mirror of
https://github.com/VikParuchuri/surya.git
synced 2026-06-04 21:03:53 +08:00
63 lines
1.6 KiB
TOML
63 lines
1.6 KiB
TOML
[project]
|
|
name = "surya-ocr"
|
|
version = "2.0.0a0"
|
|
description = "OCR, layout, reading order, and table recognition via VLM (vllm + llama.cpp)."
|
|
readme = "README.md"
|
|
license = { text = "Apache-2.0" }
|
|
authors = [
|
|
{ name = "Vik Paruchuri", email = "vik.paruchuri@gmail.com" },
|
|
]
|
|
requires-python = ">=3.10,<4"
|
|
keywords = ["ocr", "pdf", "text detection", "text recognition", "tables"]
|
|
dependencies = [
|
|
"transformers>=4.56.1",
|
|
"torch>=2.7.0,<3",
|
|
"pydantic>=2.5.3,<3",
|
|
"pydantic-settings>=2.1.0,<3",
|
|
"python-dotenv>=1.0.0,<2",
|
|
"pillow>=10.2.0,<11",
|
|
"pypdfium2==4.30.0",
|
|
"filetype>=1.2.0,<2",
|
|
"click>=8.1.8,<9",
|
|
"platformdirs>=4.3.6,<5",
|
|
"opencv-python-headless==4.11.0.86",
|
|
"einops>=0.8.1,<0.9",
|
|
"openai>=1.55.0,<2",
|
|
"httpx>=0.27.0,<0.28",
|
|
"huggingface-hub>=0.26.0,<1",
|
|
"filelock>=3.16.0,<4",
|
|
"beautifulsoup4>=4.12.0,<5",
|
|
]
|
|
|
|
[project.urls]
|
|
Repository = "https://github.com/VikParuchuri/surya"
|
|
|
|
[project.scripts]
|
|
surya_detect = "surya.scripts.detect_text:detect_text_cli"
|
|
surya_ocr = "surya.scripts.ocr_text:ocr_text_cli"
|
|
surya_layout = "surya.scripts.detect_layout:detect_layout_cli"
|
|
surya_gui = "surya.scripts.run_streamlit_app:streamlit_app_cli"
|
|
surya_table = "surya.scripts.table_recognition:table_recognition_cli"
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"pre-commit>=4.2.0",
|
|
"jupyter>=1.0.0",
|
|
"pytesseract>=0.3.10",
|
|
"pymupdf>=1.23.8",
|
|
"datasets>=2.16.1",
|
|
"rapidfuzz>=3.6.1",
|
|
"streamlit>=1.31.0",
|
|
"pytest>=8.3.4",
|
|
"pdftext>=0.5.1",
|
|
"tabulate>=0.9.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["surya"]
|
|
|