FLAML 2.3.6__tar.gz → 2.4.0__tar.gz

{FLAML-2.3.6 → flaml-2.4.0}/FLAML.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: FLAML
-Version: 2.3.6
+Version: 2.4.0
 Summary: A fast library for automated machine learning and tuning
 Home-page: https://github.com/microsoft/FLAML
 Author: Microsoft Corporation
@@ -8,34 +8,133 @@ Author-email: hpo@microsoft.com
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.9
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE.md
+Requires-Dist: NumPy>=1.17
 Provides-Extra: automl
+Requires-Dist: lightgbm>=2.3.1; extra == "automl"
+Requires-Dist: xgboost<3.0.0,>=0.90; extra == "automl"
+Requires-Dist: scipy>=1.4.1; extra == "automl"
+Requires-Dist: pandas>=1.1.4; extra == "automl"
+Requires-Dist: scikit-learn>=1.0.0; extra == "automl"
 Provides-Extra: notebook
+Requires-Dist: jupyter; extra == "notebook"
 Provides-Extra: spark
+Requires-Dist: pyspark>=3.2.0; extra == "spark"
+Requires-Dist: joblibspark>=0.5.0; extra == "spark"
+Requires-Dist: joblib<=1.3.2; extra == "spark"
 Provides-Extra: test
+Requires-Dist: numpy<2.0.0,>=1.17; python_version < "3.13" and extra == "test"
+Requires-Dist: numpy>2.0.0; python_version >= "3.13" and extra == "test"
+Requires-Dist: jupyter; python_version < "3.13" and extra == "test"
+Requires-Dist: lightgbm>=2.3.1; extra == "test"
+Requires-Dist: xgboost<2.0.0,>=0.90; python_version < "3.11" and extra == "test"
+Requires-Dist: xgboost>=2.0.0; python_version >= "3.11" and extra == "test"
+Requires-Dist: scipy>=1.4.1; extra == "test"
+Requires-Dist: pandas<2.0.0,>=1.1.4; python_version < "3.10" and extra == "test"
+Requires-Dist: pandas>=1.1.4; python_version >= "3.10" and extra == "test"
+Requires-Dist: scikit-learn>=1.2.0; extra == "test"
+Requires-Dist: thop; extra == "test"
+Requires-Dist: pytest>=6.1.1; extra == "test"
+Requires-Dist: pytest-rerunfailures>=13.0; extra == "test"
+Requires-Dist: coverage>=5.3; extra == "test"
+Requires-Dist: pre-commit; extra == "test"
+Requires-Dist: torch; extra == "test"
+Requires-Dist: torchvision; extra == "test"
+Requires-Dist: catboost>=0.26; python_version < "3.13" and extra == "test"
+Requires-Dist: rgf-python; extra == "test"
+Requires-Dist: optuna<=3.6.1,>=2.8.0; extra == "test"
+Requires-Dist: openml; python_version < "3.13" and extra == "test"
+Requires-Dist: statsmodels>=0.12.2; extra == "test"
+Requires-Dist: psutil; extra == "test"
+Requires-Dist: dataclasses; extra == "test"
+Requires-Dist: transformers[torch]; extra == "test"
+Requires-Dist: datasets; extra == "test"
+Requires-Dist: evaluate; extra == "test"
+Requires-Dist: nltk!=3.8.2; extra == "test"
+Requires-Dist: rouge_score; extra == "test"
+Requires-Dist: hcrystalball; extra == "test"
+Requires-Dist: seqeval; extra == "test"
+Requires-Dist: pytorch-forecasting; python_version < "3.13" and extra == "test"
+Requires-Dist: mlflow-skinny<=2.22.1; extra == "test"
+Requires-Dist: joblibspark>=0.5.0; extra == "test"
+Requires-Dist: joblib<=1.3.2; extra == "test"
+Requires-Dist: nbconvert; extra == "test"
+Requires-Dist: nbformat; extra == "test"
