[tool.poetry]
name = "marker-pdf"
version = "1.6.2"
description = "Convert documents to markdown with high speed and accuracy."
authors = ["Vik Paruchuri <github@vikas.sh>"]
readme = "README.md"
license = "GPL-3.0-or-later"
repository = "https://github.com/VikParuchuri/marker"
keywords = ["pdf", "markdown", "ocr", "nlp"]
packages = [
    {include = "marker"}
]
include = [
    "marker/scripts/*.sh",
    "marker/scripts/*.html",
]

[tool.poetry.dependencies]
python = "^3.10"
Pillow = "^10.1.0"
pydantic = "^2.4.2"
pydantic-settings = "^2.0.3"
transformers = "^4.45.2"
python-dotenv = "^1.0.0"
torch = "^2.5.1"
tqdm = "^4.66.1"
ftfy = "^6.1.1"
rapidfuzz = "^3.8.1"
surya-ocr = "~0.13.1"
regex = "^2024.4.28"
pdftext = "~0.6.2"
markdownify = "^0.13.1"
click = "^8.1.7"
markdown2 = "^2.5.2"
filetype = "^1.2.0"
scikit-learn = "^1.6.1"
google-genai = "^1.0.0"
anthropic = "^0.46.0"
pre-commit = "^4.2.0"

# Optional dependencies for documents
mammoth = {version = "^1.9.0", optional = true}
openpyxl = {version = "^3.1.5", optional = true}
python-pptx = {version = "^1.0.2", optional = true}
ebooklib = {version = "^0.18", optional = true}
weasyprint = {version = "^63.1", optional = true}
openai = "^1.65.2"

[tool.poetry.group.dev.dependencies]
jupyter = "^1.0.0"
datasets = "^2.21.0"
streamlit = "^1.37.1"
fastapi = "^0.115.4"
uvicorn = "^0.32.0"
python-multipart = "^0.0.16"
pytest = "^8.3.3"
pytest-mock = "^3.14.0"
apted = "1.0.3"
distance = "0.1.3"
lxml = "5.3.0"
tabulate = "^0.9.0"
latex2mathml = "^3.77.0"
playwright = "^1.49.1"

[tool.poetry.extras]
full = ["mammoth", "openpyxl", "python-pptx", "ebooklib", "weasyprint"]

[tool.poetry.scripts]
marker = "marker.scripts.convert:convert_cli"
marker_single = "marker.scripts.convert_single:convert_single_cli"
marker_chunk_convert = "marker.scripts.chunk_convert:chunk_convert_cli"
marker_gui = "marker.scripts.run_streamlit_app:streamlit_app_cli"
marker_server = "marker.scripts.server:server_cli"

[build-system]
requires = ["poetry-core"]
build-backend = "poetry.core.masonry.api"