Dockerfile

FROM python:3.10-bookworm

# Install system dependencies for Tesseract and OpenCV
# Using bookworm ensures stable apt repositories
RUN apt-get update && apt-get install -y --no-install-recommends \
    tesseract-ocr \
    libgl1-mesa-glx \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy requirements
COPY requirements.txt .

# Install CPU only versions of torch and torchvision first to avoid massive CUDA downloads
RUN pip install --no-cache-dir torch torchvision --index-url https://download.pytorch.org/whl/cpu
RUN pip install --no-cache-dir -r requirements.txt
# Copy source code
COPY . .

# Create necessary directories for storage
RUN mkdir -p /app/storage/uploads /app/storage/processed

# Default command (overridden by docker-compose)
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]