+Requires-Dist: ipykernel; extra == "test"
+Requires-Dist: pytorch-lightning; extra == "test"
+Requires-Dist: tensorboardX; extra == "test"
+Requires-Dist: requests; extra == "test"
+Requires-Dist: packaging; extra == "test"
+Requires-Dist: dill; extra == "test"
 Provides-Extra: catboost
+Requires-Dist: catboost>=0.26; extra == "catboost"
 Provides-Extra: blendsearch
+Requires-Dist: optuna<=3.6.1,>=2.8.0; extra == "blendsearch"
+Requires-Dist: packaging; extra == "blendsearch"
 Provides-Extra: ray
+Requires-Dist: ray[tune]<2.5.0,>=1.13; extra == "ray"
 Provides-Extra: azureml
+Requires-Dist: azureml-mlflow; extra == "azureml"
 Provides-Extra: nni
+Requires-Dist: nni; extra == "nni"
 Provides-Extra: vw
+Requires-Dist: vowpalwabbit<9.0.0,>=8.10.0; extra == "vw"
+Requires-Dist: scikit-learn; extra == "vw"
 Provides-Extra: hf
+Requires-Dist: transformers[torch]==4.26; extra == "hf"
+Requires-Dist: datasets; extra == "hf"
+Requires-Dist: nltk<=3.8.1; extra == "hf"
+Requires-Dist: rouge_score; extra == "hf"
+Requires-Dist: seqeval; extra == "hf"
 Provides-Extra: nlp
-Provides-Extra: ts_forecast
+Requires-Dist: transformers[torch]==4.26; extra == "nlp"
+Requires-Dist: datasets; extra == "nlp"
+Requires-Dist: nltk<=3.8.1; extra == "nlp"
+Requires-Dist: rouge_score; extra == "nlp"
+Requires-Dist: seqeval; extra == "nlp"
+Provides-Extra: ts-forecast
+Requires-Dist: holidays; extra == "ts-forecast"
+Requires-Dist: prophet>=1.1.5; extra == "ts-forecast"
+Requires-Dist: statsmodels>=0.12.2; extra == "ts-forecast"
+Requires-Dist: hcrystalball>=0.1.10; extra == "ts-forecast"
 Provides-Extra: forecast
+Requires-Dist: holidays; extra == "forecast"
+Requires-Dist: prophet>=1.1.5; extra == "forecast"
+Requires-Dist: statsmodels>=0.12.2; extra == "forecast"
+Requires-Dist: hcrystalball>=0.1.10; extra == "forecast"
+Requires-Dist: pytorch-forecasting>=0.10.4; python_version < "3.13" and extra == "forecast"
+Requires-Dist: pytorch-lightning>=1.9.0; extra == "forecast"
+Requires-Dist: tensorboardX>=2.6; extra == "forecast"
 Provides-Extra: benchmark
-Provides-Extra: openai
-Provides-Extra: autogen
-Provides-Extra: mathchat
-Provides-Extra: retrievechat
+Requires-Dist: catboost>=0.26; extra == "benchmark"
+Requires-Dist: psutil==5.8.0; extra == "benchmark"
+Requires-Dist: xgboost==1.3.3; extra == "benchmark"
+Requires-Dist: pandas==1.1.4; extra == "benchmark"
 Provides-Extra: synapse
+Requires-Dist: joblibspark>=0.5.0; extra == "synapse"
+Requires-Dist: optuna<=3.6.1,>=2.8.0; extra == "synapse"
+Requires-Dist: pyspark>=3.2.0; extra == "synapse"
 Provides-Extra: autozero
-License-File: LICENSE
-License-File: NOTICE.md
+Requires-Dist: scikit-learn; extra == "autozero"
+Requires-Dist: pandas; extra == "autozero"
+Requires-Dist: packaging; extra == "autozero"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 [![PyPI version](https://badge.fury.io/py/FLAML.svg)](https://badge.fury.io/py/FLAML)
 ![Conda version](https://img.shields.io/conda/vn/conda-forge/flaml)
@@ -53,15 +152,9 @@ License-File: NOTICE.md
     <br>
 </p>
 
