requirements.txt

# --- API ---
fastapi==0.95.2
uvicorn==0.22.0
pydantic==1.8.2
python-multipart==0.0.6
python-dotenv==1.0.0

# --- OCR / imaging ---
pytesseract==0.3.10
Pillow==10.0.0
opencv-python-headless==4.7.0.72
PyMuPDF==1.22.5

# --- NLP ---
spacy==3.2.4
thinc==8.0.17                 # pin to match spaCy 3.2.x
typing-extensions==4.5.0      # avoids the issubclass/type-check blowup
negspacy==1.0.2
fuzzywuzzy==0.18.0
python-Levenshtein==0.21.1
regex==2023.8.8

# --- Transformers / Torch ---
transformers==4.32.1
tokenizers==0.13.3
torch==2.0.1

# --- Data ---
pandas==2.0.3
numpy==1.25.2

# --- Cloud / APIs ---
firebase-admin==5.1.0
google-generativeai==0.3.1

PyMuPDF==1.22.5 #fitz