150 Commits

Author SHA1 Message Date
Chi Wang
9f3af1ef80 cleanup 2023-09-27 04:20:22 +00:00
Chi Wang
23ceac0fe0 cleanup 2023-09-25 21:42:24 +00:00
Chi Wang
efa8213d9d cleanup 2023-09-21 15:40:14 +00:00
Chi Wang
23633ae744 cleanup 2023-09-21 15:39:52 +00:00
Chi Wang
ec85b4984d cleanup 2023-09-19 02:26:57 +00:00
Chi Wang
a4b9297719 cleanup 2023-09-16 16:34:16 +00:00
Chi Wang
99f2f82fa3 Merge remote-tracking branch 'upstream/autogen-links' into code 2023-09-16 16:34:04 +00:00
Chi Wang
bc4473fe8a cleanup 2023-09-16 10:57:57 +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
599731cb22
rename human to user_proxy (#1215)
* rename human to user_proxy

* notebook update and bug fix
2023-09-11 14:33:47 +00:00
Qingyun Wu
3bfc5f21d2 Merge remote-tracking branch 'origin/main' into autogen-links 2023-09-11 09:39:55 -04:00
Chi Wang
0cb79dfdff
group chat for visualization (#1213)
* group chat for visualization

* show figure

* webpage update

* link update

* example 2

* example 2

---------

Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
2023-09-10 23:20:45 +00:00
Qingyun Wu
faee51ca9c update links 2023-09-08 10:07:19 -04:00
Chi Wang
93b9e09166
admin takeover in group chat (#1209)
* admin takeover in group chat

* comments

* add comments
2023-09-07 02:17:53 +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
Chi Wang
44932712c4
Prompt improvement (#1203)
* prompt improvement

* image None for unsupported lang

* notebook update

* prompt improvement
2023-08-30 00:54:09 +00:00
Chi Wang
57a2bea95a
prompt improvement (#1188)
* test

* chart

* plan

* separate

* bump version to 2.0.1

* explain plan and code/lang

* notebook update

* notebook update

* typo

* plan

* match can be None
2023-08-27 22:16:52 +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
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
3527e8a14d
update colab link (#1118)
* update colab link

* typo

* upload file instruction
2023-07-11 17:45:04 +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
Chi Wang
9c09090bf9
update notebook with new models (#1112)
* rerun notebook with new models

* planning agent

* link to notebook
2023-07-09 05:25:43 +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
8236533faf
update math notebook (#1095)
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2023-07-02 15:26:30 +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
a30d198530
Fix documentation (#1075)
* Fix indentation in documentation

* newline

* version
2023-06-11 01:03:49 +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
Qingyun Wu
fed28e700b
add agent notebook and documentation (#1052)
* 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>

* renaming and doc format

* typo

---------

Co-authored-by: Chi Wang <wang.chi@microsoft.com>
2023-05-28 03:17:23 +00:00
Qingyun Wu
3e6e834bbb
remove redundant doc and add tutorial (#1004)
* remove redundant doc and add tutorial

* add demos for pydata2023

* Update pydata23 docs

* remove redundant notebooks

* Move tutorial notebooks to notebook folder

* update readme and notebook links

* update notebook links

* update links

* update readme

---------

Co-authored-by: Li Jiang <lijiang1@microsoft.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-05-27 02:59:51 +00:00
Chi Wang
a0b318b12e
create an automl option to remove unnecessary dependency for autogen and tune (#1007)
* version update post release v1.2.2

* automl option

* import pandas

* remove automl.utils

* default

* test

* type hint and version update

* dependency update

* link to open in colab

* use packging.version to close #725

---------

Co-authored-by: Li Jiang <lijiang1@microsoft.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-05-24 23:55:04 +00:00
Chi Wang
9977a7aae1
Blogpost for adaptation in HumanEval (#1048)
* Blogpost for adaptation in HumanEval

