requirements.txt

# ── Core ─────────────────────────────────────────────────────────────────────
docling>=2.5.0
docling-core>=2.0.0

# ── Streamlit ─────────────────────────────────────────────────────────────────
streamlit>=1.35.0

# ── OCR backends ─────────────────────────────────────────────────────────────
easyocr>=1.7.0          # Pure-Python OCR (no system deps needed)
# pytesseract            # Tesseract wrapper — uncomment if packages.txt has tesseract

# ── Document format support ───────────────────────────────────────────────────
python-docx>=1.1.0      # DOCX reading/writing
python-pptx>=0.6.23     # PPTX support
openpyxl>=3.1.2         # XLSX support
pandas>=2.0.0           # CSV / tabular
beautifulsoup4>=4.12.0  # HTML parsing
lxml>=5.0.0             # XML/HTML backend

# ── Image processing ──────────────────────────────────────────────────────────
Pillow>=10.0.0
opencv-python-headless>=4.9.0  # headless for server environments

# ── PDF ───────────────────────────────────────────────────────────────────────
pypdfium2>=4.0.0        # Fast PDF rendering backend used by Docling
pdfminer.six>=20221105

# ── ML / model support ────────────────────────────────────────────────────────
torch>=2.1.0
torchvision>=0.16.0
transformers>=4.40.0
huggingface-hub>=0.20.0

# ── Misc utilities ────────────────────────────────────────────────────────────
requests>=2.31.0
tqdm>=4.66.0