Dockerfile

FROM python:3.12-slim

WORKDIR /app

RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential && rm -rf /var/lib/apt/lists/*

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

# Pre-download models so they're cached in the image layer
RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('all-MiniLM-L6-v2')"
RUN python -c "from flashrank import Ranker; Ranker(model_name='ms-marco-MiniLM-L-12-v2')"

COPY . .

EXPOSE 7860

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