Jirka Borovec
b348cb1136
configure & apply pyupgrade with py3.8+ ( #1333 )
...
* configure pyupgrade with `py3.8+`
* apply update
---------
Co-authored-by: Li Jiang <bnujli@gmail.com >
2024-08-12 02:54:18 +00:00
Jirka Borovec
cd0e88e383
fix missing req. arg for new datasets package ( #1334 )
...
Co-authored-by: Li Jiang <bnujli@gmail.com >
2024-08-12 02:19:11 +00:00
Gleb Levitski
3de0dc667e
Add ruff sort to pre-commit and sort imports in the library ( #1259 )
...
* lint
* bump ver
* bump ver
* fixed circular import
---------
Co-authored-by: Jirka Borovec <6035284+Borda@users.noreply.github.com >
2024-03-12 21:28:57 +00:00
Chi Wang
4886cb5689
Rename Responsive -> Conversable ( #1202 )
...
* responsive -> conversable
* preview
* rename
* register reply
* rename and version
* bump version to 2.1.0
* notebook
* bug fix
2023-09-12 00:07:35 +00:00
Chi Wang
5f9b514be7
suffix in model name ( #1206 )
...
* suffix in model name
* bump version to 2.0.3
2023-09-04 02:32:51 +00:00
Yiran Wu
87c2361040
fix generate_reply when sender is None. ( #1186 )
...
* fix generate_reply
* code format
* add test case
* update
* update
* Update test/autogen/agentchat/test_responsive_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update test/autogen/agentchat/test_responsive_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update flaml/autogen/agentchat/responsive_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2023-08-25 10:50:22 +00:00
Yiran Wu
07b97eb469
cover function calls with no arguments ( #1185 )
2023-08-20 05:28:29 +00:00
Chi Wang
7ab4d114d7
silent; code_execution_config; exit; version ( #1179 )
...
* silent; code_execution_config; exit; version
* url
* url
* readme
* preview
* doc
* url
* endpoints
* timeout
* chess
* Fix retrieve chat
* config
* mathchat
---------
Co-authored-by: Li Jiang <bnujli@gmail.com >
2023-08-14 07:09:45 +00:00
Li Jiang
700ff05874
Add RetrieveChat ( #1158 )
...
* Add RetrieveChat notebook, RetrieveAssistantAgent and RetrieveUserProxyAgent
* Update according to comments
* Add output
* Add tests, merge main, address comments
* Fix tests
* Merge main
* Remove unnecessary code
* Update test
* Update notebook, some functions
* Fix print issue
* Update notebook
* Update notebook
* Update notebook
* Improve retrieve utils and update notebook
* Update vector db creation method
* Update notebook
* Update notebook
* Add terminate if no more context
* Update prompt and notebook, add example for update context
* Update results
* Update results
* Update results of update context
* Fix typo
* Add table of contents
* Update table of contents
2023-08-13 12:51:54 +00:00
Chi Wang
c44d2f4a01
support async in agents ( #1178 )
...
* Make auto reply method pluggable
* support async
* async
* allow richer trigger types
* test list
* rename key
2023-08-08 01:34:47 +00:00
Chi Wang
a603e6dddc
Make auto reply method pluggable ( #1177 )
...
* Make auto reply method pluggable
* allow richer trigger types
* test list
2023-08-07 18:41:58 +00:00
Chi Wang
2208dfb79e
Improve auto reply registration ( #1170 )
...
* Improve auto reply registration
* object key
* fix test error
* bug fix in math user proxy agent
* allow send/receive without reply
* reset -> stop
2023-08-04 14:26:58 +00:00
Chi Wang
45b7d908e4
consecutive auto reply, history, template, group chat, class-specific reply ( #1165 )
...
* max consecutive auto reply
* chess notebook
* link to notebook
* clear history
* filter
* **context -> context
* format str template
* groupchat
* register class specific reply
* groupchat notebook
* move human reply into generate_reply
* arg in config
* colab link
* remove room
* rename
2023-08-03 09:17:20 +00:00
Chi Wang
c48babd02f
raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; find code blocks with llm when regex fails. ( #1154 )
...
