Releases · microsoft/autogen

09 Apr 18:51

sonichi

v0.2.23

5292024

v0.2.23

This is a minor release with cost update for OpenAI models.

Highlights

New sample app using websockets with FastAPI and AutoGen
New user guide for long context handling

Thanks to @liujun121533 @davorrunje @martinzrrl @thinkall @WaelKarkoub @sethupavan12 and all the other contributors!

What's Changed

Use assistant tag to filter config by @sonichi in #2316
Fix typo in conversation-patterns.ipynb by @liujun121533 in #2322
Add Websockets example by @davorrunje in #2291
Improve readability of notebooks by @martinzrrl in #2200
cost update for gpt-3.5-turbo-0125 by @sonichi in #2332
Add back to top and year by @thinkall in #2324
Document Migration to TransformMessages by @WaelKarkoub in #2247
Fix docs related to Azure OpenAI's "model" by @sethupavan12 in #2315

New Contributors

@liujun121533 made their first contribution in #2322
@martinzrrl made their first contribution in #2200
@sethupavan12 made their first contribution in #2315

Full Changelog: v0.2.22...v0.2.23

Contributors

thinkall, sonichi, and 5 other contributors

Assets 2

06 Apr 20:15

sonichi

v0.2.22

4a44093

v0.2.22

Highlights

New capability TransformMessage: a generalization of previous long context handling capabilities. The previous capabilities will be deprecated.
New research AutoDefense: Defend against jailbreak attacks with AutoGen.
New support for non-OpenAI models:
New user guide for custom speaker selection in group chat
Update of StateFlow blogpost and paper.
New notebook on web scraping with tool use.
New example in gallery: Create Issues from Code Commits.

Thanks to @WaelKarkoub @ekzhu @skzhang1 @davorrunje @afourney @Wannabeasmartguy @jackgerrits @rajan-chari @XHMY @jtoy @marklysze @Andrew8xx8 @thinkall @BeibinLi @benstein @sharsha315 @levscaut @Karthikeya-Meesala @r-b-g-b @cheng-tan @kevin666aa and all the other contributors!

What's Changed

Transform Messages Capability by @WaelKarkoub in #1923
Bump express from 4.18.2 to 4.19.2 in /website by @dependabot in #2157
Add website analytics by @ekzhu in #2201
Render AgentOptimzier notebook in web by @skzhang1 in #2197
Replace iostream warning message with info by @davorrunje in #2207
AutoGenBench: Handle Ctrl-C more gracefully. by @afourney in #2174
fix the problem config_list_from_dotenv() can't correctly get other p… by @Wannabeasmartguy in #2172
Fix generate_init_message for Multimodal Messages by @WaelKarkoub in #2124
Support string based UDFs by @jackgerrits in #2195
Ignore protobuf generated files in CAP by @rajan-chari in #2215
AutoDefense Blog by @XHMY in #1982
2147 - Fix notebook bug to make a copy of configs for each agent by @jtoy in #2176
Improve Image Generation Notebook by @WaelKarkoub in #2213
Added ability to specify 'role' field for select speaker messages for Group Chats (Replaces PR #2167) by @marklysze in #2199
Fixed types related to function calling by @davorrunje in #2230
Replace unofficial with official pre-commit hook for ruff by @davorrunje in #2229
Re-commit of #2182: Customisation of speaker select message and prompt in GroupChat by @marklysze in #2233
Fix websockets demo notebook by @davorrunje in #2227
Fixed spelling in agentchat_transform_messages.ipynb by @Andrew8xx8 in #2234
Improving website navigation and help click-through analytics collection by @ekzhu in #2205
Dont include api ref tree in docs sidebar by @jackgerrits in #2244
Fix unstructured deps installation error by @thinkall in #2248
Add PNG and JPEG files to LFS automatically by @davorrunje in #2226
Allow custom name for functions module by @jackgerrits in #2241
Reduce sleep() in CAP library code by @rajan-chari in #2189
Notebook on web scraping with tool use by @ekzhu in #2192
Break up contributor guide for better navigability by @ekzhu in #2250
Update vision capability test: create dummy image before testing by @BeibinLi in #2258
Auto collapse side bar entries when selecting other sections by @jackgerrits in #2257
Fix Vision Capability Test for MacOS by @BeibinLi in #2260
Update listdir() in sample code docs to take correct args by @benstein in #2261
Multiline docstrings fix by @sharsha315 in #2130
Add in memory cache class by @jackgerrits in #2266
Add support for Anthropic Claude models by @levscaut in #2245
Composio: add new example by @Karthikeya-Meesala in #2237
Re-commit of #2222: Expanded speaker name matching during speaker selection by @marklysze in #2267
RetrieveUserProxyAgent, use context_max_tokens from retrieve_config if provided by @r-b-g-b in #2259
fix logging cost flaky test by @cheng-tan in #2277
Remove subdirectory .gitattributes files and add relevant files to lfs by @ekzhu in #2270
Update RetrieveChat blog to fix some outdated APIs by @thinkall in #2273
Add support for system message in Claude Notebook by @levscaut in #2280
add composio to ecosystem page by @Karthikeya-Meesala in #2272
Add isort by @thinkall in #2265
Remove info log for IOStream using default. by @ekzhu in #2281
Fix LMM test in CI by installing lfs by @ekzhu in #2282
Fix FileNotFoundError english-words.txt in RetrieveChatTest by @thinkall in #2284
Add html parser for RAG and some improvements by @thinkall in #2271
Composio: update text - "Composio Logo" -> "Composio Example" by @Karthikeya-Meesala in #2288
bump version to 0.2.22 by @sonichi in #2256
Copy llm_config to avoid external changes by @jackgerrits in #2290
Fix typo in websockets notebook by @davorrunje in #2287
Fix types in tool tests by @davorrunje in #2285
[Bug Fix] [CAP] Sleep removal introduced an Actor resolution bug. by @rajan-chari in #2296
Add Custom GroupChat Speaker Selection to tutorial by @kevin666aa in #2219
Update StateFlow blog by @kevin666aa in #2262
Fix cost calculation when completion_token is None by @kevin666aa in #2292

