Dockerfile

FROM python:3.11-slim

WORKDIR /app

# Build deps for llama-cpp-python
RUN apt-get update && apt-get install -y \
    build-essential cmake git curl \
    && rm -rf /var/lib/apt/lists/*

# Copy and install Python deps first (Docker layer cache)
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy app
COPY app.py .

# HF Spaces requires port 7860
EXPOSE 7860

# Startup: download model then launch API
CMD ["python", "-u", "app.py"]