error message in the presence of OpenAI API timeouts by @jackgerrits in #1577
• Update base container for website by @gagb in #1584
• avoid access private variable by @sonichi in #1592

New Contributors

• @amihalik made their first contribution in #1574

Full Changelog: v0.2.11...v0.2.12

v0.2.11

Highlights

Two major upgrades of conversation programming (experimental features under active development):

• Finite state machine (FSM) based group chat: allow more fine-grained control of speaker order transition in group chat.
• Multiple sequential chats: program a sequence of chats and carry previous chat results to new chats.

AutoGen Studio updates:

• Workflow export.
• Skill editing.
• CSV support.
• Windows testing.

Other improvements:

• Allow timeout for code execution in windows.
• Make every agent receive the termination message in group chat.
• Improvement in documentation.
• Fix an import issue.

Thanks to @joshkyh @freedeaths @qingyun-wu @victordibia @pretherford @ekzhu @jackgerrits @samuelogboye @Xtrah @olgavrou @thinkall @abhaymathur21 and all the other contributors!

What's Changed

• Disable default code execution on society_of_mind and web_surfer. by @afourney in #1516
• Add notebooks section on website by @jackgerrits in #1495
• Update pyproject.toml for Poetry mismatch by @agamm in #1454
• Update tests for code_utils and use ThreadPoolExecutor for code execution in windows by @ekzhu in #1472
• remove useless code in groupchat; simplify the handling of termination msg by @sonichi in #1532
• Fix example for LLM configuration docs by @jackgerrits in #1528
• fix(path): Update Installation.md -Update Dockerfile path for Autogen base image build by @samuelogboye in #1425
• Update outdated link in README.md by @Xtrah in #1541
• Fix formatting of notebook contributing.md by @jackgerrits in #1540
• Custom Model Client docs follow-up by @olgavrou in #1545
• Fix docstrings of a_initiate_chat by @thinkall in #1539
• Autogenstudio Updates [CSV support, Workflow Export, Skill Editing, Windows Testing ] by @victordibia in #1475
• Graph group chat by @joshkyh in #857
• Update Docker.md by @abhaymathur21 in #1554
• patch to graph groupchat by @sonichi in #1555
• Import oai.client directly in ConversableAgent by @AkashKulkarni4444 in #1557
• New initiate_chats Interface for Managing Dependent Chats in ConversableAgent by @qingyun-wu in #1402

New Contributors

• @agamm made their first contribution in #1454
• @samuelogboye made their first contribution in #1425
• @Xtrah made their first contribution in #1541
• @abhaymathur21 made their first contribution in #1554
• @AkashKulkarni4444 made their first contribution in #1557

Full Changelog: v0.2.10...v0.2.11

v0.2.10

Breaking change

Change code_execution_config default in ConversableAgent to False to match the default value change of last_n_messages.

Highlights

• Custom model client for extensibility of the inference mechanism
• SocietyOfMindAgent: demonstrating using nested chat to compose a more capable single agent based on multi-agent chat
• Improvement of tool call and function call and GPTAssistantAgent
• Documentation improvement for function call, gallery, FAQ, notebooks etc.

Thanks to @olgavrou @afourney @davorrunje @jtrugman @ekzhu @namanbarkiya @maxim-saplin @jackgerrits @Yanni8 @victordibia @eltociear @pmalarme and all the other contributors!

What's Changed

• Update function call doc with example of not using decorator syntax. by @ekzhu in #1441
• Improve docs/gallery card component by @namanbarkiya in #1445
• FAQ, working with LLM endpoints and explaining why config-list is a list by @maxim-saplin in #1451
• fixed wrong doc link by @Yanni8 in #1449
• Removed "Tool Call Id" from main content string. by @afourney in #1471
• docs: initial Jupyter support for website docs, move config notebook by @jackgerrits in #1448
• Adds a SocietyOfMindAgent that presents as a single agent, but runs GroupChat as an inner-monologue by @afourney in #890
• Function calling upgrade by @davorrunje in #1443
• fix: unit test should not call private function by @olgavrou in #1494
• Bump autogenbench version. by @afourney in #1485
• update readme to add note on required Quarto Version. Update readme t… by @victordibia in #1493
• Update README.md by @eltociear in #1491
• Implement Overwrite Tools Functionality in GPTAssistantAgent by @jtrugman in #1434
• Update Contribute.md, #1502 by @victordibia in #1508
• Fix image print for auto feedback from code notebook by @pmalarme in #1389
• deprecate using None for code_execution_config by @jackgerrits in #1506
• Added new models to token_count_utils by @afourney in #1511
• change code_execution_config default by @sonichi in #1518
• Fix tests for GPT assistant by @davorrunje in #1505
• fix broken links from moving oai utils notebook by @jackgerrits in #1497
• Custom Model Client support by @olgavrou in #1345

New Contributors

• @namanbarkiya made their first contribution in #1445
• @jtrugman made their first contribution in #1434
• @pmalarme made their first contribution in #1389

Full Changelog: v0.2.9...v0.2.10

v0.2.9

Highlights

• GroupChat support in AutoGen Studio.
• Introducing AutoGenBench, A Tool for Measuring and Evaluating AutoGen Agents.
• (Experimental) Allow agents to send history cleaning commands in group chat.
• Notebook example for SQL agent and Spider environment.
• New examples added to Gallery, such as stateful development environment in Jupyter Notebook and X-Force IDE.

Thanks to @victordibia @afourney @GregorD1A1 @byronxu99 @cemtu @olimoz @randombet and all the other contributors!

