FROM python:3.10-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    wget \
    libgomp1 \
    libopenblas0 \
    && rm -rf /var/lib/apt/lists/*

# Install llama-cpp-python with pre-built wheel (Luigi repo)
RUN pip install https://huggingface.co/Luigi/llama-cpp-python-wheels-hf-spaces-free-cpu/resolve/main/llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl

# Install Gradio and other UI dependencies
RUN pip install gradio numpy

# Download the model (Qwen 2.5 7B Instruct Quantized Q4_K_M)
RUN wget https://huggingface.co/bartowski/Qwen2.5-7B-Instruct-GGUF/resolve/main/Qwen2.5-7B-Instruct-Q4_K_M.gguf -O model.gguf

COPY app.py .

EXPOSE 7860

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