FROM python:3.11-slim

RUN apt-get update && apt-get install -y --no-install-recommends \
    git build-essential cmake curl ca-certificates && \
    rm -rf /var/lib/apt/lists/*

WORKDIR /app

RUN git clone https://github.com/ggerganov/llama.cpp /tmp/llama.cpp && \
    cmake -S /tmp/llama.cpp -B /tmp/llama.cpp/build -DBUILD_SERVER=ON -DBUILD_SHARED_LIBS=OFF && \
    cmake --build /tmp/llama.cpp/build -j && \
    cp /tmp/llama.cpp/build/bin/llama-server /usr/local/bin/llama-server

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

ENV PORT=7860
ENV MODEL_PATH=/app/models/Qwen3.5-0.8B-Q4_K_M.gguf

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