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

ENV DEBIAN_FRONTEND=noninteractive
RUN apt-get update && apt-get install -y python3 python3-pip && rm -rf /var/lib/apt/lists/*

WORKDIR /app
COPY requirements.txt ./
RUN pip3 install --no-cache-dir --upgrade pip && pip3 install --no-cache-dir -r requirements.txt

COPY . .

ENV HOST=0.0.0.0
ENV PORT=8000
EXPOSE 8000

CMD ["python3", "-m", "inference.api"]