Dockerfile

FROM python:3.11-slim

# Install system dependencies for compiling GGUF/llama.cpp runtime
RUN apt-get update && apt-get install -y \
    build-essential \
    cmake \
    git \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Set up a new user named "user" with UID 1000 (Hugging Face convention)
RUN useradd -m -u 1000 user

# Setup writeable cache directories under /tmp
ENV HOME=/tmp \
    HF_HOME=/tmp/huggingface_cache \
    XDG_CACHE_HOME=/tmp/cache \
    TORCH_EXTENSIONS_DIR=/tmp/torch_extensions \
    TRITON_CACHE_DIR=/tmp/triton_cache \
    PORT=7860

WORKDIR /code

# Copy and install Python dependencies
COPY requirements.txt /code/requirements.txt
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt

# Copy code with ownership
COPY --chown=user:user . /code

# Set user to 1000
USER user

EXPOSE 7860

# Run with single Uvicorn worker as per model API specifications
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]