* autogen.agent -> autogen.agentchat
* bug fix in portfolio
* notebook
* timeout
* timeout
* infer lang; close #1150
* timeout
* message context
* context handling
* add sender to generate_reply
* clean up the receive function
* move mathchat to contrib
* contrib
* last_message
* Add OptiGuide: agent and notebook
* Optiguide notebook: add figures and URL
1. figures and code points to remote URL
2. simplify the prompt for the interpreter, because
all information is already in the chat history.
* Update name: Agent -> GenericAgent
* Update notebook
* Rename: GenericAgent -> ResponsiveAgent
* Rebase to autogen.agentchat
* OptiGuide: Comment, sytle, and notebook updates
* simplify optiguide
* raise error when msg is invalid; fix docstr
* allow return None for generate_reply()
* update_system_message
* test update_system_message
* simplify optiguide
* simplify optiguide
* simplify optiguide
* simplify optiguide
* move test
* add test and fix bug
* doc update
* doc update
* doc update
* color
* optiguide
* prompt
* test danger case
* packaging
* docker
* remove path in traceback
* capture ipython output
* simplify
* find code blocks with llm
* find code with llm
* order
* order
* fix bug in context handling
* print executing msg
* print executing msg
* test find code
* test find code
* disable find_code
* default_auto_reply
* default auto reply
* remove optiguide
* remove -e
---------
Co-authored-by: Beibin Li <beibin79@gmail.com >
2023-08-01 02:22:30 +00:00
Chi Wang
7ddb171cd9
autogen.agent -> autogen.agentchat ( #1148 )
...
* autogen.agent -> autogen.agentchat
* bug fix in portfolio
* notebook
* timeout
* timeout
* infer lang; close #1150
* timeout
* message context
* context handling
* add sender to generate_reply
* clean up the receive function
* move mathchat to contrib
* contrib
* last_message
2023-07-29 04:17:51 +00:00
Chi Wang
ecf51f41bb
rename GenericAgent -> ResponsiveAgent ( #1146 )
...
* rename GenericAgent -> ResponsiveAgent
* always
2023-07-26 05:22:25 +00:00
Chi Wang
3e7aac6e8b
unify auto_reply; bug fix in UserProxyAgent; reorg agent hierarchy ( #1142 )
...
* simplify the initiation of chat
* version update
* include openai
* completion
* load config list from json
* initiate_chat
* oai config list
* oai config list
* config list
* config_list
* raise_error
* retry_time
* raise condition
* oai config list
* catch file not found
* catch openml error
* handle openml error
* handle openml error
* handle openml error
* handle openml error
* handle openml error
* handle openml error
* close #1139
* use property
* termination msg
* AIUserProxyAgent
* smaller dev container
* update notebooks
* match
* document code execution and AIUserProxyAgent
* gpt 3.5 config list
* rate limit
* variable visibility
* remove unnecessary import
* quote
* notebook comments
* remove mathchat from init import
* two users
* import location
* expose config
* return str not tuple
* rate limit
* ipython user proxy
* message
* None result
* rate limit
* rate limit
* rate limit
* rate limit
* make auto_reply a common method for all agents
* abs path
* refactor and doc
* set mathchat_termination
* code format
* modified
* emove import
* code quality
* sender -> messages
* system message
* clean agent hierarchy
* dict check
* invalid oai msg
* return
* openml error
* docstr
---------
Co-authored-by: kevin666aa <yrwu000627@gmail.com >
2023-07-25 23:46:11 +00:00
Chi Wang
2406e69496
Json config list, agent refactoring and new notebooks ( #1133 )
...
