wehub-resource-sync
58 lines
1.7 KiB
TOML
58 lines
1.7 KiB
TOML
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "markitdown-ocr"
|
|
dynamic = ["version"]
|
|
description = 'OCR plugin for MarkItDown - Extracts text from images in PDF, DOCX, PPTX, and XLSX via LLM Vision'
|
|
readme = "README.md"
|
|
requires-python = ">=3.10"
|
|
license = "MIT"
|
|
keywords = ["markitdown", "ocr", "pdf", "docx", "xlsx", "pptx", "llm", "vision"]
|
|
authors = [
|
|
{ name = "Contributors", email = "noreply@github.com" },
|
|
]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Programming Language :: Python",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
"Programming Language :: Python :: Implementation :: CPython",
|
|
]
|
|
|
|
# Core dependencies — matches the file-format libraries markitdown already uses
|
|
dependencies = [
|
|
"markitdown>=0.1.0",
|
|
"pdfminer.six>=20251230",
|
|
"pdfplumber>=0.11.9",
|
|
"PyMuPDF>=1.24.0",
|
|
"mammoth~=1.11.0",
|
|
"python-docx",
|
|
"python-pptx",
|
|
"pandas",
|
|
"openpyxl",
|
|
"Pillow>=9.0.0",
|
|
]
|
|
|
|
# llm_client is passed in by the user (same as for markitdown image descriptions);
|
|
# install openai or any OpenAI-compatible SDK separately.
|
|
[project.optional-dependencies]
|
|
llm = [
|
|
"openai>=1.0.0",
|
|
]
|
|
|
|
[project.urls]
|
|
Documentation = "https://github.com/microsoft/markitdown#readme"
|
|
Issues = "https://github.com/microsoft/markitdown/issues"
|
|
Source = "https://github.com/microsoft/markitdown"
|
|
|
|
[tool.hatch.version]
|
|
path = "src/markitdown_ocr/__about__.py"
|
|
|
|
# CRITICAL: Plugin entry point - MarkItDown will discover this plugin through this entry point
|
|
[project.entry-points."markitdown.plugin"]
|
|
ocr = "markitdown_ocr"
|