FROM python:3.11-slim

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

WORKDIR /app

RUN git clone --depth 1 https://github.com/ggml-org/llama.cpp /src && \
    cmake -S /src -B /src/build -DCMAKE_BUILD_TYPE=Release && \
    cmake --build /src/build --target llama-server -j2 && \
    find /src/build -type f \( -name '*.so' -o -name '*.so.*' \) -exec cp {} /usr/local/lib/ \; && \
    ldconfig && \
    test -f /src/build/bin/llama-server

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

COPY app.py .
COPY models ./models

ENV PORT=7860
ENV MODEL_PATH=/app/models/Qwen3.5-0.8B-Q8_0.gguf
ENV LLAMA_SERVER=/src/build/bin/llama-server

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