* added default value to logprobs param
* fixed to work withversions of openai below 1.5.0
* rebase
* fixed openai version in comments
* polishing
* limit openai version to below 1.5.0
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.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>
* bump version to 0.2.1
* remove example link
* update
---------
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
Co-authored-by: kevin666aa <yrwu000627@gmail.com>
* LMM Code added
* LLaVA notebook update
* Test cases and Notebook modified for OpenAI v1
* Move LMM into contrib
To resolve test issues and deploy issues
In the future, we can install pillow by default, and then move back
LMM agents into agentchat
* LMM test setup update
* try...except... clause for LMM tests
* disable patch for llava agent test
To resolve dependencies issue for build
* Add LMM Blog
* Change docstring for LMM agents
* Docstring update patch
* llava: insert reply at position 1 now
So, it can still handle human_input_mode
and max_consecutive_reply
* Resolve comments
Fixing: typos, blogs, yml, and add OpenAIWrapper
* Signature typo fix for LMM agent: system_message
* Update LMM "content" from latest OpenAI release
Reference https://platform.openai.com/docs/guides/vision
* update LMM test according to latest OpenAI release
* Fully support GPT-4V now
1. Add a notebook for GPT-4V. LLava notebook also updated.
2. img_utils updated
3. GPT-4V formatter now return base64 image with mime type
4. Infer mime type directly from b64 image content (while loading
without suffix)
5. Test cases modified according to all the related changes.
* GPT-4V link updated in blog
---------
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* 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>
* Add custom embedding function
* Add support to custom vector db
* Improve docstring
* Improve docstring
* Improve docstring
* Add support to customized is_termination_msg fucntion
* Add a test for customize vector db with lancedb
* Fix tests
* Add test for embedding_function
* Update docstring
* FORMATTING
* UPDATE - OAI __init__.py
* ruff
* ADD - notebook covering oai API configuration options and their different purposes
* ADD openai util updates so that the function just assumes the same environment variable name for all models, also added functionality for adding API configurations like api_base etc.
* ADD - updates to config_list_from_dotenv and tests for openai_util testing, update example notebook
* UPDATE - added working config_list_from_dotenv() with passing tests, and updated notebook
* UPDATE - code and tests to potentially get around the window build permission error, used different method of producing temporary files
---------
Co-authored-by: Ward <award40@LAMU0CLP74YXVX6.uhc.com>
* Replace `assert`s in the `conversable_agent` module with `if-log-raise`.
* Use a `logger` object in the `code_utils` module.
* Replace use of `assert` with `if-log-raise` in the `code_utils` module.
* Replace use of `assert` in the `math_utils` module with `if-not-raise`.
* Replace `assert` with `if` in the `oai.completion` module.
* Replace `assert` in the `retrieve_utils` module with an if statement.
* Add missing `not`.
* Blacken `completion.py`.
* Test `generate_reply` and `a_generate_reply` raise an assertion error
when there are neither `messages` nor a `sender`.
* Test `execute_code` raises an `AssertionError` when neither code nor
filename is provided.
* Test `split_text_to_chunks` raises when passed an invalid chunk mode.
* * Add `tiktoken` and `chromadb` to test dependencies as they're used in
the `test_retrieve_utils` module.
* Sort the test requirements alphabetically.
* UPDATE - Updated retrieve_utils.py to have the ability to parse text from pdf files
* UNDO - change to recursive condition
* UPDATE - updated agentchat_RetrieveChat.ipynb to clarify which file types are accepted to be in the docs path
* ADD - missing import
* UPDATE - setup.py to have PyPDF2 in retrievechat
* RE-ADD - urls
* ADD - tests for retrieve utils, and removed deprecated PyPdf2
* Update agentchat_RetrieveChat.ipynb
* Update retrieve_utils.py
Fix format
* Update retrieve_utils.py
Replace print with logger
* UPDATE - added more specific exception to PDF decryption try/catch
* FIX - typo, return statement at wrong indentation in extract_text_from_pdf
---------
Co-authored-by: Ward <award40@LAMU0CLP74YXVX6.uhc.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
* Refactor into automl subpackage
Moved some of the packages into an automl subpackage to tidy before the
task-based refactor. This is in response to discussions with the group
and a comment on the first task-based PR.