New Contributors

@Wannabeasmartguy made their first contribution in #2172
@XHMY made their first contribution in #1982
@jtoy made their first contribution in #2176
@Andrew8xx8 made their first contribution in #2234
@benstein made their first contribution in #2261
@sharsha315 made their first contribution in #2130
@levscaut made their first contribution in #2245
@Karthikeya-Meesala made their first contribution in #2237
@r-b-g-b made their first contribution in #2259

Full Changelog: v0.2.21...v0.2.22

Contributors

jtoy, benstein, and 21 other contributors

Assets 2

28 Mar 15:32

sonichi

v0.2.21

6fbb9e8

v0.2.21

Highlights

New feature from research: AgentOptimizer
- Blog
- Notebook
New feature in code execution: Support user defined functions in local CLI executor - similar functionality to the "skills" in AutoGen Studio.
New agent capability: Vision Capability for ConversableAgents allows them to "see" images.
New IOStream protocol and support for web sockets!
New custom model: Mistral AI API with native tool call support. conversational chess game powered by mistral
New benchmarking tool: WebArena. Run agents in the WebArena benchmark.
Doc improvement
- Tutorial about tool use
- Simplified quick start
- Link to notebook rendering
Other improvements such as silencing pip install messages, parsing HTML style tags, getting list of actors from directory service.

Thanks to @skzhang1 @jackgerrits @BeibinLi @davorrunje @ekzhu @olgavrou @WaelKarkoub @rajan-chari @eltociear @jamesliu @shouldnotappearcalm and all the other contributors!

What's Changed

Fix link in non-openai model doc by @ekzhu in #2106
mypy in pre-commit fixed by @davorrunje in #2117
Silences Pip Install Messages in Code Executors by @WaelKarkoub in #2105
Update agentchat_nestedchat_optiguide.ipynb by @eltociear in #2122
Removing tool use from Use-Cases/agent_chat by @ekzhu in #2120
Update docs for new executors by @ekzhu in #2119
missing jupyter when import JupyterCodeExecutor by @jamesliu in #2132
Add vision capability by @BeibinLi in #2025
Native tool call support for Mistral AI API and topic notebook. by @ekzhu in #2135
New conversational chess notebook using nested chats and tool use by @ekzhu in #2137
add webarena in samples by @olgavrou in #2114
context to kwargs by @qingyun-wu in #2064
Bump webpack-dev-middleware from 5.3.3 to 5.3.4 in /website by @dependabot in #2131
Parse Any HTML-esh Style Tags by @WaelKarkoub in #2046
Integrate AgentOptimizer by @skzhang1 in #1767
Introducing IOStream protocol and adding support for websockets by @davorrunje in #1551
[CAP] [Feature] Get list of actors from directory service. by @rajan-chari in #2073
Mark cache as a protocol and update type hints to reflect by @jackgerrits in #2168
fix(): fix word spelling errors by @shouldnotappearcalm in #2171
Implement User Defined Functions for Local CLI Executor by @jackgerrits in #2102
simplify getting-started; update news by @sonichi in #2175
update AgentOptimizer docs by @skzhang1 in #2178
Fix formatting of admonitions in udf docs by @jackgerrits in #2188
Fix iostream on new thread by @davorrunje in #2181
Add link for rendering notebooks docs on website by @jackgerrits in #2191

