Dockerfile

FROM python:3.11-slim

ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV OLLAMA_HOST=0.0.0.0:11434
ENV OLLAMA_ORIGINS="*"
ENV OLLAMA_MODELS=/data/ollama_models

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

# Download Ollama v0.3.4 binary (pre-compiled, 283MB, zero build time)
RUN wget -q https://github.com/ollama/ollama/releases/download/v0.3.4/ollama-linux-amd64 \
    -O /usr/local/bin/ollama && chmod +x /usr/local/bin/ollama

RUN pip install --no-cache-dir starlette uvicorn huggingface_hub httpx

WORKDIR /app
COPY app.py /app/app.py

EXPOSE 7860

HEALTHCHECK --interval=60s --timeout=30s --start-period=1800s --retries=3 \
    CMD curl -sf http://localhost:7860/health || exit 1

CMD ["python3", "/app/app.py"]