Dockerfile

FROM python:3.11-slim

WORKDIR /app

# Install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy the Python package
COPY data_cleaning_env/ ./data_cleaning_env/

# Copy root-level files needed at runtime
COPY inference.py .
COPY openenv.yaml .

# Pre-download datasets at build time to avoid runtime downloads
ENV PYTHONPATH=/app
RUN python -c "from data_cleaning_env.datasets import preload_all; preload_all()"

EXPOSE 7860

ENV PYTHONPATH=/app
CMD ["uvicorn", "data_cleaning_env.server.app:app", "--host", "0.0.0.0", "--port", "7860"]