# syntax=docker/dockerfile:1
FROM python:3.12-slim

ENV DEBIAN_FRONTEND=noninteractive

# Build & runtime deps for llama-cpp-python (CPU, OpenBLAS)
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential cmake git curl ca-certificates \
    libopenblas-dev && \
    rm -rf /var/lib/apt/lists/*

# Writable home and cache locations
ENV HOME=/app \
    HF_HOME=/app/hf_cache \
    HF_HUB_CACHE=/app/hf_cache \
    XDG_CACHE_HOME=/app/.cache
RUN mkdir -p /app /app/hf_cache /app/.cache && chmod -R 777 /app

# Workdir
WORKDIR /app

# Python deps
COPY requirements.txt /app/requirements.txt
RUN pip install --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt && \
    CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" \
    pip install --no-cache-dir llama-cpp-python==0.2.90

# App
COPY app.py /app/app.py
COPY README.md /app/README.md

# Gradio port
EXPOSE 7860

ENV GRADIO_SERVER_NAME=0.0.0.0 \
    GRADIO_SERVER_PORT=7860

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