# Core libraries used by the GUI (concept_gui.py) and corpus builder
pymupdf
beautifulsoup4
requests
chardet
pillow
numpy
tqdm
ebooklib
markdown
tkinterdnd2
pdflatex

# Optional: language detection and image text-likeness improvements
langid
opencv-python-headless

# Optional (ASR for audio/video in corpus_builder.py)
openai-whisper
torch

# Notes (external binaries, install via system package manager):
# - pandoc (for high‑quality Markdown→PDF)
# - wkhtmltopdf (engine for HTML→PDF; enables local file access)
# - tesseract (OCR CLI)
# - ffmpeg/ffprobe (media handling)
# - ocrmypdf (for scanned PDFs)