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

RUN apt-get update && apt-get install -y \
    git wget curl python3 python3-pip && rm -rf /var/lib/apt/lists/*

WORKDIR /app

COPY requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

COPY . /app

RUN mkdir -p /app/.cache && chmod -R 777 /app/.cache

ENV HF_HOME=/app/.cache
ENV TRANSFORMERS_CACHE=/app/.cache
ENV HF_HUB_CACHE=/app/.cache

ENV PORT=7860

CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]