# PaddleOCR-VL GPU Variant (Transformers-based, not vLLM)
# Vision-Language Model for document parsing using transformers with CUDA
FROM nvidia/cuda:12.4.0-runtime-ubuntu22.04

LABEL maintainer="Task Venture Capital GmbH <hello@task.vc>"
LABEL description="PaddleOCR-VL 0.9B GPU - Vision-Language Model using transformers"
LABEL org.opencontainers.image.source="https://code.foss.global/host.today/ht-docker-ai"

# Environment configuration
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1
ENV HF_HOME=/root/.cache/huggingface
ENV SERVER_PORT=8000
ENV SERVER_HOST=0.0.0.0

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    python3.11 \
    python3.11-venv \
    python3.11-dev \
    python3-pip \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libgomp1 \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/* \
    && update-alternatives --install /usr/bin/python python /usr/bin/python3.11 1 \
    && update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1

# Create and activate virtual environment
RUN python -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

# Install PyTorch with CUDA support
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir \
    torch==2.5.1 \
    torchvision \
    --index-url https://download.pytorch.org/whl/cu124

# Install Python dependencies (transformers-based, not vLLM)
RUN pip install --no-cache-dir \
    transformers \
    accelerate \
    safetensors \
    pillow \
    fastapi \
    uvicorn[standard] \
    python-multipart \
    httpx \
    protobuf \
    sentencepiece \
    einops

# Copy server files (same as CPU variant - it auto-detects CUDA)
COPY image_support_files/paddleocr_vl_server.py /app/paddleocr_vl_server.py
COPY image_support_files/paddleocr-vl-cpu-entrypoint.sh /usr/local/bin/paddleocr-vl-entrypoint.sh
RUN chmod +x /usr/local/bin/paddleocr-vl-entrypoint.sh

# Expose API port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=300s --retries=3 \
    CMD curl -f http://localhost:8000/health || exit 1

ENTRYPOINT ["/usr/local/bin/paddleocr-vl-entrypoint.sh"]