* Use code executors in notebook.
* Add custom code executor guide
* Add to gitignore
* Update
* fix links
* link
* typo
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Added vectordb base and chromadb
* Remove timer and unused functions
* Added filter by distance
* Added test utils
* Fix format
* Fix type hint of dict
* Rename test
* Add test chromadb
* Fix test no chromadb
* Add coverage
* Don't skip test vectordb utils
* Add types
* Fix tests
* Fix docs build error
* Add types to base
* Update base
* Update utils
* Update chromadb
* Add get_docs_by_ids
* Improve docstring
* Update init params
* Update init vector db
* Add get all docs
* Move chroma_results_to_query_results to utils
* Add init vectordb
* Convert format of results for old version
* Improve type hints
* Update get_context for new query results format
* Fix typo
* Improve init db
* Update default folder
* Update logger
* Update init, add embedding func
* Update distance_threshold
* Fix logger name
* Update qdrant
* Fix init db
* Update notebooks
* Use kwargs to improve readability
* Improve docstring of vectordb, add two attributes
* Add db_config
* Update gitignore
* Update comments
* Add source
* Fix file downloaded from urls have the same name
* Remove files added by mistake
* Improve docstring
* Update docstring
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Update docstring
* Update docstring
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Start Gemini integration: works ok with Text now
* Gemini notebook lint
* try catch "import" for Gemini
* Debug: id issue for chat completion in Gemini
* Add RAG example
* Update docs for RAG
* Fix missing pydash
* Remove temp folder
* Fix test error in runs/7206014032/job/19630042864
* Fix tqdm warning
* Fix notebook output
* Gemini's vision model is supported now
* Install instructions for the Gemini branch
* Catch and retry when see Interval Server Error 500
* Allow gemini to take more flexible messages
i.e., it can take messages where "user" is not the last role.
* Use int time for Gemini client
* Handle other exceptions in gemini call
* rename to "create" function for gemini
* GeminiClient compatible with ModelClient now
* Lint
* Update instructions in Gemini notebook
* Lint
* Remove empty blocks from Gemini notebook
* Add gemini into example page
* self.create instead of call
* Add py and Py into python execution
* Remove error code from merging
* Remove pydash dependency for gemini
* Add cloud-gemini doc
* Remove temp file
* cache import update
* Add test case for summary with mm input
* Lint: warnings instead of print
* Add test cases for gemini
* Gemini test config
* Disable default model for gemini
* Typo fix in gemini workflow
* Correct grammar in example notebook
* Raise if "model" is not provided in create(...)
* Move TODOs into a roadmap
* Update .github/workflows/contrib-tests.yml
Co-authored-by: Davor Runje <davor@airt.ai>
* Gemini test config update
* Update setup.py
Co-authored-by: Davor Runje <davor@airt.ai>
* Update test/oai/test_gemini.py
Co-authored-by: Davor Runje <davor@airt.ai>
* Update test/oai/test_gemini.py
Co-authored-by: Davor Runje <davor@airt.ai>
* Remove python 3.8 from gemini
No google's generativeai for Windows with Python 3.8
* Update import error handling for gemini
* Count tokens and cost for gemini
---------
Co-authored-by: Li Jiang <bnujli@gmail.com>
Co-authored-by: Davor Runje <davor@airt.ai>
* update default agent system message
* session friendly name functionality
* minor formatting
* fix issues with groupchat and version bump
* fix issues with groupchat and version bump. address #1580
* update groupchat system message
* add support for copying message in chatbox
* rewrite how agent history is maintained in workflow manager. Directly extend GroupChat and Conversable agent and override process_message method. Allow passing a message processor.
Fixes bug where the last message from a groupchat manager does not get called via register_reply.
* general qol updates
* add support for downloading + copying skills, models and agents from UI
* add regex check to agent name, address #1507
* add support for uploading workflow files
* refactor, add support for streaming intermediate agent response to ui
* improve streaming ux
* add support for uploading skills, models, agents, workflows
* add datamodel for socket message
* version update
* fix chatbox height bug
* fix csv pagination issue
* improve hidden menu for uploading entities
* fix minor issue with animation timing on chat interface
* version bump, css fixes
* use description field in autogen conversable class for description
* add implementation for llm summarization of agent chat
* support for llm summary of agent history
* formatting fixes
* formatting updates
* add dockerfile to run autogenstudio in a docker contailer
* autogenstudio docker container
* updates to websockets
* update socket connection logic,
* support using socket for passing message requests where a socket is available
* improve command for building frontend
* formatting updates
* remove duplicated code
# overwrite skills.py in work_dir is duplicated
* update description location
as Where the code calls is like config.description
* version bump
* refactor to ensure each session and call within a session has an independent working directory
* support use of socket for sending messages where available
* use rsync to copy built files to ui direction instead of cp -rT
* spelling correctino
* readme update
* fix numpy version
* version bump
* add support for dot env variables and updating default app dir to /home/<user>/.autogenstudio
* formatting update
* update gitignore
* formatting updates
---------
Co-authored-by: James Woffinden-Luey <jluey@microsoft.com>
Co-authored-by: cillyfly <cillyfly@gmail.com>
* Change defualt model for `lmm`
* Try to use PIL image for LMM's _oai_messages
* Update test cases and llava
* Remove redundant files
* Update the imports for lmm tests
* Test case fix
* Docstring update
* LMM notebook lint
* Typo correction for img_utils and its test
* Fix self.client bug for Dalle Agent
The self.client member variable is reserved for OpenAI's LLM-compatible
client, which requires usage summary support.
