Dockerfile

# 1. Start from the official NVIDIA CUDA development image. This is the key change.
FROM nvidia/cuda:12.1.1-devel-ubuntu22.04

# 2. Set up the environment to be non-interactive and add Python paths
ENV DEBIAN_FRONTEND=noninteractive
ENV PATH="/root/.local/bin:${PATH}"

# 3. Install Python 3.11, pip, and other essential tools
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3-pip \
    python-is-python3 \
    git \
    && rm -rf /var/lib/apt/lists/*

# 4. Install uv for fast package installation
RUN pip install uv

# 5. Copy requirements and install them.
# The base image is clean, so we need to install everything, including torch.
COPY requirements.txt .
RUN uv pip install --no-cache --system -r requirements.txt

# 6. Copy the application code
COPY ./app.py /app/app.py
WORKDIR /app

# 7. Expose the port
EXPOSE 7860

# 8. Run the application with uvicorn
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]