Init

requirements.txt

@@ -0,0 +1,45 @@
+# Core dependencies
+ultralytics>=8.0.0        # YOLOv8
+pytesseract>=0.3.10       # Tesseract OCR Python wrapper
+
+# Image processing
+pdf2image>=1.16.0         # PDF to image conversion
+Pillow>=10.0.0            # Image manipulation
+opencv-python>=4.8.0      # Computer vision
+
+# Data handling
+numpy>=1.24.0
+pandas>=2.0.0
+scikit-learn>=1.3.0       # For DBSCAN clustering in 02_create_labels.py
+
+# API dependencies (for main.py)
+fastapi>=0.104.0          # FastAPI web framework
+uvicorn>=0.24.0           # ASGI server
+python-multipart>=0.0.6   # For file upload support
+
+# System utilities
+# IMPORTANT: Requires system-level installation of:
+#
+# 1. Tesseract OCR:
+#    - Windows: Download from https://github.com/UB-Mannheim/tesseract/wiki
+#              After installation, add to PATH or set: pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
+#    - Linux: sudo apt-get install tesseract-ocr tesseract-ocr-swe tesseract-ocr-eng
+#    - macOS: brew install tesseract tesseract-lang
+#
+# 2. Poppler (for pdf2image):
+#    - Windows: Download from https://github.com/oschwartz10612/poppler-windows/releases
+#    - Linux: sudo apt-get install poppler-utils
+#    - macOS: brew install poppler
+#
+# 3. Swedish language data for Tesseract:
+#    After installing Tesseract, you may need to download Swedish language files (swe.traineddata)
+#    from https://github.com/tesseract-ocr/tessdata
+
+# Optional: GPU support
+# torch>=2.0.0              # PyTorch with CUDA support
+# torchvision>=0.15.0
+
+# Development tools (optional)
+# jupyter>=1.0.0
+# matplotlib>=3.7.0
+# seaborn>=0.12.0