New Contributors

@jamesliu made their first contribution in #2132
@shouldnotappearcalm made their first contribution in #2171

Full Changelog: v0.2.20...v0.2.21

Contributors

jamesliu, ekzhu, and 12 other contributors

Assets 2

21 Mar 00:18

sonichi

v0.2.20

88a71d5

v0.2.20

Highlights

New research: StateFlow - Build LLM Workflows with Customized State-Oriented Transition Function in GroupChat
New feature in contrib: Image Generation Capability
New sample app: Composable Actor Platform for AutoGen
New example added to Gallery: Multimodal Webagent created with AutoGen and OpenAI's Assistants API
AutoGen Studio improvement
- Upload/Dowload of Skills/Workflows
- Streaming Agent Replies
- Agent Message Summarization
- Support Azure AI Search
Documentation improvement
- Tutorial about Tool Use
- Topic about Alternative Models:
- Topic about RAG
- More Notebooks
Improvement of using customized reply functions, nested chat, code execution, GPTAssistantAgent, and AutoGenBench
Bug fix of async multi-chats and async reply functions

Thanks to @kevin666aa @WaelKarkoub @rajan-chari @schauppi @victordibia @ekzhu @Dave2011 @LittleLittleCloud @jackgerrits @davorrunje @qingyun-wu @christianladron @lalo @huskydoge @afourney @IANTHEREAL @cheng-tan @gagb @randombet @abhaymathur21 @panckreous @veh3546 @marklysze and all the other contributors!

What's Changed

added new example in gallery.json by @schauppi in #1955
Rename tutorial chatper "Termination" to "Chat Termination" by @ekzhu in #1962
Redirect from /docs/tutorial/termination to /docs/tutorial/chat-termination by @ekzhu in #1991
Feature: Composable Actor Platform for AutoGen by @rajan-chari in #1655
Rename tutorial chapter: "what is next" --> "what next" by @ekzhu in #1992
fixed typo by @Dave2011 in #1997
[.Net] add release to nuget pipeline by @LittleLittleCloud in #1989
Fix file not being flushed bug by @jackgerrits in #2003
Fix type issues in exception_utils.py by @jackgerrits in #1972
Fix type and default value of the code_execution_config parameter in UserProxyAgent by @davorrunje in #1996
add RAG under topics by @qingyun-wu in #1990
Add extra_body field to LLMConfig dataclass for Azure AI Search support on Autogen studio by @christianladron in #2011
fix: [autogenbench] writing to stdout encoding error in win-os by @lalo in #2002
StateFlow Blog by @kevin666aa in #1826
Update chat-termination.ipynb by @huskydoge in #2019
Update link to AGS repo in AGS blogpost by @victordibia in #2022
refactor: [conversable_agent] remove raise from property access by @lalo in #2006
Bump autogenbench version to 0.0.2 by @afourney in #2027
Add another batch of notebooks to the website by @jackgerrits in #1969
[Feature] Adds Image Generation Capability 2.0 by @WaelKarkoub in #1907
Allow different senders in nested chat by @qingyun-wu in #2028
Autogenstudio Updates [Upload/Dowload of Skills/Workflows, Streaming Agent Replies, Agent Message Summarization] by @victordibia in #1801
Separate openai assistant related config items from llm_config by @IANTHEREAL in #2037
Bump follow-redirects from 1.15.4 to 1.15.6 in /website by @dependabot in #2035
bug fix: fix agent_logging test by @cheng-tan in #2036
Improve doc formatting of initiate_chats by @gagb in #2041
Fix a initiate chats by @randombet in #1938
Request for longer response to make cache test more robust. by @ekzhu in #2043
adjust order of side bars by @sonichi in #2040
code_utils.py powershell command bugfix in MacOS by @abhaymathur21 in #1963
Add docs about how to use docker for when autogen itself is run in docker by @jackgerrits in #2052
Use nested exceptions in get_powershell_command by @jackgerrits in #2058
Update pre-commit by @davorrunje in #2067
Fix typo in conversation-patterns.ipynb by @panckreous in #2066
fix test_human_input by @sonichi in #2063
Resolve types issues in coding by @jackgerrits in #2055
Add LM Studio Example in Topics by @ekzhu in #2044
Encapsulate colored into a module by @jackgerrits in #2057
refactor: [conversable_agent] remove list of func pointers by @lalo in #2005
Fix type issues in openai_utils.py by @jackgerrits in #2062
Pin databind version to fix pydoc-markdown failure in CI by @ekzhu in #2091
Add mypy to pre-commit by @davorrunje in #2068
Add links to roadmap issues from README, Getting-Started, Contribute and Tutorial by @ekzhu in #2072
Bug Fix: Icons centered on homepage by @veh3546 in #2089
Consolidate separate caching docs by @jackgerrits in #2054
Pin databind package versions in gh-release CI by @ekzhu in #2094
Simplify creating a new agent with custom reply function by @sonichi in #2095
Update GitHub actions by @davorrunje in #2078
Add tool use chapter to tutorial by @ekzhu in #2079
[Documentation] Using non-OpenAI models by @marklysze in #2076
Print slow tests in CI by @jackgerrits in #2082
Ignore deprecated files from mypy test by @jackgerrits in #2103

