FLAML Versions Save

What's Changed

• Update README.md with autogen links by @aindree-2005 in https://github.com/microsoft/FLAML/pull/1235
• Bump postcss from 8.4.18 to 8.4.31 in /website by @dependabot in https://github.com/microsoft/FLAML/pull/1238
• Bump @babel/traverse from 7.20.1 to 7.23.2 in /website by @dependabot in https://github.com/microsoft/FLAML/pull/1248
• [ENH] Add support for sklearn HistGradientBoostingEstimator by @glevv in https://github.com/microsoft/FLAML/pull/1230
• Update Installation.md (for a Typo) by @ScottzCodez in https://github.com/microsoft/FLAML/pull/1258
• Fix spark errors by @thinkall in https://github.com/microsoft/FLAML/pull/1274
• docs: fix link to reference by @Borda in https://github.com/microsoft/FLAML/pull/1263
• Update AutoML-NLP.md by @dhruvthakur2000 in https://github.com/microsoft/FLAML/pull/1239
• Don't specify a pre-release in the numpy dependency by @jackgerrits in https://github.com/microsoft/FLAML/pull/1286
• Np.inf by @sonichi in https://github.com/microsoft/FLAML/pull/1289
• Bump follow-redirects from 1.15.2 to 1.15.4 in /website by @dependabot in https://github.com/microsoft/FLAML/pull/1266
• Add ruff sort to pre-commit and sort imports in the library by @glevv in https://github.com/microsoft/FLAML/pull/1259

New Contributors

• @aindree-2005 made their first contribution in https://github.com/microsoft/FLAML/pull/1235
• @glevv made their first contribution in https://github.com/microsoft/FLAML/pull/1230
• @ScottzCodez made their first contribution in https://github.com/microsoft/FLAML/pull/1258
• @dhruvthakur2000 made their first contribution in https://github.com/microsoft/FLAML/pull/1239
• @jackgerrits made their first contribution in https://github.com/microsoft/FLAML/pull/1286

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.1.1...v2.1.2

This release adds support for xgboost 2.0, and improves the docstr of preprocessors. Welcome @domoritz to the community!

What's Changed

• support xgboost 2.0 by @sonichi in https://github.com/microsoft/FLAML/pull/1219
• fix ref to research by @domoritz in https://github.com/microsoft/FLAML/pull/1218
• Fix typo Whetehr -> Whether by @domoritz in https://github.com/microsoft/FLAML/pull/1220
• Update autogen links by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1214
• improve docstr of preprocessors by @sonichi in https://github.com/microsoft/FLAML/pull/1227

New Contributors

• @domoritz made their first contribution in https://github.com/microsoft/FLAML/pull/1218

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.1.0...v2.1.1

This update renames a few classes and methods.

What's Changed

• Migration headsup by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1204
• group chat for visualization by @sonichi in https://github.com/microsoft/FLAML/pull/1213
• rename human to user_proxy by @sonichi in https://github.com/microsoft/FLAML/pull/1215
• Rename Responsive -> Conversable by @sonichi in https://github.com/microsoft/FLAML/pull/1202

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.3...v2.1.0

This release adds support for model name suffix "-0613" and allows admin takeover in the group chat, plus a more complex group chat example. Thanks @qingyun-wu @LeoLjl @JieyuZ2 @skzhang1 @pcdeadeasy @LittleLittleCloud for code review.

What's Changed

• suffix in model name by @sonichi in https://github.com/microsoft/FLAML/pull/1206
• fix typo by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1210
• admin takeover in group chat by @sonichi in https://github.com/microsoft/FLAML/pull/1209

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.2...v2.0.3

This release contains an improvement to the assistant agent prompt, and doc update. Thanks @thinkall for the contribution and @BeibinLi @qingyun-wu @kevin666aa for reviewing and testing.

