pyproject.toml

[project]
name = "text2dataset"
description = "Easily turn large English text datasets into Japanese text datasets using open LLMs"
authors = [
    { name = "speed1313", email = "speedtry13@icloud.com" }
]
dependencies = [
    "vllm>=0.6.1",
    "datasets>=3.0.0",
    "wandb>=0.18.0",
    "transformers==4.45.2",
    "deepl>=1.19.1",
    "python-dotenv>=1.0.1",
    "openai>=1.52.2",
]
readme = "README.md"
requires-python = ">= 3.12.1"
license = {file = "LICENSE"}

dynamic = [
    "version"
]

[project.urls]
Repository = "https://github.com/llm-jp/text2dataset"

[project.scripts]
text2dataset = "text2dataset.main:main"

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.version]
path = "src/text2dataset/_version.py"


[tool.hatch.build]
exclude = [
  "/.*",
  "/docs",
  "/tests",
  "/results",
  "/scripts",
  "/img2dataset",
  "/wandb",
  "/*.log",
  "/*.out",
  "/*.sh",
  "/*.jsonl",
]

[tool.rye]
managed = true
dev-dependencies = [
    "openpyxl>=3.1.5",
    "ruff>=0.6.4",
    "mypy>=1.11.2",
    "wheel>=0.44.0",
    "pytest>=8.3.3",
]


[tool.hatch.metadata]
allow-direct-references = true

[tool.hatch.build.targets.wheel]
packages = ["src/text2dataset"]