So, we rename self.client to self._dalle_client to resolve this issue
* function calling upgraded: async/sync mixing works now for all combinations and register_function added to simplify registration of functions without decorators
* polishing
* fixing tests
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* add function decorator to converasble agent
* polishing
* polishing
* added function decorator to the notebook with async function calls
* added support for return type hint and JSON encoding of returned value if needed
* polishing
* polishing
* refactored async case
* Python 3.8 support added
* polishing
* polishing
* missing docs added
* refacotring and changes as requested
* getLogger
* documentation added
* test fix
* test fix
* added testing of agentchat_function_call_currency_calculator.ipynb to test_notebook.py
* added support for Pydantic parameters in function decorator
* polishing
* Update website/docs/Use-Cases/agent_chat.md
Co-authored-by: Li Jiang <bnujli@gmail.com>
* Update website/docs/Use-Cases/agent_chat.md
Co-authored-by: Li Jiang <bnujli@gmail.com>
* fixes problem with logprob parameter in openai.types.chat.chat_completion.Choice added by openai version 1.5.0
* get 100% code coverage on code added
* updated docs
* default values added to JSON schema
* serialization using json.dump() add for values not string or BaseModel
* added limit to openai version because of breaking changes in 1.5.0
* added line-by-line comments in docs to explain the process
* polishing
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
* Change "content" type in Conversable Agent
* content and system_message support str and List
Update for all other agents
* Content_str now also takes None as input
* Group Chat now works with LMM too
* Style: newline for import in Conversable Agentt
* Add test for gourpchat + lmm
* Resolve comments
1. Undo AssistantAgent changes
2. Modify the asserts and raises in `content_str` function and update
test accordingly.
* Undo AssistantAgent
* Update comments and add assertion for LMM
* Typo fix in docstring for content_str
* Remove “None” out conversable_agent.py
* Lint message to dict in multimodal_conversable_agent.py
* Address lint issues
* linting
* Move lmm test into contrib test
* Resolve 2 comments
* Move img_utils into contrib folder
* Resolve img_utils path issues
* add agenteval-notebook for math problems and the blog post about it
* update gitignore
* updates to notebook
* adding folder for the logs
* adding math problems logs
* adding folder for alfworld logs
* added limitiation and future work to blog post
* minor edits blog post
* adding changes
* reorg
* modify the main notebook
* modification of the main notebook
* remove wrong notebook
* uploading new notebook
* update agenteval notebook
* change the sample
* Update agenteval_cq_math.ipynb
* adding final changes to notebook
* updated framework picture
* Update index.mdx
* Update index.md
* Add files via upload
* updates to notebool
* revise the blog
* revise the blog
* update the agent img
* revise the blog
* revise the blog
* Excluded model logs from the main branch, you can find them in agenteval branch
* Fixed pre-commit formatting.
* Update website/blog/2023-11-11-AgentEval/index.mdx
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* update gitignore
* update index.mdx
* update authors.yml by adding Negar and Julia
* remove md file
* remove md file
* update gitignore
* update authors file
* pre-commit checks
* pre-commit checks on authors.yml
* pre-commit checks on authors.yml
* update index.mdx
* update authors.yml by adding Negar and Julia
* updated the blog-post version 1
* updated the blog-post: TL;DR is ready
* updated the blog-post: first part of introduction is ready
* updated figures: typos on fig 1, changed terminology on the fig 2
* upadated the Framework part
* fixed redering issues
* upload zip file instead of single samples
* update prealgebra.zip
* update
* upload
* update z
* update naming
* update zip
* update the agenteval notebook
* update the notebook - removing unmercenary logs
* updated fig 1 and references to it
* updated fig 1
* incorporated PR comments
* merged agenteval branch
* final changes to the blog
* updated taxonomy
* update notebook
* minor changes to the blog
* Fixed formatting
* Update the link in agenteval_cq_math.ipynb
* update the blog and link in notebook
* Update index.mdx
* change folder name
* Changes to be committed:
modified: OAI_CONFIG_LIST_sample.txt
* add sample OAI file
* fix the url link to colab and typos
* fix the url link to colab and typos
* add authors
* update profile pic
* "update authors"
* fixing the problem in test_groupchat.py
* update the title lower case
* reverting changes in setup.py
* rerun pre-commit
---------
Co-authored-by: Negar Arabzadeh <ngr.arabzadeh@gmail.com>
Co-authored-by: Julia Kiseleva <jukisele@microsoft.com>
Co-authored-by: afourney <adamfo@microsoft.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
* Initial commit.