What's Changed

• Update readme and AutoGen docs by @thinkall in https://github.com/microsoft/FLAML/pull/1183
• Prompt improvement by @sonichi in https://github.com/microsoft/FLAML/pull/1203

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.1...v2.0.2

This release contains prompt improvement and bug fix. In the next version, we will rename ResponsiveAgent to ConversableAgent.

Thanks @kevin666aa for the contribution, and @skzhang1 @LittleLittleCloud @JieyuZ2 @gagb for reviewing.

What's Changed

• Cover function calls with no arguments by @kevin666aa in https://github.com/microsoft/FLAML/pull/1185
• fix generate_reply when sender is None. by @kevin666aa in https://github.com/microsoft/FLAML/pull/1186
• prompt improvement by @sonichi in https://github.com/microsoft/FLAML/pull/1188
• document response fields by @sonichi in https://github.com/microsoft/FLAML/pull/1199

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.0...v2.0.1

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 autogen and tune.
• In v2.0.0rc2, we supercharged FLAML with support for new OpenAI gpt-3.5-turbo and gpt-4 models in autogen and 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 agentchat framework, 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 https://github.com/microsoft/FLAML/pull/1048
• Improve messaging in documentation by @sonichi in https://github.com/microsoft/FLAML/pull/1050
• create an automl option to remove unnecessary dependency for autogen and tune by @sonichi in https://github.com/microsoft/FLAML/pull/1007
• docs: 📝 Fix link to installation section in Task-Oriented-AutoML.md by @badjouras in https://github.com/microsoft/FLAML/pull/1051
• doc and test update by @sonichi in https://github.com/microsoft/FLAML/pull/1053
• remove redundant doc and add tutorial by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1004
• add agent notebook and documentation by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1052
• Support more azure openai api_type by @thinkall in https://github.com/microsoft/FLAML/pull/1059
• suppress warning message of pandas_on_spark to_spark by @thinkall in https://github.com/microsoft/FLAML/pull/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 https://github.com/microsoft/FLAML/pull/1056
• Fix documentation by @sonichi in https://github.com/microsoft/FLAML/pull/1075
• encode timeout msg in bytes by @sonichi in https://github.com/microsoft/FLAML/pull/1078
• Add pands requirement in benchmark option by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1070
• Fix pyspark tests in workflow by @thinkall in https://github.com/microsoft/FLAML/pull/1071
• Docmentation for agents by @qingyun-wu in https://github.com/microsoft/FLAML/pull/1057
• Links to papers by @sonichi in https://github.com/microsoft/FLAML/pull/1084
• update openai model support by @sonichi in https://github.com/microsoft/FLAML/pull/1082
• string to array by @sonichi in https://github.com/microsoft/FLAML/pull/1086
• Factor out time series-related functionality into a time series Task object by @EgorKraevTransferwise in https://github.com/microsoft/FLAML/pull/989
• An agent implementation of MathChat by @kevin666aa in https://github.com/microsoft/FLAML/pull/1090
• temp solution for joblib 1.3.0 issue by @thinkall in https://github.com/microsoft/FLAML/pull/1100
