19 lines
830 B
Plaintext
19 lines
830 B
Plaintext
# Primary converter for clean text PDFs -> LLM-oriented markdown.
|
|
# Pulls pymupdf + tabulate transitively; no separate pin needed.
|
|
# NOTE: pinned to the lightweight 0.3.x line on purpose. The 1.27.x releases
|
|
# bundle an ML layout/OCR pipeline (onnxruntime + Tesseract) that fails on plain
|
|
# text PDFs without a tessdata install and pulls heavy deps we don't want here.
|
|
pymupdf4llm==0.3.4
|
|
|
|
# Validates topic datasets (md/<topic>/<name>.json) against their JSON Schemas.
|
|
# Used by validate.py; lightweight, pure-Python.
|
|
jsonschema>=4.0
|
|
|
|
# Fallbacks (install only if needed, see README):
|
|
# markitdown # DOCX/PPTX/XLSX/HTML -> md
|
|
# marker-pdf # heavier, ML/GPU, OCRs scanned PDFs
|
|
# docling # heavier, ML/GPU, messy layouts/tables
|
|
|
|
# Dev/test tooling (not needed at runtime; web.py is stdlib-only).
|
|
pytest>=8.0
|