* Disable LLM response caching.
* Add teachability option to setup.py
* Modify test to use OAI_CONFIG_LIST as suggested in the docs.
* Expand unit test.
* Complete unit test.
* Add filter_dict
* details
* AnalysisAgent
* details
* More documentation and debug output.
* Support retrieval of any number of relevant memos, including zero.
* More robust analysis separator.
* cleanup
* teach_config
* refactoring
* For robustness, allow more flexibility on memo storage and retrieval.
* de-dupe the retrieved memos.
* Simplify AnalysisAgent. The unit tests now pass with gpt-3.5
* comments
* Add a verbosity level to control analyzer messages.
* refactoring
* comments
* Persist memory on disk.
* cleanup
* Use markdown to format retrieved memos.
* Use markdown in TextAnalyzerAgent
* Add another verbosity level.
* clean up logging
* notebook
* minor edits
* cleanup
* linter fixes
* Skip tests that fail to import openai
* Address reviewer feedback.
* lint
* refactoring
* Improve wording
* Improve code coverage.
* lint
* Use llm_config to control caching.
* lowercase notebook name
* Sort out the parameters passed through to ConversableAgent, and supply full docstrings for the others.
* lint
* Allow TextAnalyzerAgent to be given a different llm_config than TeachableAgent.
* documentation
* Modifications to run openai workflow.
* Test on just python 3.10.
Replace agent with agent teachable_agent as recommended.
* Test on python 3.9 instead of 3.10.
* Remove space from name -> teachableagent
---------
Co-authored-by: Li Jiang <bnujli@gmail.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* fix bug for windows
* fix bug for windows
* more clear example
* link to example
* add test
* format
* comment
* fix assertion error
* fix test error and links
---------
Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com>
* add basic support to Spark dataframe
add support to SynapseML LightGBM model
update to pyspark>=3.2.0 to leverage pandas_on_Spark API
* clean code, add TODOs
* add sample_train_data for pyspark.pandas dataframe, fix bugs
* improve some functions, fix bugs
* fix dict change size during iteration
* update model predict
* update LightGBM model, update test
* update SynapseML LightGBM params
* update synapseML and tests
* update TODOs
* Added support to roc_auc for spark models
* Added support to score of spark estimator
* Added test for automl score of spark estimator
* Added cv support to pyspark.pandas dataframe
* Update test, fix bugs
* Added tests
* Updated docs, tests, added a notebook
* Fix bugs in non-spark env
* Fix bugs and improve tests
* Fix uninstall pyspark
* Fix tests error
* Fix java.lang.OutOfMemoryError: Java heap space
* Fix test_performance
* Update test_sparkml to test_0sparkml to use the expected spark conf
* Remove unnecessary widgets in notebook
* Fix iloc java.lang.StackOverflowError
* fix pre-commit
* Added params check for spark dataframes
* Refactor code for train_test_split to a function
* Update train_test_split_pyspark
* Refactor if-else, remove unnecessary code
* Remove y from predict, remove mem control from n_iter compute
* Update workflow
* Improve _split_pyspark
* Fix test failure of too short training time
* Fix typos, improve docstrings
* Fix index errors of pandas_on_spark, add spark loss metric
* Fix typo of ndcgAtK
* Update NDCG metrics and tests
* Remove unuseful logger
* Use cache and count to ensure consistent indexes
* refactor for merge maain
* fix errors of refactor
* Updated SparkLightGBMEstimator and cache
* Updated config2params
* Remove unused import
* Fix unknown parameters
* Update default_estimator_list
* Add unit tests for spark metrics
* merging
* clean commit
* Delete mylearner.py
This file is not needed.
* fix py4j import error
* more tolerant cancelling time
* fix problems following suggestions
* Update flaml/tune/spark/utils.py
Co-authored-by: Li Jiang <bnujli@gmail.com>
* remove redundant model
* Update test/spark/custom_mylearner.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* add docstr
* reverse change in gitignore
* Update test/spark/custom_mylearner.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
---------
Co-authored-by: Li Jiang <bnujli@gmail.com>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* pickle the AutoML object
* get best model per estimator
* test deberta
* stateless API
* Add Gitter badge (#41)
* prevent divide by zero
* test roberta
* BlendSearchTuner
Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com>
Co-authored-by: The Gitter Badger <badger@gitter.im>
* v0.2.2
separate the HPO part into the module flaml.tune
enhanced implementation of FLOW^2, CFO and BlendSearch
support parallel tuning using ray tune
add support for sample_weight and generic fit arguments
enable mlflow logging
Co-authored-by: Chi Wang (MSR) <chiw@microsoft.com>
Co-authored-by: qingyun-wu <qw2ky@virginia.edu>
Eric Zhu