• support string alg in tune by @skzhang1 in https://github.com/microsoft/FLAML/pull/1093
• update flaml version in MathChat notebook by @kevin666aa in https://github.com/microsoft/FLAML/pull/1095
• doc update by @sonichi in https://github.com/microsoft/FLAML/pull/1089
• Update OptunaSearch by @skzhang1 in https://github.com/microsoft/FLAML/pull/1106
• Support function_call in autogen/agent by @kevin666aa in https://github.com/microsoft/FLAML/pull/1091
• update notebook with new models by @sonichi in https://github.com/microsoft/FLAML/pull/1112
• Enhance Integration with Spark by @levscaut in https://github.com/microsoft/FLAML/pull/1097
• Add Funccall notebook and document by @kevin666aa in https://github.com/microsoft/FLAML/pull/1110
• Update docstring for oai.completion. by @LeoLjl in https://github.com/microsoft/FLAML/pull/1113
• Try to prevent the default AssistantAgent from asking users to modify the code by @sonichi in https://github.com/microsoft/FLAML/pull/1114
• update colab link by @sonichi in https://github.com/microsoft/FLAML/pull/1118
• fix bug in math_user_proxy_agent by @kevin666aa in https://github.com/microsoft/FLAML/pull/1124
• Add log metric by @thinkall in https://github.com/microsoft/FLAML/pull/1125
• Update assistant agent by @sonichi in https://github.com/microsoft/FLAML/pull/1121
• suppress printing data split type by @xiaoboxia in https://github.com/microsoft/FLAML/pull/1126
• change price ratio by @sonichi in https://github.com/microsoft/FLAML/pull/1130
• simplify the initiation of chat by @sonichi in https://github.com/microsoft/FLAML/pull/1131
• Update docs on how to interact with local LLM by @LeoLjl in https://github.com/microsoft/FLAML/pull/1128
• Json config list, agent refactoring and new notebooks by @sonichi in https://github.com/microsoft/FLAML/pull/1133
• unify auto_reply; bug fix in UserProxyAgent; reorg agent hierarchy by @sonichi in https://github.com/microsoft/FLAML/pull/1142
• rename GenericAgent -> ResponsiveAgent by @sonichi in https://github.com/microsoft/FLAML/pull/1146
• Bump semver from 5.7.1 to 5.7.2 in /website by @dependabot in https://github.com/microsoft/FLAML/pull/1119
• autogen.agent -> autogen.agentchat by @sonichi in https://github.com/microsoft/FLAML/pull/1148
• MathChat blog post by @kevin666aa in https://github.com/microsoft/FLAML/pull/1096
• Commenting use_label_encoder - xgboost by @minghao51 in https://github.com/microsoft/FLAML/pull/1122
• raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; configurable default reply by @sonichi in https://github.com/microsoft/FLAML/pull/1154
• consecutive auto reply, history, template, group chat, class-specific reply by @sonichi in https://github.com/microsoft/FLAML/pull/1165
• Improve auto reply registration by @sonichi in https://github.com/microsoft/FLAML/pull/1170
• Make auto reply method pluggable by @sonichi in https://github.com/microsoft/FLAML/pull/1177
• support async in agents by @sonichi in https://github.com/microsoft/FLAML/pull/1178
• Updated README.md with installation Link by @royninja in https://github.com/microsoft/FLAML/pull/1180
• Add RetrieveChat by @thinkall in https://github.com/microsoft/FLAML/pull/1158
• silent; code_execution_config; exit; version by @sonichi in https://github.com/microsoft/FLAML/pull/1179

