Dockerfile

# Dockerfile
FROM python:3.12-slim

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1

# OS deps (gcc pour llama-cpp-python wheel si besoin; libgomp pour BLAS)
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential curl ca-certificates git \
  && rm -rf /var/lib/apt/lists/*

RUN useradd -m -u 1000 user
USER user
ENV PATH="/home/user/.local/bin:$PATH"

WORKDIR /app

COPY --chown=user ./requirements.txt requirements.txt
RUN pip install --upgrade pip && pip install --no-cache-dir --upgrade -r requirements.txt

RUN pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu

COPY --chown=user . .
# Crée les dossiers pour monter les volumes
RUN mkdir -p /models /hf_cache
RUN chown -R user: /models
RUN chown -R user: /hf_cache

EXPOSE 7860
ENV MODELS_DIR=/models HF_HOME=/hf_cache

CMD ["gunicorn", "-w", "1", "-b", "0.0.0.0:7860", "app:app"]