Skip to content

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

1.0 KB
Raw Blame
[project]
name = "docreader"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.10.18"
dependencies = [
    "beautifulsoup4>=4.14.2",
    "ebooklib>=0.18",
    "grpcio>=1.78.0",
    "grpcio-health-checking>=1.78.0",
    "grpcio-tools>=1.78.0",
    "lxml>=6.1.0",
    "markdownify>=0.13.1",
    "markitdown[docx,pdf,xls,xlsx,pptx]>=0.1.3",
    # Page straightening before OCR. Floors are kept low enough for the
    # project's declared Python range (>=3.10); the R22 pipeline was validated
    # against recent releases (rapidocr 3.10 / onnxruntime 1.31 / numpy 2.5).
    "numpy>=1.26",
    "onnxruntime>=1.17",
    "opencv-python-headless>=4.8",
    "opendataloader-pdf>=2.4.7",
    "openpyxl>=3.1.0",
    "pandas>=2.0.0",
    "xlrd>=2.0.0",
    "pillow>=12.2.0",
    "playwright>=1.55.0",
    "protobuf>=6.33.5",
    "pydantic>=2.13.4",
    "pypdf>=6.13.3",
    "pypdfium2>=5.8.0",
    "python-docx>=1.2.0",
    "rapidocr>=3.0",
    "requests>=2.33.0",
    "textract==1.5.0",
    "trafilatura>=2.0.0",
]