Dockerfile

FROM docker.io/nvidia/cuda:12.2.2-runtime-ubuntu22.04

USER root

# Set environment variables for cache directories
ENV MPLCONFIGDIR=/tmp/matplotlib \
    TRANSFORMERS_CACHE=/tmp/huggingface \
    HUGGINGFACE_HUB_CACHE=/tmp/huggingface \
    DEBIAN_FRONTEND=noninteractive

# Install system dependencies
RUN chmod 1777 /tmp \
    && apt-get update -q \
    && apt-get install -y --no-install-recommends \
        ca-certificates \
        wget \
        libgl1 \
        python3 \
        python3-pip \
        libglib2.0-0 \
        git \
    # Install OpenSSL 1.1
    && wget http://archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb \
    && dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb \
    && rm libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb \
    # Install CUDA repositories
    && wget -qO /tmp/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb \
    && dpkg -i /tmp/cuda-keyring.deb \
    && apt-get update -q \
    && apt-get install -y --no-install-recommends \
        libcudnn8 \
        libcublas-12-2 \
    # Clean up
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/* \
    # Create cache directories
    && mkdir -p ${MPLCONFIGDIR} ${TRANSFORMERS_CACHE} \
    && chmod -R 777 /tmp

# Install Python dependencies
COPY requirements.txt .
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy application code
COPY main.py .

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