* simplify the initiation of chat
* version update
* include openai
* completion
* load config list from json
* initiate_chat
* oai config list
* oai config list
* config list
* config_list
* raise_error
* retry_time
* raise condition
* oai config list
* catch file not found
* catch openml error
* handle openml error
* handle openml error
* handle openml error
* handle openml error
* handle openml error
* handle openml error
* close #1139
* use property
* termination msg
* AIUserProxyAgent
* smaller dev container
* update notebooks
* match
* document code execution and AIUserProxyAgent
* gpt 3.5 config list
* rate limit
* variable visibility
* remove unnecessary import
* quote
* notebook comments
* remove mathchat from init import
* two users
* import location
* expose config
* return str not tuple
* rate limit
* ipython user proxy
* message
* None result
* rate limit
* rate limit
* rate limit
* rate limit
2023-07-23 13:23:09 +00:00
Chi Wang
16f0fcd6f8
simplify the initiation of chat ( #1131 )
...
* simplify the initiation of chat
* version update
* include openai
* completion
2023-07-18 03:40:41 +00:00
Chi Wang
297a1ea9e0
Update assistant agent ( #1121 )
...
* update colab link
* typo
* upload file instruction
* update system message and notebooks
* update notebooks
* notebook test
* aoai api version and exclusion
* gpt-3.5-turbo
* dict check
* change model for test
* endpoints, cache_path and func description update
* model list
* gitter -> discord
2023-07-14 22:52:45 +00:00
Chi Wang
784c4c4f86
Try to prevent the default AssistantAgent from asking users to modify the code ( #1114 )
...
* inform assistant agent:
user proxy agent can't modify code
* update notebooks
* configure timeout in UserProxyAgent
---------
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
2023-07-10 16:07:48 +00:00
Yiran Wu
255faf97e2
Add Funccall notebook and document ( #1110 )
...
* add funccall example and doc
* revise to comments
* Update website/docs/Use-Cases/Auto-Generation.md
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* revise
* update
* minor update
* add test notebook
* update
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2023-07-10 04:56:07 +00:00
Yiran Wu
ca10b286cc
Support function_call in autogen/agent ( #1091 )
...
* update funccall
* code format
* update to comments
* update notebook
* remove test for py3.7
* allow funccall to class functions
* add test and clean up notebook
* revise notebook and test
* update
* update mathagent
* Update flaml/autogen/agent/agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update flaml/autogen/agent/user_proxy_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* revise to comments
* revise function call design, notebook and test. add doc
* code format
* ad message_to_dict function
* update mathproxyagent
* revise docstr
* update
* Update flaml/autogen/agent/math_user_proxy_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update flaml/autogen/agent/math_user_proxy_agent.py
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
* Update flaml/autogen/agent/user_proxy_agent.py
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
* simply funccall in userproxyagent, rewind auto-gen.md, revise to comments
* code format
* update
* remove notebook for another pr
* revise oai_conversation part in agent, revise function exec in user_proxy_agent
* update test_funccall
* update
* update
* fix pydantic version
* Update test/autogen/test_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* fix bug
* fix bug
* update
* update is_termination_msg to accept dict
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
Co-authored-by: Li Jiang <bnujli@gmail.com >
2023-07-05 22:08:44 +00:00
Chi Wang
4f1dfe6676
doc update ( #1089 )
...
* doc update
* add link to mathchat notebook
* use_docker property
* function name
* version update
---------
Co-authored-by: kevin666aa <yrwu000627@gmail.com >
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
2023-07-04 20:29:32 +00:00
Yiran Wu
e3ca95bf8a
An agent implementation of MathChat ( #1090 )
...
* mathcaht implementation
* code forrmat
* update readme
* update openai.yml
* update openai.yml
* update openai.yml
2023-06-25 13:49:34 +00:00
Chi Wang
8760631349
string to array ( #1086 )
...
* string to array
* exclude aoai
2023-06-17 13:11:22 +00:00
Chi Wang
e1da7f7d68
update openai model support ( #1082 )
...
* update openai model support
* new gpt3.5
* docstr
* function_call and content may co-exist
* test function call
---------
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
2023-06-16 00:58:44 +00:00
Qingyun Wu
0c7082c7bf
Docmentation for agents ( #1057 )
...
