Dockerfile

FROM python:3.10-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    gcc g++ make cmake git libopenblas-dev \
    && rm -rf /var/lib/apt/lists/*

# Install optimized llama-cpp-python wheel for CPU
RUN pip install --no-cache-dir \
    https://huggingface.co/Luigi/llama-cpp-python-wheels-hf-spaces-free-cpu/resolve/main/llama_cpp_python-0.3.22-cp310-cp310-linux_x86_64.whl

# Install other dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Strict threading limits for 2 vCPU environment
ENV PYTHONUNBUFFERED=1
ENV GRADIO_SERVER_NAME=0.0.0.0
ENV OMP_NUM_THREADS=2
ENV MKL_NUM_THREADS=2
ENV OPENBLAS_NUM_THREADS=2
ENV LLAMA_CPP_LOG_DISABLE=1

# Expose Gradio port
EXPOSE 7860

CMD ["python", "app.py"]