New Contributors

@schauppi made their first contribution in #1955
@rajan-chari made their first contribution in #1655
@Dave2011 made their first contribution in #1997
@christianladron made their first contribution in #2011
@huskydoge made their first contribution in #2019
@panckreous made their first contribution in #2066
@veh3546 made their first contribution in #2089
@marklysze made their first contribution in #2076

Full Changelog: v0.2.19...v0.2.20

Contributors

panckreous, ekzhu, and 23 other contributors

Assets 2

12 Mar 22:48

sonichi

v0.2.19

d583c80

v0.2.19

Highlights

New topics in doc:
Improvement to code executors.
Hotfix to address new numpy prerelease issue.
Bug fix in AutoGenBench.

Thanks to @qingyun-wu @jackgerrits @davorrunje @lalo and all the other contributors!

What's Changed

Require numpy be a 1.x release by @jackgerrits in #1966
Fixes LFS problem with conversable-agent.jpg by @davorrunje in #1974
Remove system message from code executors by @jackgerrits in #1933
bump version to 0.2.19 and update doc by @sonichi in #1971
Remove lint silencing comment by @jackgerrits in #1970
Examples by topics by @qingyun-wu in #1967
Add git-lhs to devcontainers by @davorrunje in #1979
fix: [autogenbench] fails on win-os unless we specify encoding by @lalo in #1957
Update local cli executor to use same filename strategy as docker by @jackgerrits in #1981

New Contributors

@lalo made their first contribution in #1957

Full Changelog: v0.2.18...v0.2.19

Contributors

lalo, sonichi, and 3 other contributors

Assets 2

12 Mar 01:54

sonichi

v0.2.18

11df53b

v0.2.18

Highlights

Support callable message: Example
Adding a tool for fine tuning custom models on conversable agents
Better command line code executor based on Docker
Important doc updates:
- Tutorial
- Notebooks
Bug fix for llm_config, powershell, logging etc.

Thanks to @qingyun-wu @olgavrou @jackgerrits @ekzhu @kevin666aa @rickyloynd-microsoft @cheng-tan @bassmang @WaelKarkoub @RohitRathore1 @bmuskalla @andreyseas @abhaymathur21 and all the other contributors!

What's Changed

Update README of AutoGenBench MATH scenario by @kevin666aa in #1891
Fix printout check for num code blocks by @jackgerrits in #1902
Compressible Agent require model field for llm_config by @kevin666aa in #1903
Implement docker based command line code executor by @jackgerrits in #1856
Accept path for work_dir in LocalCommandLineCodeExecutor by @jackgerrits in #1909
Add warning and reorder jupyter executor docs by @jackgerrits in #1908
Fix broken links by @rickyloynd-microsoft in #1905
Resolve all type issues in cache module by @jackgerrits in #1888
Fix threading issue for logging by @cheng-tan in #1901
Fix formatting in sequential chat notebook by @jackgerrits in #1914
fix: minor fixes and formatting by @bassmang in #1919
Log warning if DiskCache when RedisCache requested by @jackgerrits in #1921
Add initial type check CI by @jackgerrits in #1882
General Enhancements in agentchat 2.0 by @WaelKarkoub in #1906
Adjusts send_introductions Type Hint in GroupChat by @WaelKarkoub in #1912
AutoGen Tutorial by @ekzhu in #1702
Fix remove -> remote by @jackgerrits in #1930
Supporting callable message by @qingyun-wu in #1852
Update more notebooks to be available on the website by @jackgerrits in #1890
Update introduction.ipynb by @sonichi in #1934
Update conversable agent image by @ekzhu in #1939
Update tutorial examples, reference to register_reply. by @ekzhu in #1941
Made a configurable constant by @RohitRathore1 in #1819
Fix branch info for docker build by @bmuskalla in #1935
Move LLM Caching docs to topics by @jackgerrits in #1950
Update documentation for Quarto Version by @kevin666aa in #1951
Fixed simple grammatical mistake by @andreyseas in #1952
Update whisper notebook to use new function registration syntax by @jackgerrits in #1918
In code_utils.py, handling NotADirectoryError as well in get_powershell_command by @abhaymathur21 in #1948
Ability to fine tune custom model on conversable agents by @olgavrou in #1787
improve validation of llm_config by @sonichi in #1946
Make notebooks available in navbar by @jackgerrits in #1956