-:fire: FLAML supports AutoML and Hyperparameter Tuning in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/automated-machine-learning-fabric). In addition, we've introduced Python 3.11 support, along with a range of new estimators, and comprehensive integration with MLflow—thanks to contributions from the Microsoft Fabric product team.
-
-:fire: Heads-up: We have migrated [AutoGen](https://microsoft.github.io/autogen/) into a dedicated [github repository](https://github.com/microsoft/autogen). Alongside this move, we have also launched a dedicated [Discord](https://discord.gg/pAbnFJrkgZ) server and a [website](https://microsoft.github.io/autogen/) for comprehensive documentation.
+:fire: FLAML supports AutoML and Hyperparameter Tuning in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/automated-machine-learning-fabric). In addition, we've introduced Python 3.11 and 3.12 support, along with a range of new estimators, and comprehensive integration with MLflow—thanks to contributions from the Microsoft Fabric product team.
 
-:fire: The automated multi-agent chat framework in [AutoGen](https://microsoft.github.io/autogen/) is in preview from v2.0.0.
-
-:fire: FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
-
-:fire: [autogen](https://microsoft.github.io/autogen/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
+:fire: Heads-up: [AutoGen](https://microsoft.github.io/autogen/) has moved to a dedicated [GitHub repository](https://github.com/microsoft/autogen). FLAML no longer includes the `autogen` module—please use AutoGen directly.
 
 ## What is FLAML
 
@@ -69,7 +162,7 @@ FLAML is a lightweight Python library for efficient automation of machine
 learning and AI operations. It automates workflow based on large language models, machine learning models, etc.
 and optimizes their performance.
 
-- FLAML enables building next-gen GPT-X applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation and optimization of a complex GPT-X workflow. It maximizes the performance of GPT-X models and augments their weakness.
+- FLAML enables economical automation and tuning for ML/AI workflows, including model selection and hyperparameter optimization under resource constraints.
 - For common machine learning tasks like classification and regression, it quickly finds quality models for user-provided data with low computational resources. It is easy to customize or extend. Users can find their desired customizability from a smooth range.
 - It supports fast and economical automatic tuning (e.g., inference hyperparameters for foundation models, configurations in MLOps/LMOps workflows, pipelines, mathematical/statistical models, algorithms, computing experiments, software configurations), capable of handling large search space with heterogeneous evaluation cost and complex constraints/guidance/early stopping.
 
@@ -85,10 +178,10 @@ FLAML requires **Python version >= 3.9**. It can be installed from pip:
 pip install flaml
 ```
 
-Minimal dependencies are installed without extra options. You can install extra options based on the feature you need. For example, use the following to install the dependencies needed by the [`autogen`](https://microsoft.github.io/autogen/) package.
+Minimal dependencies are installed without extra options. You can install extra options based on the feature you need. For example, use the following to install the dependencies needed by the [`automl`](https://microsoft.github.io/FLAML/docs/Use-Cases/Task-Oriented-AutoML) module.
 