* add agent notebook and documentation
* fix bug
* set flush to True when printing msg in agent
* add a math problem in agent notebook
* remove
* header
* improve notebook doc
* notebook update
* improve notebook example
* improve doc
* improve notebook doc
* improve print
* doc
* human_input_mode
* human_input_mode str
* indent
* indent
* Update flaml/autogen/agent/user_proxy_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update notebook/autogen_agent.ipynb
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update notebook/autogen_agent.ipynb
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update notebook/autogen_agent.ipynb
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* add agent doc
* del old files
* remove chat
* agent doc
* remove chat_agent
* naming
* improve documentation
* wording
* improve agent doc
* wording
* general auto reply
* update agent doc
* human input mode
* add agent figure
* update agent figure
* update agent example figure
* update code example
* extensibility of UserProxyAgent
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2023-06-14 23:56:13 +00:00
Chi Wang
c5dfb03f0e
encode timeout msg in bytes ( #1078 )
...
* encode timeout msg in bytes
* fix msg and test
2023-06-12 18:07:14 +00:00
Chi Wang
5387a0a607
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 ( #1056 )
...
* add agent notebook and documentation
* fix bug
* set flush to True when printing msg in agent
* add a math problem in agent notebook
* remove
* header
* improve notebook doc
* notebook update
* improve notebook example
* improve doc
* agent notebook example with user feedback
* log
* log
* improve notebook doc
* improve print
* doc
* human_input_mode
* human_input_mode str
* indent
* indent
* Update flaml/autogen/agent/user_proxy_agent.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* shell command and multiple code blocks
* Update notebook/autogen_agent.ipynb
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update notebook/autogen_agent.ipynb
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* Update notebook/autogen_agent.ipynb
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
* coding agent
* math notebook
* renaming and doc format
* typo
* infer lang
* sh
* docker
* docker
* reset consecutive autoreply counter
* fix explanation
* paper talk
* human feedback
* web info
* rename test
* config list explanation
* link to blogpost
* installation
* homepage features
* features
* features
* rename agent
* remove notebook
* notebook test
* docker command
* notebook update
* lang -> cmd
* notebook
* make it work for gpt-3.5
* return full log
* quote
* docker
* docker
* docker
* docker
* docker
* docker image list
* notebook
* notebook
* use_docker
* use_docker
* use_docker
* doc
* agent
* doc
* abs path
* pandas
* docker
* reuse docker image
* context window
* news
* print format
* pyspark version in py3.8
* pyspark in py3.8
* pyspark and ray
* quote
* pyspark
* pyspark
* pyspark
---------
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu >
2023-06-09 18:40:04 +00:00
Chi Wang
b90e9ee283
doc and test update ( #1053 )
...
* doc and test update
* docker update
2023-05-26 20:24:30 +00:00
Chi Wang
e463146cb8
response filter ( #1039 )
...
* response filter
* rewrite implement based on the filter
* multi responses
* abs path
* code handling
* option to not use docker
* context
* eval_only -> raise_error
* notebook
* utils
* utils
* separate tests
* test
* test
* test
* test
* test
* test
* test
* test
* **config in test()
* test
* test
* filename
2023-05-21 22:22:29 +00:00
Qingyun Wu
2e43509690
Human agent ( #1025 )
...
* add human agent and chat agent
* feedback msg
* clean print
* remove redundant import
* make coding agent work
* import check
* terminate condition
* rename
* add docstr
* exitcode to str
* print
* save and execute code
* add max_turn_num
* add max_turn_num in test_agent.py
* reduce max_turn_num in the test
* change max_turn_num to max_consecutive_auto_reply
* update human proxy agent
* remove execution agent and dated docstr
* clean doc
* add back work_dir
* add is_termination_msg when mode is NEVER
* revise stop condition
* remove work_dir in coding agent
* human_proxy_agent docstr
* auto_reply
* clean auto_reply
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com >
2023-05-16 00:37:38 +00:00
Chi Wang
19aee67f55
coding agent; logging ( #1011 )
...
* coding agent
* tsp
* tsp
* aoai
* logging
* compact
* Handle Import Error
* cost function
* reset counter; doc
* reset_counter
* home page update
* use case
* catboost in linux
* catboost
* catboost
* catboost
* doc
* intro
* catboost
2023-05-02 20:38:23 +00:00
