unstructured[docx,image,odt,pdf]>=0.10.0
python-docx>=1.0.0
beautifulsoup4>=4.12.0
pymupdf>=1.23.0
pdfplumber>=0.10.0
pdf2image>=1.16.0
langchain>=1.0.0
langchain-text-splitters>=1.0.0
langchain-community>=0.4.0
chonkie>=1.0.0
easyocr>=1.7.0
pytesseract>=0.3.10
pillow>=10.0.0
langdetect>=1.0.9
spacy>=3.7.0
tiktoken>=0.5.0
transformers>=4.44.0
datasets>=2.20.0
sentence-transformers>=2.2.0
scikit-learn>=1.5.0
torch>=2.2.0
joblib>=1.3.0
pandas>=2.0.0
numpy<2.0,>=1.26.0
scipy>=1.13.0
typer[all]>=0.12.0
rich>=13.0.0
psutil>=5.9.0
requests>=2.31.0

[dev]
pytest>=7.4.0
pytest-cov>=4.1.0
pytest-asyncio>=0.21.0
pytest-mock>=3.12.0
pytest-env>=1.1.0
black>=23.0.0
ruff>=0.1.0
flake8>=7.0.0
mypy>=1.7.0
isort>=5.12.0
safety>=3.0.0
bandit>=1.7.0
pre-commit>=3.5.0

[llm]
openai>=1.0.0
anthropic>=0.7.0
ollama>=0.1.0

[ocr-advanced]
easyocr>=1.7.0
paddleocr>=2.7.0