* doc

* fix link

* fix link

* explain

* model

* interface

* link

* typo

* doc
2023-05-23 04:22:15 +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
Chi Wang
f097c20f86
version update post release v1.2.2 (#1005) 2023-04-25 04:48:17 +00:00
Chi Wang
fa5ccea862
extract code from text; solve_problem; request_timeout in config; improve code (#999)
* extract code from text

* solve_problem; request_timeout in config

* improve

* move import statement

* improve code

* generate assertions

* constant

* configs for implement; voting

* doc

* execute code in docker

* success indicator of code executation in docker

* success indicator

* execute code

* strip n

* add cost in generate_code

* add docstr

* filename

* bytes

* check docker version

* print log

* python test

* remove api key address

* rename exit code

* success exit code

* datasets

* exit code

* recover openai tests

* cache and pattern match

* wait

* wait

* cache and test

* timeout test

* python image name and skip macos

* windows image

* docker images

* volume path and yaml

* win path -> posix

* extensions

* path

* path

* path

* path

* path

* path

* path

* path

* path

* path

* path

* skip windows

* path

* timeout in windows

* use_docker

* use_docker

* hot fix from #1000

---------

Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
2023-04-23 11:50:29 +00:00
Susan Xueqing Liu
99bb0a8425
update nlp notebook (#940)
* update nlp notebook

* rerun

* rerun

* removing redundant in notebook

* remove redundant content in nlp notebook

* update notebook

* update plot

* update plot

* update plot

---------

Co-authored-by: Li Jiang <lijiang1@microsoft.com>
2023-04-17 17:29:36 +00:00
Chi Wang
82f0a4309d
autogen subpackage (#968)
* math utils in autogen

* cleanup

* code utils

* remove check function from code response

* comment out test

* GPT-4

* increase request timeout

* name

* logging and error handling

* better doc

* doc

* codegen optimized

* GPT series

* text

* no demo example

* math

* import openai

* import openai

* azure model name

* azure model name

* openai version

* generate assertion if necessary

* condition to generate assertions

* init region key

* rename

* comments about budget

* prompt

---------

Co-authored-by: Susan Xueqing Liu <liususan091219@users.noreply.github.com>
2023-04-08 03:04:01 +00:00
Qingyun Wu
45641000c0
Adding a test function for OpenAI completion in flaml (#951)
* improve max_valid_n and doc

* Update README.md

Co-authored-by: Li Jiang <lijiang1@microsoft.com>

* add support for chatgpt

* notebook

* newline at end of file

* chatgpt notebook

* ChatGPT in Azure

* doc

* math

* warning, timeout, log file name

* handle import error

* doc update; default value

* paper

* doc

* docstr

* eval_func

* add a test func in completion

* update notebook

* update math notebook

* improve notebok

* lint and handle exception

* flake8

* exception in test

* add agg_method

* NameError

* refactor

* Update flaml/integrations/oai/completion.py

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Update flaml/integrations/oai/completion.py

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* add example

* merge files from oai_eval_test

* Revert "merge files from oai_eval_test"
This reverts commit 1e6a550f913bb94df6e9680934ccb7175d00702e.

* merge

* save results to notebook_output

* update version and cache

* update doc

* save nb cell results to file

* fix typo in model name

* code improvements

* improve docstr

* docstr

* docstr on the Returns of test

---------

Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Li Jiang <lijiang1@microsoft.com>
Co-authored-by: Susan Xueqing Liu <liususan091219@users.noreply.github.com>
2023-04-02 16:14:11 +00:00
Chi Wang
595f5a8025
gpt-4 support; openai workflow fix; model str; timeout; voting (#958)
* workflow; model str; timeout

* voting

* notebook

* pull request

* recover workflow

* voted answer

* aoai

* ignore None answer

* default config

* note

* gpt-4

* n=5

* cleanup

* config name

* introduction

* readme

* avoid None

* add output/ to gitignore

* openai version

* invalid var

* comment long running cells
2023-03-26 17:13:06 +00:00