pyproject.toml

[project]
name = "rag-chunk"
version = "0.4.0"
description = "CLI tool to parse, chunk, and evaluate Markdown documents for RAG pipelines with token-accurate chunking support"
authors = [ { name = "messkan" } ]
license = { text = "MIT" }
readme = "README.md"
requires-python = ">=3.9"
keywords = ["rag", "chunking", "markdown", "retrieval"]
classifiers = ["Programming Language :: Python :: 3", "License :: OSI Approved :: MIT License", "Topic :: Software Development :: Libraries :: Python Modules", "Intended Audience :: Developers"]

[project.scripts]
rag-chunk = "src.cli:main"

[tool.setuptools.packages.find]
where = ["."]
include = ["src*"]

[build-system]
requires = ["setuptools>=67.0"]
build-backend = "setuptools.build_meta"

[project.optional-dependencies]
rich = ["rich>=12.0.0"]
tiktoken = ["tiktoken>=0.5.0"]
langchain = ["langchain>=0.1.0", "langchain-text-splitters>=0.0.1"]
semantic = ["sentence-transformers>=2.2.0", "numpy>=1.24.0"]
all = ["rich>=12.0.0", "tiktoken>=0.5.0", "langchain>=0.1.0", "langchain-text-splitters>=0.0.1", "sentence-transformers>=2.2.0", "numpy>=1.24.0"]