wizardchen
ef1047bf67
Introduce opendataloader and PaddleOCR-VL parser engines with tenant-level settings UI, replace liteparse, and harden Excel/PPT/Markdown parsing. Optional odl-hybrid sidecar stays local-build only and is excluded from default dev-start and full profiles.
29 lines
675 B
TOML
29 lines
675 B
TOML
[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",
|
|
"grpcio>=1.78.0",
|
|
"grpcio-health-checking>=1.78.0",
|
|
"grpcio-tools>=1.78.0",
|
|
"lxml>=6.1.0",
|
|
"markitdown[docx,pdf,xls,xlsx]>=0.1.3",
|
|
"opendataloader-pdf>=2.4.7",
|
|
"openpyxl>=3.1.0",
|
|
"pandas>=2.0.0",
|
|
"xlrd>=2.0.0",
|
|
"pillow>=12.0.0",
|
|
"playwright>=1.55.0",
|
|
"protobuf>=6.33.0",
|
|
"pydantic>=2.13.4",
|
|
"pypdf>=6.1.3",
|
|
"pypdfium2>=5.8.0",
|
|
"python-docx>=1.2.0",
|
|
"requests>=2.32.5",
|
|
"textract==1.5.0",
|
|
"trafilatura>=2.0.0",
|
|
]
|