# syntax=docker/dockerfile:1
FROM python:3.12-slim AS base

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    ML_MODEL_DIR=/models

# System deps: Pillow / image handling + psycopg2 runtime libpq + ffmpeg for
# video frame sampling (WD14+SigLIP inference on videos calls ffprobe/ffmpeg).
RUN apt-get update && apt-get install -y --no-install-recommends \
        libgl1 \
        libglib2.0-0 \
        libpq5 \
        ffmpeg \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install PyTorch CPU wheel first from its dedicated index to avoid pulling CUDA libs.
# Floor only — buildkit will pick the latest matching CPU wheel; keep this above the app-deps
# layer so transformers on PyPI doesn't accidentally resolve a mismatched torch.
RUN pip install --no-cache-dir \
        --index-url https://download.pytorch.org/whl/cpu \
        "torch>=2.5"

# Install ML requirements. Models are NOT baked in — the entrypoint fetches them
# at container start into the ${ML_MODEL_DIR} volume, and huggingface_hub's
# content-based integrity check makes subsequent starts a no-op.
COPY requirements-ml.txt /app/requirements-ml.txt
RUN pip install --no-cache-dir -r requirements-ml.txt

# Copy application code (needed so Celery can import app.tasks.ml and app.ml).
# config.py lives at the repo root and is imported by app/__init__.py via 'config.Config'.
COPY app /app/app
COPY config.py /app/config.py
COPY scripts/ensure_models.py /app/scripts/ensure_models.py
COPY scripts/entrypoint-ml.sh /app/scripts/entrypoint-ml.sh
RUN chmod +x /app/scripts/entrypoint-ml.sh && mkdir -p ${ML_MODEL_DIR}

ENTRYPOINT ["/app/scripts/entrypoint-ml.sh"]
CMD ["celery", "-A", "app.celery_app:celery", "worker", "--loglevel=info", "-Q", "ml", "--concurrency=1"]