 ```bash
-pip install "flaml[autogen]"
+pip install "flaml[automl]"
 ```
 
 Find more options in [Installation](https://microsoft.github.io/FLAML/docs/Installation).
@@ -96,39 +189,6 @@ Each of the [`notebook examples`](https://github.com/microsoft/FLAML/tree/main/n
 
 ## Quickstart
 
-- (New) The [autogen](https://microsoft.github.io/autogen/) package enables the next-gen GPT-X applications with a generic multi-agent conversation framework.
-  It offers customizable and conversable agents which integrate LLMs, tools and human.
-  By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code. For example,
-
-```python
-from flaml import autogen
-
-assistant = autogen.AssistantAgent("assistant")
-user_proxy = autogen.UserProxyAgent("user_proxy")
-user_proxy.initiate_chat(
-    assistant,
-    message="Show me the YTD gain of 10 largest technology companies as of today.",
-)
-# This initiates an automated chat between the two agents to solve the task
-```
-
-Autogen also helps maximize the utility out of the expensive LLMs such as ChatGPT and GPT-4. It offers a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` with powerful functionalites like tuning, caching, templating, filtering. For example, you can optimize generations by LLM with your own tuning data, success metrics and budgets.
-
-```python
-# perform tuning
-config, analysis = autogen.Completion.tune(
-    data=tune_data,
-    metric="success",
-    mode="max",
-    eval_func=eval_func,
-    inference_budget=0.05,
-    optimization_budget=3,
-    num_samples=-1,
-)
-# perform inference for a test instance
-response = autogen.Completion.create(context=test_instance, **config)
-```
-
 - With three lines of code, you can start using this economical and fast
   AutoML engine as a [scikit-learn style estimator](https://microsoft.github.io/FLAML/docs/Use-Cases/Task-Oriented-AutoML).
 
@@ -150,7 +210,10 @@ automl.fit(X_train, y_train, task="classification", estimator_list=["lgbm"])
 
