# FabledCurator GPU agent — runs on the desktop with the GPU.
# CUDA + cuDNN runtime so onnxruntime-gpu can use the card (it needs cuDNN 9 —
# the plain -runtime image lacks it: "libcudnn.so.9: cannot open shared object
# file"); ffmpeg for video frames.
FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive PYTHONUNBUFFERED=1
RUN apt-get update \
    && apt-get install -y --no-install-recommends python3 python3-pip ffmpeg \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app
# torch from the CUDA-12.4 wheel index (matches the base image); its wheels
# bundle their own CUDA + cuDNN and coexist with onnxruntime-gpu. Installed
# first + separately so the GPU build of torch is deterministic and layer-cached.
RUN pip3 install --no-cache-dir torch==2.6.0 --index-url https://download.pytorch.org/whl/cu124
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt
COPY fc_agent ./fc_agent

# imgutils ONNX models + the transformers SigLIP weights both cache here; mount
# a volume to persist them across restarts (the SigLIP download is ~3.5 GB once).
ENV HF_HOME=/models
EXPOSE 8770

# The control UI; the worker is started from it (or POST /start).
CMD ["uvicorn", "fc_agent.app:app", "--host", "0.0.0.0", "--port", "8770"]