Prepare for a roller coaster ride of innovation with the launch of FLAML v2.0.0! This is not just another update but a culmination of numerous enhancements, novel features, and exciting improvements we've made from v2.0.0rc1 to v2.0.0rc5, leading to the grand v2.0.0 release.
- With v2.0.0rc1, we embarked on a major refactor with the creation of an [automl] option to declutter dependencies for
autogenandtune. - In v2.0.0rc2, we supercharged FLAML with support for new OpenAI gpt-3.5-turbo and gpt-4 models in
autogenand rolled out the extensibility of autogen agents. - With v2.0.0rc3, we upped the ante by adding new OpenAI models' support of functions in agents and provided a handy code example in a dedicated notebook.
- v2.0.0rc4 brought a host of improvements to the
agentchatframework, enabling many new applications. - v2.0.0rc5 pushed the boundaries further by making auto-reply methods pluggable and supporting an asynchronous mode in agents.
Finally, we arrive at the grand v2.0.0 release! This version boasts of numerous feature enhancements in autogen, like multi-agent chat framework (in preview), expanded OpenAI model support, enhanced integration with Spark, and much more.
Documentation for AutoGen: https://microsoft.github.io/FLAML/docs/Use-Cases/Autogen
Examples: https://microsoft.github.io/FLAML/docs/Examples/AutoGen-AgentChat
Blogposts: https://microsoft.github.io/FLAML/blog
A huge shoutout to @qingyun-wu @kevin666aa @skzhang1 @ekzhu @BeibinLi @thinkall @LittleLittleCloud @JieyuZ2 @gagb @EgorKraevTransferwise @markharley @int-chaos @levscaut @feiran-jia @liususan091219 @royninja @pcdeadeasy as well as our new contributors @badjouras, @LeoLjl, @xiaoboxia, and @minghao51 who joined us during this journey. Your contributions have played a pivotal role in shaping this release.
What's Changed
- Blogpost for adaptation in HumanEval by @sonichi in #1048
- Improve messaging in documentation by @sonichi in #1050
- create an automl option to remove unnecessary dependency for autogen and tune by @sonichi in #1007
- docs: 📝 Fix link to installation section in Task-Oriented-AutoML.md by @badjouras in #1051
- doc and test update by @sonichi in #1053
- remove redundant doc and add tutorial by @qingyun-wu in #1004
- add agent notebook and documentation by @qingyun-wu in #1052
- Support more azure openai api_type by @thinkall in #1059
- suppress warning message of pandas_on_spark to_spark by @thinkall in #1058
- Agent notebook example with human feedback; Support shell command and multiple code blocks; Improve the system message for assistant agent; Improve utility functions for config lists; reuse docker image by @sonichi in #1056
- Fix documentation by @sonichi in #1075
- encode timeout msg in bytes by @sonichi in #1078
- Add pands requirement in benchmark option by @qingyun-wu in #1070
- Fix pyspark tests in workflow by @thinkall in #1071
- Docmentation for agents by @qingyun-wu in #1057
- Links to papers by @sonichi in #1084
- update openai model support by @sonichi in #1082
- string to array by @sonichi in #1086
- Factor out time series-related functionality into a time series Task object by @EgorKraevTransferwise in #989
- An agent implementation of MathChat by @kevin666aa in #1090
- temp solution for joblib 1.3.0 issue by @thinkall in #1100
- support string alg in tune by @skzhang1 in #1093
- update flaml version in MathChat notebook by @kevin666aa in #1095
- doc update by @sonichi in #1089
- Update OptunaSearch by @skzhang1 in #1106
- Support function_call in
autogen/agentby @kevin666aa in #1091 - update notebook with new models by @sonichi in #1112
- Enhance Integration with Spark by @levscaut in #1097
- Add Funccall notebook and document by @kevin666aa in #1110
- Update docstring for oai.completion. by @LeoLjl in #1113
- Try to prevent the default AssistantAgent from asking users to modify the code by @sonichi in #1114
- update colab link by @sonichi in #1118
- fix bug in math_user_proxy_agent by @kevin666aa in #1124
- Add log metric by @thinkall in #1125
- Update assistant agent by @sonichi in #1121
- suppress printing data split type by @xiaoboxia in #1126
- change price ratio by @sonichi in #1130
- simplify the initiation of chat by @sonichi in #1131
- Update docs on how to interact with local LLM by @LeoLjl in #1128
- Json config list, agent refactoring and new notebooks by @sonichi in #1133
- unify auto_reply; bug fix in UserProxyAgent; reorg agent hierarchy by @sonichi in #1142
- rename GenericAgent -> ResponsiveAgent by @sonichi in #1146
- Bump semver from 5.7.1 to 5.7.2 in /website by @dependabot in #1119
- autogen.agent -> autogen.agentchat by @sonichi in #1148
- MathChat blog post by @kevin666aa in #1096
- Commenting use_label_encoder - xgboost by @minghao51 in #1122
- raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; configurable default reply by @sonichi in #1154
- consecutive auto reply, history, template, group chat, class-specific reply by @sonichi in #1165
- Improve auto reply registration by @sonichi in #1170
- Make auto reply method pluggable by @sonichi in #1177
- support async in agents by @sonichi in #1178
- Updated README.md with installation Link by @royninja in #1180
- Add RetrieveChat by @thinkall in #1158
- silent; code_execution_config; exit; version by @sonichi in #1179
New Contributors
- @badjouras made their first contribution in #1051
- @kevin666aa made their first contribution in #1090
- @LeoLjl made their first contribution in #1113
- @xiaoboxia made their first contribution in #1126
- @minghao51 made their first contribution in #1122
Full Changelog: v1.2.4...v2.0.0