 ```python
 from flaml import tune
-tune.run(evaluation_function, config={…}, low_cost_partial_config={…}, time_budget_s=3600)
+
+tune.run(
+    evaluation_function, config={…}, low_cost_partial_config={…}, time_budget_s=3600
+)
 ```
 
 - [Zero-shot AutoML](https://microsoft.github.io/FLAML/docs/Use-Cases/Zero-Shot-AutoML) allows using the existing training API from lightgbm, xgboost etc. while getting the benefit of AutoML in choosing high-performance hyperparameter configurations per task.

{FLAML-2.3.6 → flaml-2.4.0}/FLAML.egg-info/requires.txt

@@ -1,10 +1,5 @@
 NumPy>=1.17
 
-[autogen]
-openai==0.27.8
-diskcache
-termcolor
-
 [automl]
 lightgbm>=2.3.1
 xgboost<3.0.0,>=0.90
@@ -31,23 +26,18 @@ optuna<=3.6.1,>=2.8.0
 packaging
 
 [catboost]
-
-[catboost:python_version < "3.11"]
-catboost<1.2,>=0.26
-
-[catboost:python_version >= "3.11"]
-catboost<=1.2.5,>=0.26
+catboost>=0.26
 
 [forecast]
-holidays<0.14
-prophet>=1.0.1
+holidays
+prophet>=1.1.5
 statsmodels>=0.12.2
-hcrystalball==0.1.10
-pytorch-lightning==1.9.0
-tensorboardX==2.6
+hcrystalball>=0.1.10
+pytorch-lightning>=1.9.0
+tensorboardX>=2.6
 
-[forecast:python_version < "3.11"]
-pytorch-forecasting>=0.9.0
+[forecast:python_version < "3.13"]
+pytorch-forecasting>=0.10.4
 
 [hf]
 transformers[torch]==4.26
@@ -56,14 +46,6 @@ nltk<=3.8.1
 rouge_score
 seqeval
 
-[mathchat]
-openai==0.27.8
-diskcache
-termcolor
-sympy
-pydantic==1.10.9
-wolframalpha
-
 [nlp]
 transformers[torch]==4.26
 datasets
@@ -77,20 +59,8 @@ nni
 [notebook]
 jupyter
 
-[openai]
-openai==0.27.8
-diskcache
-
 [ray]
-ray[tune]~=1.13
-
-[retrievechat]
-openai==0.27.8
-diskcache
-termcolor
-chromadb
-tiktoken
-sentence_transformers
+ray[tune]<2.5.0,>=1.13
 
 [spark]
 pyspark>=3.2.0
@@ -103,62 +73,67 @@ optuna<=3.6.1,>=2.8.0
 pyspark>=3.2.0
 
 [test]
-jupyter
 lightgbm>=2.3.1
-xgboost<2.0.0,>=0.90
 scipy>=1.4.1
-scikit-learn>=1.0.0
+scikit-learn>=1.2.0
 thop
 pytest>=6.1.1
+pytest-rerunfailures>=13.0
 coverage>=5.3
 pre-commit
 torch
 torchvision
 rgf-python
 optuna<=3.6.1,>=2.8.0
-openml
 statsmodels>=0.12.2
-psutil==5.8.0
+psutil
 dataclasses
-transformers[torch]==4.26
-datasets<=3.5.0
-nltk<=3.8.1
+transformers[torch]
+datasets
+evaluate
+nltk!=3.8.2
 rouge_score
-hcrystalball==0.1.10
+hcrystalball
 seqeval
-mlflow==2.15.1
+mlflow-skinny<=2.22.1
 joblibspark>=0.5.0
 joblib<=1.3.2
 nbconvert
 nbformat
 ipykernel
-pytorch-lightning<1.9.1
-tensorboardX==2.6
-requests<2.29.0
+pytorch-lightning
+tensorboardX
+requests
 packaging
-pydantic==1.10.9
-sympy
-wolframalpha
 dill
 
 [test:python_version < "3.10"]
 pandas<2.0.0,>=1.1.4
 
 [test:python_version < "3.11"]
-catboost<1.2,>=0.26
-pytorch-forecasting<=0.10.1,>=0.9.0
+xgboost<2.0.0,>=0.90
+
+[test:python_version < "3.13"]
+numpy<2.0.0,>=1.17
+jupyter
+catboost>=0.26
+openml
+pytorch-forecasting
 
 [test:python_version >= "3.10"]
 pandas>=1.1.4
 
 [test:python_version >= "3.11"]
-catboost>=0.26
+xgboost>=2.0.0
+
+[test:python_version >= "3.13"]
+numpy>2.0.0
 
 [ts_forecast]
-holidays<0.14
-prophet>=1.0.1
+holidays
+prophet>=1.1.5
 statsmodels>=0.12.2
-hcrystalball==0.1.10
+hcrystalball>=0.1.10
 
 [vw]
 vowpalwabbit<9.0.0,>=8.10.0

{FLAML-2.3.6 → flaml-2.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: FLAML
-Version: 2.3.6
+Version: 2.4.0
 Summary: A fast library for automated machine learning and tuning
 Home-page: https://github.com/microsoft/FLAML
 Author: Microsoft Corporation
@@ -8,34 +8,133 @@ Author-email: hpo@microsoft.com
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.9
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE.md
+Requires-Dist: NumPy>=1.17
 Provides-Extra: automl
+Requires-Dist: lightgbm>=2.3.1; extra == "automl"
+Requires-Dist: xgboost<3.0.0,>=0.90; extra == "automl"
+Requires-Dist: scipy>=1.4.1; extra == "automl"
+Requires-Dist: pandas>=1.1.4; extra == "automl"
+Requires-Dist: scikit-learn>=1.0.0; extra == "automl"
 Provides-Extra: notebook
+Requires-Dist: jupyter; extra == "notebook"
 Provides-Extra: spark
+Requires-Dist: pyspark>=3.2.0; extra == "spark"
+Requires-Dist: joblibspark>=0.5.0; extra == "spark"
+Requires-Dist: joblib<=1.3.2; extra == "spark"
 Provides-Extra: test
