Dockerfile

FROM pytorch/pytorch:2.2.0-cuda12.1-cudnn8-runtime

ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    TRANSFORMERS_CACHE=/cache

RUN apt-get update && apt-get install -y --no-install-recommends \
    gcc \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

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

COPY . .

EXPOSE 7860

CMD ["sh", "-c", "uvicorn main:app --host 0.0.0.0 --port ${PORT:-7860}"]