FROM python:3.11-slim

LABEL maintainer="All API Collection"
LABEL description="All API Collection - Document extraction, conversion, and database query API"
LABEL version="1.0.0"

RUN apt-get update && apt-get install -y --no-install-recommends \
    curl \
    ffmpeg \
    libmagic1 \
    nodejs \
    && rm -rf /var/lib/apt/lists/*

RUN groupadd --gid 1000 appuser && \
    useradd --uid 1000 --gid appuser --shell /bin/bash --create-home appuser

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu && \
    python -m spacy download en_core_web_sm

COPY --chown=appuser:appuser . .

RUN mkdir -p /app/models && python3 -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='ibm-granite/granite-embedding-small-english-r2', local_dir='/app/models/bge-384')" && chown -R appuser:appuser /app/models

RUN mkdir -p /app/logs && \
    chown -R appuser:appuser /app/logs

RUN chmod +x /app/start.sh

USER appuser

ENV PYTHONPATH=/app
ENV PYTHONUNBUFFERED=1

EXPOSE 7860

HEALTHCHECK --interval=30s --timeout=10s --start-period=30s --retries=3 \
    CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/health')" || exit 1

CMD ["/bin/bash", "/app/start.sh"]