+Requires-Dist: numpy<2.0.0,>=1.17; python_version < "3.13" and extra == "test"
+Requires-Dist: numpy>2.0.0; python_version >= "3.13" and extra == "test"
+Requires-Dist: jupyter; python_version < "3.13" and extra == "test"
+Requires-Dist: lightgbm>=2.3.1; extra == "test"
+Requires-Dist: xgboost<2.0.0,>=0.90; python_version < "3.11" and extra == "test"
+Requires-Dist: xgboost>=2.0.0; python_version >= "3.11" and extra == "test"
+Requires-Dist: scipy>=1.4.1; extra == "test"
+Requires-Dist: pandas<2.0.0,>=1.1.4; python_version < "3.10" and extra == "test"
+Requires-Dist: pandas>=1.1.4; python_version >= "3.10" and extra == "test"
+Requires-Dist: scikit-learn>=1.2.0; extra == "test"
+Requires-Dist: thop; extra == "test"
+Requires-Dist: pytest>=6.1.1; extra == "test"
+Requires-Dist: pytest-rerunfailures>=13.0; extra == "test"
+Requires-Dist: coverage>=5.3; extra == "test"
+Requires-Dist: pre-commit; extra == "test"
+Requires-Dist: torch; extra == "test"
+Requires-Dist: torchvision; extra == "test"
+Requires-Dist: catboost>=0.26; python_version < "3.13" and extra == "test"
+Requires-Dist: rgf-python; extra == "test"
+Requires-Dist: optuna<=3.6.1,>=2.8.0; extra == "test"
+Requires-Dist: openml; python_version < "3.13" and extra == "test"
+Requires-Dist: statsmodels>=0.12.2; extra == "test"
+Requires-Dist: psutil; extra == "test"
+Requires-Dist: dataclasses; extra == "test"
+Requires-Dist: transformers[torch]; extra == "test"
+Requires-Dist: datasets; extra == "test"
+Requires-Dist: evaluate; extra == "test"
+Requires-Dist: nltk!=3.8.2; extra == "test"
+Requires-Dist: rouge_score; extra == "test"
+Requires-Dist: hcrystalball; extra == "test"
+Requires-Dist: seqeval; extra == "test"
+Requires-Dist: pytorch-forecasting; python_version < "3.13" and extra == "test"
+Requires-Dist: mlflow-skinny<=2.22.1; extra == "test"
+Requires-Dist: joblibspark>=0.5.0; extra == "test"
+Requires-Dist: joblib<=1.3.2; extra == "test"
+Requires-Dist: nbconvert; extra == "test"
+Requires-Dist: nbformat; extra == "test"
+Requires-Dist: ipykernel; extra == "test"
+Requires-Dist: pytorch-lightning; extra == "test"
+Requires-Dist: tensorboardX; extra == "test"
+Requires-Dist: requests; extra == "test"
+Requires-Dist: packaging; extra == "test"
+Requires-Dist: dill; extra == "test"
 Provides-Extra: catboost
+Requires-Dist: catboost>=0.26; extra == "catboost"
 Provides-Extra: blendsearch
+Requires-Dist: optuna<=3.6.1,>=2.8.0; extra == "blendsearch"
+Requires-Dist: packaging; extra == "blendsearch"
 Provides-Extra: ray
+Requires-Dist: ray[tune]<2.5.0,>=1.13; extra == "ray"
 Provides-Extra: azureml
+Requires-Dist: azureml-mlflow; extra == "azureml"
 Provides-Extra: nni
+Requires-Dist: nni; extra == "nni"
 Provides-Extra: vw
+Requires-Dist: vowpalwabbit<9.0.0,>=8.10.0; extra == "vw"
+Requires-Dist: scikit-learn; extra == "vw"
 Provides-Extra: hf
+Requires-Dist: transformers[torch]==4.26; extra == "hf"
+Requires-Dist: datasets; extra == "hf"
+Requires-Dist: nltk<=3.8.1; extra == "hf"
+Requires-Dist: rouge_score; extra == "hf"
+Requires-Dist: seqeval; extra == "hf"
 Provides-Extra: nlp
-Provides-Extra: ts_forecast
+Requires-Dist: transformers[torch]==4.26; extra == "nlp"
+Requires-Dist: datasets; extra == "nlp"
+Requires-Dist: nltk<=3.8.1; extra == "nlp"
+Requires-Dist: rouge_score; extra == "nlp"
+Requires-Dist: seqeval; extra == "nlp"
+Provides-Extra: ts-forecast
+Requires-Dist: holidays; extra == "ts-forecast"
+Requires-Dist: prophet>=1.1.5; extra == "ts-forecast"
+Requires-Dist: statsmodels>=0.12.2; extra == "ts-forecast"
+Requires-Dist: hcrystalball>=0.1.10; extra == "ts-forecast"
 Provides-Extra: forecast
+Requires-Dist: holidays; extra == "forecast"
+Requires-Dist: prophet>=1.1.5; extra == "forecast"
+Requires-Dist: statsmodels>=0.12.2; extra == "forecast"
+Requires-Dist: hcrystalball>=0.1.10; extra == "forecast"
+Requires-Dist: pytorch-forecasting>=0.10.4; python_version < "3.13" and extra == "forecast"
+Requires-Dist: pytorch-lightning>=1.9.0; extra == "forecast"
+Requires-Dist: tensorboardX>=2.6; extra == "forecast"
 Provides-Extra: benchmark
-Provides-Extra: openai
-Provides-Extra: autogen