Only changes here are moving subpackages and modules into the new
automl, fixing imports to work with this structure and fixing some
dependencies in setup.py.
* Fix doc building post automl subpackage refactor
* Fix broken links in website post automl subpackage refactor
* Fix broken links in website post automl subpackage refactor
* Remove vw from test deps as this is breaking the build
* Move default back to the top-level
I'd moved this to automl as that's where it's used internally, but had
missed that this is actually part of the public interface so makes sense
to live where it was.
* Re-add top level modules with deprecation warnings
flaml.data, flaml.ml and flaml.model are re-added to the top level,
being re-exported from flaml.automl for backwards compatability. Adding
a deprecation warning so that we can have a planned removal later.
* Fix model.py line-endings
* WIP
* WIP - Notes below
Got to the point where the methods from AutoML are pulled to
GenericTask. Started removing private markers and removing the passing
of automl to these methods. Done with decide_split_type, started on
prepare_data. Need to do the others after
* Re-add generic_task
* Most of the merge done, test_forecast_automl fit succeeds, fails at predict()
* Remaining fixes - test_forecast.py passes
* Comment out holidays-related code as it's not currently used
* Further holidays cleanup
* Fix imports in a test
* tidy up validate_data in time series task
* Test fixes
* Fix tests: add Task.__str__
* Fix tests: test for ray.ObjectRef
* Hotwire TS_Sklearn wrapper to fix test fail
* Attempt at test fix
* Fix test where val_pred_y is a list
* Attempt to fix remaining tests
* Push to retrigger tests
* Push to retrigger tests
* Push to retrigger tests
* Push to retrigger tests
* Remove plots from automl/test_forecast
* Remove unused data size field from Task
* Fix import for CLASSIFICATION in notebook
* Monkey patch TFT to avoid plotting, to fix tests on MacOS
* Monkey patch TFT to avoid plotting v2, to fix tests on MacOS
* Monkey patch TFT to avoid plotting v2, to fix tests on MacOS
* Fix circular import
* remove redundant code in task.py post-merge
* Fix test: set svd_solver="full" in PCA
* Update flaml/automl/data.py
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* Fix review comments
* Fix task -> str in custom learner constructor
* Remove unused CLASSIFICATION imports
* Hotwire TS_Sklearn wrapper to fix test fail by setting
optimizer_for_horizon == False
* Revert changes to the automl_classification and pin FLAML version
* Fix imports in reverted notebook
* Fix FLAML version in automl notebooks
* Fix ml.py line endings
* Fix CLASSIFICATION task import in automl_classification notebook
* Uncomment pip install in notebook and revert import
Not convinced this will work because of installing an older version of
the package into the environment in which we're running the tests, but
let's see.
