FROM python:3.11-slim

WORKDIR /app

# System deps (libgomp for ONNX Runtime, curl for health check)
RUN apt-get update && apt-get install -y --no-install-recommends \
    libgomp1 \
    curl \
    && rm -rf /var/lib/apt/lists/*

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

# Pre-download the fastembed ONNX model so cold starts don't hit the network
RUN python3 -c "from fastembed import TextEmbedding; list(TextEmbedding('BAAI/bge-small-en-v1.5').embed(['warmup']))"

# Copy app code
COPY app.py answer.py retrieval.py ./

# Copy runtime data (chroma vector store + JSONL chunks, not books)
COPY data/chroma/ ./data/chroma/
COPY data/book_chunks.jsonl ./data/book_chunks.jsonl
COPY data/presentation_chunks.jsonl ./data/presentation_chunks.jsonl
COPY data/glp/ ./data/glp/
COPY data/pali-cannon/ ./data/pali-cannon/

# Streamlit config
COPY .streamlit/ ./.streamlit/

EXPOSE 7860

HEALTHCHECK CMD curl --fail http://localhost:7860/_stcore/health || exit 1

CMD ["streamlit", "run", "app.py", \
     "--server.port=7860", \
     "--server.address=0.0.0.0", \
     "--server.headless=true", \
     "--browser.gatherUsageStats=false"]