Metadata-Version: 2.1
Name: autogluon-assistant
Version: 0.0.1
Summary: An LLM-backed AI agent for competitive tabular machine learning
Project-URL: Homepage, https://github.com/autogluon/autogluon-assistant
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: autogluon.tabular[all]<2.0,>=1.1
Requires-Dist: importlib-resources<7.0,>=6.4.5
Requires-Dist: langchain<0.4,>=0.3.3
Requires-Dist: langchain_openai<0.3,>=0.2.2
Requires-Dist: langchain_aws<0.3,>=0.2.2
Requires-Dist: openfe<0.1,>=0.0.12
Requires-Dist: pydantic<3.0,>=2.9.2
Requires-Dist: hydra-core>=1.3
Requires-Dist: matplotlib>=3.9.2
Requires-Dist: typer>=0.12.5
Requires-Dist: rich>=13.8.1
Requires-Dist: s3fs>=2024.9.0
Requires-Dist: joblib>=1.4.2
Requires-Dist: python-calamine
Requires-Dist: sentence-transformers>=3.1.0
Requires-Dist: tenacity<10.0,>=8.2.2
Requires-Dist: gensim>=4.3
Provides-Extra: dev
Requires-Dist: black>=24; extra == "dev"
Requires-Dist: GitRepo>=1; extra == "dev"
Requires-Dist: pytest>=7; extra == "dev"
Requires-Dist: isort; extra == "dev"
Requires-Dist: ruff==0.4; extra == "dev"

# Autogluon Assistant

AutoGluon Assistant (AG-A) provides users a simple interface where they can input their data, describe their problem, and receive a highly accurate and competitive ML solution — without writing any code. By leveraging the state-of-the-art AutoML capabilities of AutoGluon and integrating them with a Large Language Model (LLM), AG-A automates the entire data science pipeline. AG-A takes AutoGluon’s automation from three lines of code to zero, enabling users to solve new supervised learning tabular problems using only natural language descriptions.
