Dockerfile

FROM python:3.11-slim

# Install Tesseract OCR + system deps
RUN apt-get update && \
    apt-get install -y --no-install-recommends \
        tesseract-ocr \
        libgl1 \
        libglib2.0-0 && \
    rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install Python deps first (layer caching)
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy project files
COPY . .

# Train the model at build time (generates weights)
RUN python -m src.train

# HF Spaces expects port 7860
EXPOSE 7860

CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "7860"]