# CUDA + cuDNN + Python base. Matches A10 (Ampere) on HF Spaces.
FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

# System deps marker-pdf needs at runtime: poppler for PDF rendering, plus the
# usual fonts so rasterized output looks right. ca-certs for outbound HTTPS.
RUN apt-get update && apt-get install -y --no-install-recommends \
        python3.11 python3.11-venv python3-pip \
        git \
        poppler-utils \
        libgl1 libglib2.0-0 \
        fonts-liberation fonts-dejavu-core \
        ca-certificates \
        curl \
    && rm -rf /var/lib/apt/lists/*

RUN ln -sf /usr/bin/python3.11 /usr/local/bin/python && \
    ln -sf /usr/bin/python3.11 /usr/local/bin/python3

# HF Spaces runs containers as a non-root user (UID 1000) by default. Create
# matching user so files we write at runtime have sane ownership.
RUN useradd -m -u 1000 -s /bin/bash app

# Pin every cache marker touches to /data (HF Bucket mount). Without this,
# cold starts re-download multiple GB of weights even though the bucket is
# attached:
#   HF_HOME / HF_HUB_CACHE / TRANSFORMERS_CACHE — HuggingFace Hub model cache.
#   TORCH_HOME — Torch hub checkpoints.
#   XDG_CACHE_HOME — catches anything that writes to `~/.cache/...` (e.g.
#     datalab's text-detection + OCR-error-detection models, which marker
#     pulls separately from the Hub).
#   DATALAB_CACHE_DIR — explicit datalab override, belt-and-suspenders.
ENV HF_HOME=/data/hf \
    HF_HUB_CACHE=/data/hf/hub \
    TRANSFORMERS_CACHE=/data/hf/transformers \
    TORCH_HOME=/data/torch \
    XDG_CACHE_HOME=/data/cache \
    DATALAB_CACHE_DIR=/data/datalab \
    PORT=7860

WORKDIR /app

COPY --chown=app:app requirements.txt /app/requirements.txt
RUN pip install --upgrade pip && pip install -r /app/requirements.txt

# marker-pdf calls download_font() during PdfConverter init, which writes to
# `<site-packages>/static/fonts/`. That dir doesn't exist yet and the app user
# can't create it under root-owned site-packages. Pre-create + chown so marker
# can populate it on first parse.
#
# Use `pip show` to derive the install location — robust against the python3
# / python3.10 / python3.11 split on this image (apt installs 3.11 but pip
# is bound to 3.10 where marker actually lives).
RUN STATIC_DIR="$(pip show marker-pdf | awk -F': ' '/^Location:/ {print $2 "/static"}')" \
    && mkdir -p "$STATIC_DIR/fonts" \
    && chown -R app:app "$STATIC_DIR"

COPY --chown=app:app app /app/app

USER app

EXPOSE 7860

CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860", "--timeout-keep-alive", "1800"]