pyproject.toml

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

[project]
name = "chonkie"
version = "0.3.0"
description = "🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library"
readme = "README.md"
requires-python = ">=3.9"
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 :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Development Status :: 4 - Beta",
    "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>=0.2.0"
]

[project.urls]
Homepage = "https://github.com/bhavnicksm/chonkie"
Documentation = "https://docs.chonkie.ai"
[project.optional-dependencies]
model2vec = ["model2vec>=0.1.0", "numpy>=1.23.0, <2.2"]
st = ["sentence-transformers>=3.0.0", "numpy>=1.23.0, <2.2"]
openai = ["openai>=1.0.0", "numpy>=1.23.0, <2.2"]
semantic = ["model2vec>=0.1.0", "numpy>=1.23.0, <2.2"]
all = ["sentence-transformers>=3.0.0", "numpy>=1.23.0, <2.2", "openai>=1.0.0", "model2vec>=0.1.0"]
dev = [
    "pytest>=6.2.0", 
    "datasets>=1.14.0",
    "transformers>=4.0.0",
    "ruff>=0.0.265"
]

[tool.pytest.ini_options]
pythonpath = "src"

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

[tool.ruff]
select = ["F", "I", "D", "DOC"]