Dockerfile

FROM python:3.10-slim

WORKDIR /app

# Install minimal system dependencies (OpenBLAS + OpenMP for the prebuilt wheel)
RUN apt-get update && apt-get install -y \
    libopenblas-dev \
    libopencc-dev \
    libgomp1 \
    && rm -rf /var/lib/apt/lists/*

# Install llama-cpp-python from prebuilt wheel (FAST - no build needed!)
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

# Copy and install other requirements
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application files
COPY app.py .
COPY meeting_summarizer/ meeting_summarizer/

# Pre-download model on build (optional, speeds up first run)
# RUN python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='unsloth/Qwen3-0.6B-GGUF', filename='Qwen3-0.6B-Q4_K_M.gguf', local_dir='./models')"

EXPOSE 7860
# Cache bust: 2026-02-01-v1

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