New Contributors

@bassmang made their first contribution in #1919
@bmuskalla made their first contribution in #1935
@andreyseas made their first contribution in #1952

Full Changelog: v0.2.17...v0.2.18

Contributors

bmuskalla, ekzhu, and 12 other contributors

Assets 2

07 Mar 03:30

sonichi

v0.2.17

c37227b

v0.2.17

Highlights

Summary of recent updates.
Support customized speaker selection method: example.
Improvement in nested chats and code execution.
Improvement in doc, notebooks and docker file.
Bug fix for clear history and custom client.
Fix message processing order for proper combination of agent capabilities.

Thanks to @kevin666aa @ekzhu @jackgerrits @GregorD1A1 @KazooTTT @swiecki @truebit and all the other contributors!

What's Changed

Remove default trigger value for register_nested_chats by @ekzhu in #1833
Split apart ecosystem page, update sidebar, other website tweaks by @jackgerrits in #1812
Upgrade Quarto and use notebook metadata for frontmatter by @jackgerrits in #1836
Fix for bugs appeared when using function calls with clear history functionality by @GregorD1A1 in #1531
revert quarto upgrade by @jackgerrits in #1840
adjust the order of message processing by @sonichi in #1841
add doc about effects for capabilities by @sonichi in #1842
Upgrade quarto and include mitigation for title issue, fix links by @jackgerrits in #1851
Create topics dir and move llm config by @jackgerrits in #1853
Raise errors if incompatible args are used with an executor by @jackgerrits in #1855
Add documentation for jupyter code executor by @jackgerrits in #1809
summary of recent updates by @sonichi in #1850
Small edits to update blog post by @jackgerrits in #1869
Fix docs for. EmbeddedIPythonCodeExecutor by @jackgerrits in #1871
Resolve warning on port binding by @jackgerrits in #1870
Move executor diag print to conversable_agent by @jackgerrits in #1867
Change name from LocalCommandlineCodeExecutor to LocalCommandLineCodeExecutor by @jackgerrits in #1873
fix: update the docs link by @KazooTTT in #1879
Fix devcontainer Dockerfile for arm by @jackgerrits in #1866
Resolve type issues in redis cache by @jackgerrits in #1872
UPDATE: Fixed broken examples links by @swiecki in #1886
Add test to confirm that executor timeout preserves kernel state by @jackgerrits in #1885
Add annoucement bar for what's new blog post by @jackgerrits in #1884
fix ModelClient create function signature error by @truebit in #1865
Fix issue with git checkout main by @ekzhu in #1876
Download lfs in website build by @jackgerrits in #1894
Allow user to pass in a customized speaker selection method by @kevin666aa in #1791

New Contributors

@swiecki made their first contribution in #1886
@truebit made their first contribution in #1865

Full Changelog: v0.2.16...v0.2.17

Contributors

ekzhu, swiecki, and 6 other contributors

Assets 2

01 Mar 05:21

sonichi

v0.2.16

0a49f2a

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

Contributors

victordibia, freedeaths, and 11 other contributors

Assets 2

25 Feb 17:41

sonichi

v0.2.15

8ec1c3e

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

Contributors

dkirsche, thinkall, and 13 other contributors

Assets 2

16 Feb 07:11

sonichi

v0.2.14

7ceee5d

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

Contributors

bobbravo2, sonichi, and 13 other contributors

Assets 2

Releases: microsoft/autogen

v0.2.23

Highlights

What's Changed

New Contributors

Contributors

v0.2.22

Highlights

What's Changed

New Contributors

Contributors

v0.2.21

Highlights

What's Changed

New Contributors

Contributors

v0.2.20

Highlights

What's Changed

New Contributors

Contributors

v0.2.19

Highlights

What's Changed

New Contributors

Contributors

v0.2.18

Highlights

What's Changed

New Contributors

Contributors

v0.2.17

Highlights

What's Changed

New Contributors

Contributors

v0.2.16

Highlights

What's Changed

New Contributors

Contributors

v0.2.15

Highlights

What's Changed

New Contributors

Contributors

v0.2.14

Highlights

What's Changed

New Contributors

Contributors