pyproject.toml

[tool.poetry]
name = "omniparse"
version = "0.0.1"
description = "API to convert Documents | Media | Webpage into Structured Markdown for LLM usecases"
authors = ["Adithya S K <adithyaskolavi@gmail.com>"]
license = "Apache"
readme = "README.md"
keywords = ["pdf", "markdown", "ocr", "parse"]
include = [
    "server.py",
]

[tool.poetry.dependencies]
python = "^3.10"
scikit-learn = "^1.3.2"
Pillow = "^10.1.0"
pydantic = "^2.4.2"
pydantic-settings = "^2.0.3"
transformers = "^4.41.2" 
numpy = "^1.26.1"
python-dotenv = "^1.0.0"
torch = "^2.2.2" # Issue with torch 2.3.0 and vision models - https://github.com/pytorch/pytorch/issues/121834
tqdm = "^4.66.1"
tabulate = "^0.9.0"
ftfy = "^6.1.1"
texify = "^0.1.8"
rapidfuzz = "^3.8.1"
surya-ocr = "^0.4.3"
filetype = "^1.2.0"
regex = "^2024.4.28"
pdftext = "^0.3.10"
grpcio = "^1.63.0"
fastapi = "^0.111.0"
uvicorn = "^0.29.0"
pypdfium2 = "^4.30.0"
moviepy = "^1.0.3"
openai-whisper = "^20231117"
pytube = "^15.0.0"
beautifulsoup4 = "^4.12.3"
html2text = "^2024.2.26"
selenium = "^4.21.0"
webdriver-manager = "^4.0.1"
img2pdf = "^0.5.1"
matplotlib = "^3.9.0"
timm = "^1.0.7"
flash-attn = "^2.5.9"
art = "^6.2"
gradio = "^4.37.1"
nltk = "^3.8.1"
marker-pdf = "^0.2.16"

[tool.poetry.scripts]
omniparse = "server:main"

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