New Contributors

• @badjouras made their first contribution in https://github.com/microsoft/FLAML/pull/1051
• @kevin666aa made their first contribution in https://github.com/microsoft/FLAML/pull/1090
• @LeoLjl made their first contribution in https://github.com/microsoft/FLAML/pull/1113
• @xiaoboxia made their first contribution in https://github.com/microsoft/FLAML/pull/1126
• @minghao51 made their first contribution in https://github.com/microsoft/FLAML/pull/1122

Full Changelog: https://github.com/microsoft/FLAML/compare/v1.2.4...v2.0.0

This version makes auto-reply methods pluggable and supports asynchronous mode in agents. An example of handling data steams is added. Thanks to @qingyun-wu @ekzhu for laying the foundation and reviewing!

What's Changed

• Make auto reply method pluggable by @sonichi in https://github.com/microsoft/FLAML/pull/1177
• support async in agents by @sonichi in https://github.com/microsoft/FLAML/pull/1178

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.0rc4...v2.0.0rc5

This pre-release makes lots of improvements in the agentchat framework. Many new applications are enabled. Thanks @JieyuZ2 @gagb @thinkall @BeibinLi @ekzhu @LittleLittleCloud @kevin666aa @qingyun-wu @LeoLjl and others for your contributions!

What's Changed

• update colab link by @sonichi in https://github.com/microsoft/FLAML/pull/1118
• fix bug in math_user_proxy_agent by @kevin666aa in https://github.com/microsoft/FLAML/pull/1124
• Add log metric by @thinkall in https://github.com/microsoft/FLAML/pull/1125
• Update assistant agent by @sonichi in https://github.com/microsoft/FLAML/pull/1121
• suppress printing data split type by @xiaoboxia in https://github.com/microsoft/FLAML/pull/1126
• change price ratio by @sonichi in https://github.com/microsoft/FLAML/pull/1130
• simplify the initiation of chat by @sonichi in https://github.com/microsoft/FLAML/pull/1131
• Update docs on how to interact with local LLM by @LeoLjl in https://github.com/microsoft/FLAML/pull/1128
• Json config list, agent refactoring and new notebooks by @sonichi in https://github.com/microsoft/FLAML/pull/1133
• unify auto_reply; bug fix in UserProxyAgent; reorg agent hierarchy by @sonichi in https://github.com/microsoft/FLAML/pull/1142
• rename GenericAgent -> ResponsiveAgent by @sonichi in https://github.com/microsoft/FLAML/pull/1146
• Bump semver from 5.7.1 to 5.7.2 in /website by @dependabot in https://github.com/microsoft/FLAML/pull/1119
• autogen.agent -> autogen.agentchat by @sonichi in https://github.com/microsoft/FLAML/pull/1148
• MathChat blog post by @kevin666aa in https://github.com/microsoft/FLAML/pull/1096
• Commenting use_label_encoder - xgboost by @minghao51 in https://github.com/microsoft/FLAML/pull/1122
• raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; configurable default reply by @sonichi in https://github.com/microsoft/FLAML/pull/1154
• consecutive auto reply, history, template, group chat, class-specific reply by @sonichi in https://github.com/microsoft/FLAML/pull/1165
• Improve auto reply registration by @sonichi in https://github.com/microsoft/FLAML/pull/1170

New Contributors

• @xiaoboxia made their first contribution in https://github.com/microsoft/FLAML/pull/1126
• @minghao51 made their first contribution in https://github.com/microsoft/FLAML/pull/1122

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.0rc3...v2.0.0rc4

Highlights

Added new OpenAI models' support of functions in agents. Thanks to @kevin666aa, @sonichi and @qingyun-wu Please find a code example in this notebook: https://github.com/microsoft/FLAML/blob/main/notebook/autogen_agent_function_call.ipynb

What's Changed

• temp solution for joblib 1.3.0 issue by @thinkall in https://github.com/microsoft/FLAML/pull/1100
• support string alg in tune by @skzhang1 in https://github.com/microsoft/FLAML/pull/1093
• update flaml version in MathChat notebook by @kevin666aa in https://github.com/microsoft/FLAML/pull/1095
• doc update by @sonichi in https://github.com/microsoft/FLAML/pull/1089
• Update OptunaSearch by @skzhang1 in https://github.com/microsoft/FLAML/pull/1106
• Support function_call in autogen/agent by @kevin666aa in https://github.com/microsoft/FLAML/pull/1091
• update notebook with new models by @sonichi in https://github.com/microsoft/FLAML/pull/1112
• Enhance Integration with Spark by @levscaut in https://github.com/microsoft/FLAML/pull/1097
• Add Funccall notebook and document by @kevin666aa in https://github.com/microsoft/FLAML/pull/1110
• Update docstring for oai.completion. by @LeoLjl in https://github.com/microsoft/FLAML/pull/1113
• Try to prevent the default AssistantAgent from asking users to modify the code by @sonichi in https://github.com/microsoft/FLAML/pull/1114

New Contributors

• @LeoLjl made their first contribution in https://github.com/microsoft/FLAML/pull/1113

Full Changelog: https://github.com/microsoft/FLAML/compare/v2.0.0rc2...v2.0.0rc3