Dockerfile

FROM ollama/ollama:latest

ENV OLLAMA_HOST=0.0.0.0
ENV OLLAMA_LLM_LIBRARY=cpu
ENV PYTHONUNBUFFERED=1
ENV OLLAMA_KEEP_ALIVE=-1
ENV OLLAMA_MAX_LOADED_MODELS=2
ENV OLLAMA_NUM_PARALLEL=1
ENV OLLAMA_NUM_THREADS=2
ENV OLLAMA_CONTEXT_LENGTH=4096
ENV OLLAMA_FLASH_ATTENTION=1
ENV OLLAMA_ORIGINS=*
ENV USE_LLAMA_CPP=false

USER root

# ✅ Minimal deps only — no build tools needed
RUN apt-get update && apt-get install -y \
    python3 python3-pip curl \
    && rm -rf /var/lib/apt/lists/*

# ✅ All Python deps — fast, no compilation
RUN pip3 install --no-cache-dir --break-system-packages \
    flask flask-cors requests ollama \
    Pillow pandas openpyxl PyPDF2 python-docx \
    beautifulsoup4 lxml huggingface_hub \
    openai anthropic

# ✅ Bake router model
RUN ollama serve & \
    OLLAMA_PID=$! && \
    until curl -s http://localhost:11434/api/tags > /dev/null 2>&1; do sleep 2; done && \
    ollama pull qwen3:0.6b && \
    kill $OLLAMA_PID && \
    wait $OLLAMA_PID 2>/dev/null || true

WORKDIR /app
COPY . .
RUN chmod +x start.sh

EXPOSE 7860
ENTRYPOINT ["/bin/bash", "/app/start.sh"]