-Provides-Extra: mathchat
-Provides-Extra: retrievechat
+Requires-Dist: catboost>=0.26; extra == "benchmark"
+Requires-Dist: psutil==5.8.0; extra == "benchmark"
+Requires-Dist: xgboost==1.3.3; extra == "benchmark"
+Requires-Dist: pandas==1.1.4; extra == "benchmark"
 Provides-Extra: synapse
+Requires-Dist: joblibspark>=0.5.0; extra == "synapse"
+Requires-Dist: optuna<=3.6.1,>=2.8.0; extra == "synapse"
+Requires-Dist: pyspark>=3.2.0; extra == "synapse"
 Provides-Extra: autozero
-License-File: LICENSE
-License-File: NOTICE.md
+Requires-Dist: scikit-learn; extra == "autozero"
+Requires-Dist: pandas; extra == "autozero"
+Requires-Dist: packaging; extra == "autozero"
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: provides-extra
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 [![PyPI version](https://badge.fury.io/py/FLAML.svg)](https://badge.fury.io/py/FLAML)
 ![Conda version](https://img.shields.io/conda/vn/conda-forge/flaml)
@@ -53,15 +152,9 @@ License-File: NOTICE.md
     <br>
 </p>
 
-:fire: FLAML supports AutoML and Hyperparameter Tuning in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/automated-machine-learning-fabric). In addition, we've introduced Python 3.11 support, along with a range of new estimators, and comprehensive integration with MLflow—thanks to contributions from the Microsoft Fabric product team.
-
-:fire: Heads-up: We have migrated [AutoGen](https://microsoft.github.io/autogen/) into a dedicated [github repository](https://github.com/microsoft/autogen). Alongside this move, we have also launched a dedicated [Discord](https://discord.gg/pAbnFJrkgZ) server and a [website](https://microsoft.github.io/autogen/) for comprehensive documentation.
+:fire: FLAML supports AutoML and Hyperparameter Tuning in [Microsoft Fabric Data Science](https://learn.microsoft.com/en-us/fabric/data-science/automated-machine-learning-fabric). In addition, we've introduced Python 3.11 and 3.12 support, along with a range of new estimators, and comprehensive integration with MLflow—thanks to contributions from the Microsoft Fabric product team.
 
-:fire: The automated multi-agent chat framework in [AutoGen](https://microsoft.github.io/autogen/) is in preview from v2.0.0.
-
-:fire: FLAML is highlighted in OpenAI's [cookbook](https://github.com/openai/openai-cookbook#related-resources-from-around-the-web).
-
-:fire: [autogen](https://microsoft.github.io/autogen/) is released with support for ChatGPT and GPT-4, based on [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673).
+:fire: Heads-up: [AutoGen](https://microsoft.github.io/autogen/) has moved to a dedicated [GitHub repository](https://github.com/microsoft/autogen). FLAML no longer includes the `autogen` module—please use AutoGen directly.
 
 ## What is FLAML
 
@@ -69,7 +162,7 @@ FLAML is a lightweight Python library for efficient automation of machine
 learning and AI operations. It automates workflow based on large language models, machine learning models, etc.
 and optimizes their performance.
 
-- FLAML enables building next-gen GPT-X applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation and optimization of a complex GPT-X workflow. It maximizes the performance of GPT-X models and augments their weakness.
+- FLAML enables economical automation and tuning for ML/AI workflows, including model selection and hyperparameter optimization under resource constraints.
 - For common machine learning tasks like classification and regression, it quickly finds quality models for user-provided data with low computational resources. It is easy to customize or extend. Users can find their desired customizability from a smooth range.
 - It supports fast and economical automatic tuning (e.g., inference hyperparameters for foundation models, configurations in MLOps/LMOps workflows, pipelines, mathematical/statistical models, algorithms, computing experiments, software configurations), capable of handling large search space with heterogeneous evaluation cost and complex constraints/guidance/early stopping.
 
@@ -85,10 +178,10 @@ FLAML requires **Python version >= 3.9**. It can be installed from pip:
 pip install flaml
 ```
 