What's Changed

• Autogenstudio - Add GroupChat Support to UI by @victordibia in #1352
• Cleanup and unify Dockerfiles by @gagb in #1333
• Fixed skipping code execution in docker test if already running in a container by @davorrunje in #1383
• docs: new gallery item added. by @cemtu in #1365
• add blog and warning in readme for new breaking changes by @olgavrou in #1380
• test permissions by @olaoluwasalami in #1264
• Fix permission block for deploy-website.yml by @ekzhu in #1397
• Introduces AutoGenBench by @afourney in #1048
• Fixed broken links. by @afourney in #1408
• bump version to 0.2.9 by @sonichi in #1430
• Add SQL agent and Spider environment by @byronxu99 in #1218
• Add A Stateful Dev Environment by Jupiter example to gallery by @randombet in #1376
• Correct small typos in system messages by @pbadeer in #1410
• docs: split apart installation docs into parts by @jackgerrits in #1420
• functionality of manual history cleaning by user proxy added by @GregorD1A1 in #1230

New Contributors

• @cemtu made their first contribution in #1365
• @byronxu99 made their first contribution in #1218
• @pbadeer made their first contribution in #1410
• @jackgerrits made their first contribution in #1420
• @GregorD1A1 made their first contribution in #1230

Full Changelog: v0.2.8...v0.2.9

v0.2.8

Breaking changes

1. use_docker defaults to True.
2. last_n_messages defaults to "auto".

Highlights

1. Support both redis cache and diskcache for agent chat and client.
2. Web surfer agent
3. Allow initiate_chat with no message to take human input.
4. Add dev container for AutoGen Studio.

Thanks to @olgavrou @afourney @vijaykramesh @ekzhu @balakreshnan @bitnom @gagb and all the other contributors!

What's Changed

• set use_docker to default to True by @olgavrou in #1147
• Add dev container for AutoGen Studio by @gagb in #1241
• Allow initiate_chat without passing message by @bitnom in #1244
• [Core] implement redis cache mode by @vijaykramesh in #1222
• More documentation for Cache. Updated FAQ to include database Locked error by @balakreshnan in #1291
• Add a web surfer agent that can search and browse the web. by @afourney in #1093
• bump version to 0.2.8 by @sonichi in #1349
• fix website production css by @cheng-tan in #1366
• Add an AutoGen UI example powered by Panel by @randombet in #1348
• Change last_n_messages to default to 'auto' by @afourney in #1356

New Contributors

• @olgavrou made their first contribution in #1147
• @vijaykramesh made their first contribution in #1222
• @balakreshnan made their first contribution in #1291
• @randombet made their first contribution in #1348

Full Changelog: v0.2.7...v0.2.8

v0.2.7

Headsup: in the next release we will change the default setting of use_docker in code_execution_config to True. It needs to be set to False or None explicitly to disable docker.

Highlights

• Support Python 3.12.
• Support function call style API in function decorator.
• Support AzureOpenAI when using azure endpoints.
• Add usage summary for agents.
• Improvement in docker usage and documentation.
• Bug fix for tool call, async, group chat.
• Improvement in AutoGen studio.
• Filter llm configurations by tag.

Thanks to @ekzhu, @maxim-saplin, @kevin666aa, @r3d91ll, @Yanni8, @yenif, @davorrunje, @shhdgit, @ashutoshpw, @afourney and all the other contributors!

What's Changed

• Update studio README.md with badges by @gagb in #1225
• Add documentation and raise exception when registering async reply function in sync chat by @davorrunje in #1208
• Upgrade docusaurus by @olaoluwasalami in #1101
• fix: forward kwargs to conversable agent + fix typing by @joseferben in #1193
• [Core] Sanitize filename before using it as docker image tag. Fix #1069 by @ekzhu in #1127
• [Core] Compatibility with function call style API (Azure OpenAI and Gemini) by @ekzhu in #1227
• Refined the user_proxy description. by @afourney in #951
• update default aoai version by @sonichi in #1229
• Fix bug in async group chat with func/tool call by @sonichi in #1243
• fix: Fixed typo from 'mont' to 'mount' by @eaandersen in #1250
• Improve test for function call in groupchat by @sonichi in #1252
• run sync and async in async by @yenif in #1242
• Added the ability to add tags to the OAI_CONFIG_LIST, and filter by @afourney in #1226
• Docker Documentation by @r3d91ll in #1251
• Replaced asyncio.coroutines.iscoroutinefunction with inspect.iscoroutinefunction by @davorrunje in #1267
• remove name from tool response by @yenif in #1263
• [Core] Update documentation for function call compatibility by @ekzhu in #1237
• add workdir in test by @sonichi in #1274
• remove filter_dict by @sonichi in #1284
• Add usage summary for agents by @kevin666aa in #1269
• [AutoGen Studio] Fix the new workflow process by @shhdgit in #1181
• Switched to AzureOpenAI for api_type=="azure" by @maxim-saplin in #1232
• removed alpine image by @Yanni8 in #1279
• Update README.md by @olivMertens in #1306
• Chore: Updated Blog and removed cd frontend by @ashutoshpw in #1301
• def _prepare_chat for groupchat manager to reset the groupchat by @yenif in #1254
• Fix website accessibility by @cheng-tan in #1153
• Support for Python 3.12 by @ekzhu in #1317

New Contributors

• @joseferben made their first contribution in #1193
• @eaandersen made their first contribution in #1250
• @r3d91ll made their first contribution in #1251
• @shhdgit made their first contribution in #1181
• @Yanni8 made their first contribution in #1279
• @olivMertens made their first contribution in #1306
• @ashutoshpw made their first contribution in #1301
• @cheng-tan made their first contribution in #1153

Full Changelog: v0.2.6...v0.2.7