eSliderandGitHub
f99dfea104
pdftotext still wins on born-digital PDFs. Empty text layers go through pdftoppm + tesseract eng+deu. Optional OCR_ENGINE=paddle. Gitea #6.
17 lines
489 B
TOML
17 lines
489 B
TOML
[project]
|
|
name = "2dph"
|
|
version = "0.1.0"
|
|
description = "Evidence-first brain: LadybugDB knowledge graph + hybrid RAG over the ops stack. Facts need two sources or they are (not confirmed)."
|
|
readme = "README.md"
|
|
requires-python = ">=3.12"
|
|
license = { text = "MIT" }
|
|
dependencies = [
|
|
"ladybug==0.19.1",
|
|
"markitdown[docx,epub,html,image-exif,pdf,pptx,xlsx,zip]>=0.1.7",
|
|
"mistune==3.3.4",
|
|
"model2vec==0.8.2",
|
|
"numpy>=2.5.2",
|
|
"pyyaml>=6.0.3",
|
|
"requests>=2.34.2",
|
|
]
|