extract_document_to_md / requirements.txt
wang.lingxiao
merge
add6977
Raw
History Blame
627 Bytes
# Core dependencies
gradio[mcp]>=4.0.0
mcp-server-gradio
# Document processing
python-docx>=1.1.0
PyMuPDF>=1.23.0
python-pptx>=0.6.21
openpyxl>=3.1.0
striprtf>=0.0.26
ebooklib>=0.18
# OCR capabilities
pytesseract>=0.3.10
Pillow>=10.0.0
# AI and NLP
spacy>=3.7.0
transformers>=4.30.0
torch>=2.0.0
# Utilities
python-dateutil>=2.8.2
pyyaml>=6.0
markdown>=3.5.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
requests>=2.31.0
# Optional: Advanced features
matplotlib>=3.7.0
pandas>=2.0.0
numpy>=1.24.0
scikit-learn>=1.3.0
# Development and testing
pytest>=7.4.0
black>=23.0.0
flake8>=6.0.0
# Performance
uvloop>=0.17.0
aiofiles>=23.0.0