pyproject.toml

[build-system]
requires = ["setuptools>=45", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "chonkie"
version = "0.1.2"
description = "🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library"
readme = "README.md"
requires-python = ">=3.8"
license = {file = "LICENSE"}
keywords = ["chunking", "rag", "nlp", "text-processing"]
authors = [
    {name = "Bhavnick Minhas", email = "bhavnicksm@gmail.com"}
]
classifiers = [
    "License :: OSI Approved :: MIT License",
    "Programming Language :: Python",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.8",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: Implementation :: CPython",
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Developers",
    "Intended Audience :: Science/Research",
    "Intended Audience :: Information Technology",
    "Topic :: Scientific/Engineering :: Artificial Intelligence",
    "Topic :: Scientific/Engineering :: Information Analysis",
    "Topic :: Text Processing :: Linguistic"
]
dependencies = [
    "autotiktokenizer", "tokenizers>=0.13.0", "tiktoken>=0.2.0"
]

[project.urls]
Homepage = "https://github.com/bhavnicksm/chonkie"

[project.optional-dependencies]
sentence = ["spacy>=3.0.0"]
semantic = ["sentence-transformers>=2.0.0", "numpy>=1.23.0"]
all = ["spacy>=3.0.0", "sentence-transformers>=2.0.0", "numpy>=1.23.0"]
dev = ["pytest>=6.2.0", "transformers>=4.0.0", "tiktoken>=0.2.0", "black>=21.12b0", "isort>=5.10.2", "flake8>=4.0.0", "mypy>=0.910", "pylint>=2.11.1", "pre-commit>=2.15.0"]

# Add a Vietnamese-specific group
sentence-vi = ["underthesea"]
semantic-vi = ["pyvi", "sentence-transformers>=2.0.0", "numpy>=1.23.0"]
all-vi = ["pyvi", "underthesea", "spacy>=3.0.0", "sentence-transformers>=2.0.0", "numpy>=1.23.0"]

[tool.setuptools]
package-dir = {"" = "src"}
packages = ["chonkie", "chonkie.chunker"]