# ---------- builder stage ----------
FROM python:3.11-slim AS builder

RUN apt-get update && \
    apt-get install -y --no-install-recommends curl ca-certificates && \
    curl -fsSL https://ollama.com/install.sh | sh && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

# ---------- runtime stage ----------
FROM python:3.11-slim

# runtime utils (ffmpeg only if you really need audio transcription)
RUN apt-get update && \
    apt-get install -y --no-install-recommends curl ca-certificates procps && \
    apt-get clean && rm -rf /var/lib/apt/lists/*

# copy ollama binary from builder
COPY --from=builder /usr/local/bin/ollama /usr/local/bin/ollama

# python deps
COPY requirements.txt /tmp/
RUN pip install --no-cache-dir -U pip && \
    pip install --no-cache-dir -r /tmp/requirements.txt

WORKDIR /code
COPY . .

ENV OLLAMA_HOST=0.0.0.0:11434
EXPOSE 7860 11434

# health-check so Docker knows when the container is really ready
HEALTHCHECK --interval=30s --timeout=3s --start-period=15s --retries=3 \
  CMD curl -f http://localhost:7860/ || exit 1

CMD bash -c "\
    ollama serve & \
    while ! curl -s http://localhost:11434/api/tags >/dev/null; do \
        echo 'waiting for ollama…'; sleep 1; done; \
    ollama pull ${OLLAMA_MODEL:-tinyllama:1.1b-chat-q4_0}; \
    exec gunicorn -b 0.0.0.0:7860 --workers 1 --timeout 120 app:app"