-Minimal dependencies are installed without extra options. You can install extra options based on the feature you need. For example, use the following to install the dependencies needed by the [`autogen`](https://microsoft.github.io/autogen/) package.
+Minimal dependencies are installed without extra options. You can install extra options based on the feature you need. For example, use the following to install the dependencies needed by the [`automl`](https://microsoft.github.io/FLAML/docs/Use-Cases/Task-Oriented-AutoML) module.
 
 ```bash
-pip install "flaml[autogen]"
+pip install "flaml[automl]"
 ```
 
 Find more options in [Installation](https://microsoft.github.io/FLAML/docs/Installation).
@@ -96,39 +189,6 @@ Each of the [`notebook examples`](https://github.com/microsoft/FLAML/tree/main/n
 
 ## Quickstart
 
-- (New) The [autogen](https://microsoft.github.io/autogen/) package enables the next-gen GPT-X applications with a generic multi-agent conversation framework.
-  It offers customizable and conversable agents which integrate LLMs, tools and human.
-  By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code. For example,
-
-```python
-from flaml import autogen
-
-assistant = autogen.AssistantAgent("assistant")
-user_proxy = autogen.UserProxyAgent("user_proxy")
-user_proxy.initiate_chat(
-    assistant,
-    message="Show me the YTD gain of 10 largest technology companies as of today.",
-)
-# This initiates an automated chat between the two agents to solve the task
-```
-
-Autogen also helps maximize the utility out of the expensive LLMs such as ChatGPT and GPT-4. It offers a drop-in replacement of `openai.Completion` or `openai.ChatCompletion` with powerful functionalites like tuning, caching, templating, filtering. For example, you can optimize generations by LLM with your own tuning data, success metrics and budgets.
-
-```python
-# perform tuning
-config, analysis = autogen.Completion.tune(
-    data=tune_data,
-    metric="success",
-    mode="max",
-    eval_func=eval_func,
-    inference_budget=0.05,
-    optimization_budget=3,
-    num_samples=-1,
-)
-# perform inference for a test instance
-response = autogen.Completion.create(context=test_instance, **config)
-```
-
 - With three lines of code, you can start using this economical and fast
   AutoML engine as a [scikit-learn style estimator](https://microsoft.github.io/FLAML/docs/Use-Cases/Task-Oriented-AutoML).
 
@@ -150,7 +210,10 @@ automl.fit(X_train, y_train, task="classification", estimator_list=["lgbm"])
 
 ```python
 from flaml import tune
-tune.run(evaluation_function, config={…}, low_cost_partial_config={…}, time_budget_s=3600)
+
+tune.run(
+    evaluation_function, config={…}, low_cost_partial_config={…}, time_budget_s=3600
+)
 ```
 
 - [Zero-shot AutoML](https://microsoft.github.io/FLAML/docs/Use-Cases/Zero-Shot-AutoML) allows using the existing training API from lightgbm, xgboost etc. while getting the benefit of AutoML in choosing high-performance hyperparameter configurations per task.