Dockerfile

FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    HF_HOME=/tmp/huggingface \
    TRANSFORMERS_CACHE=/tmp/huggingface/transformers \
    HF_HUB_CACHE=/tmp/huggingface/hub

RUN apt-get update && apt-get install -y python3 python3-pip git && rm -rf /var/lib/apt/lists/*
WORKDIR /app

# Create writable cache directories for HuggingFace
RUN mkdir -p /tmp/huggingface && chmod -R 777 /tmp/huggingface

COPY requirements.txt /app/
RUN python3 -m pip install --upgrade pip && pip3 install -r requirements.txt

COPY app.py /app/

# Spaces exposes the app on $PORT
ENV PORT=7860
EXPOSE 7860
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]