* Revert c6a5dd1a0
* Fix get_classification_objective import in suggest.py
* Remove hcrystallball docs reference in TS_Sklearn
* Merge markharley:extract-task-class-from-automl into this
* Fix import, remove smooth.py
* Fix dependencies to fix TFT fail on Windows Python 3.8 and 3.9
* Add tensorboardX dependency to fix TFT fail on Windows Python 3.8 and 3.9
* Set pytorch-lightning==1.9.0 to fix TFT fail on Windows Python 3.8 and 3.9
* Set pytorch-lightning==1.9.0 to fix TFT fail on Windows Python 3.8 and 3.9
* Disable PCA reduction of lagged features for now, to fix svd convervence fail
* Merge flaml/main into time_series_task
* Attempt to fix formatting
* Attempt to fix formatting
* tentatively implement holt-winters-no covariates
* fix forecast method, clean class
* checking external regressors too
* update test forecast
* remove duplicated test file, re-add sarimax, search space cleanup
* Update flaml/automl/model.py
removed links. Most important one probably was: https://robjhyndman.com/hyndsight/ets-regressors/
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
* prevent short series
* add docs
* First attempt at merging Holt-Winters
* Linter fix
* Add holt-winters to TimeSeriesTask.estimators
* Fix spark test fail
* Attempt to fix another spark test fail
* Attempt to fix another spark test fail
* Change Black max line length to 127
* Change Black max line length to 120
* Add logging for ARIMA params, clean up time series models inheritance
* Add more logging for missing ARIMA params
* Remove a meaningless test causing a fail, add stricter check on ARIMA params
* Fix a bug in HoltWinters
* A pointless change to hopefully trigger the on and off KeyError in ARIMA.fit()
* Fix formatting
* Attempt to fix formatting
* Attempt to fix formatting
* Attempt to fix formatting
* Attempt to fix formatting
* Add type annotations to _train_with_config() in state.py
* Add type annotations to prepare_sample_train_data() in state.py
* Add docstring for time_col argument of AutoML.fit()
* Address @sonichi's comments on PR
* Fix formatting
* Fix formatting
* Reduce test time budget
* Reduce test time budget
* Increase time budget for the test to pass
* Remove redundant imports
* Remove more redundant imports
* Minor fixes of points raised by Qingyun
* Try to fix pandas import fail
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Try to fix pandas import fail, again
* Formatting fixes
* More formatting fixes
* Added test that loops over TS models to ensure coverage
* Fix formatting issues
* Fix more formatting issues
* Fix random fail in check
* Put back in tests for ARIMA predict without fit
* Put back in tests for lgbm
* Update test/test_model.py
cover dedup
* Match target length to X length in missing test
---------
Co-authored-by: Mark Harley <mark.harley@transferwise.com>
Co-authored-by: Mark Harley <mharley.code@gmail.com>
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
Co-authored-by: Chi Wang <wang.chi@microsoft.com>
Co-authored-by: Andrea W <a.ruggerini@ammagamma.com>
Co-authored-by: Andrea Ruggerini <nescio.adv@gmail.com>
Co-authored-by: Egor Kraev <Egor.Kraev@tw.com>
Co-authored-by: Li Jiang <bnujli@gmail.com>
* 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>
* 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>
* Mark experimental classes
* template
* multi model
* test
* multi-config doc
* doc
* doc
* test
---------
Co-authored-by: Li Jiang <bnujli@gmail.com>
* 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>
* 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
* 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
* prompt and messages
* remove confusing words
* notebook name
---------
Co-authored-by: Li Jiang <lijiang1@microsoft.com>
Co-authored-by: Susan Xueqing Liu <liususan091219@users.noreply.github.com>
* improve max_valid_n and doc
* Update README.md
Co-authored-by: Li Jiang <lijiang1@microsoft.com>
* newline at end of file
* doc
---------
Co-authored-by: Li Jiang <lijiang1@microsoft.com>
Co-authored-by: Susan Xueqing Liu <liususan091219@users.noreply.github.com>
Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu>
* add cost budget; move loc of make_dir
* support openai completion
* install pytest in workflow
* skip openai test
* test openai
* path for docs rebuild
* install datasets
* signal
* notebook
* notebook in workflow
* optional arguments and special params
* key -> k
* improve readability
* assumption
* optimize for model selection
* larger range of max_tokens
* notebook
* python package workflow
* skip on win
Davor Runje
Chi Wang
Joshua Kim
Qingyun Wu
Li Jiang
Beibin Li
Li Jiang
Ricky Loynd
Aaron
Mohamed Attia
Shaokun
Yiran Wu
EgorKraevTransferwise
Jirka Borovec
Susan Xueqing Liu