FROM python:3.11-slim

# System deps: Tesseract (OCR) + Poppler (PDF rasterization for scanned PDFs)
RUN apt-get update && apt-get install -y --no-install-recommends \
        tesseract-ocr \
        poppler-utils \
        libgl1 \
        libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

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

# Pre-download the embedding model at build time so the first request is fast.
RUN python -c "from fastembed import TextEmbedding; TextEmbedding(model_name='BAAI/bge-small-en-v1.5')"

COPY app ./app
COPY static ./static

# Most PaaS platforms inject $PORT; default to 8000 locally.
ENV PORT=8000
EXPOSE 8000

CMD ["sh", "-c", "uvicorn app.main:app --host 0.0.0.0 --port ${PORT}"]