Dockerfile

# Use a Python base with high compatibility
FROM python:3.10-slim

# Install system dependencies for OCR and Image processing
RUN apt-get update && apt-get install -y \
    libgl1-mesa-glx \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Install GLM-OCR and required inference engines
RUN pip install --no-cache-dir \
    torch --index-url https://download.pytorch.org/whl/cpu \
    transformers \
    accelerate \
    einops \
    pillow \
    fastapi \
    uvicorn \
    python-multipart

# Script to pre-load the model (0.9B is ~1.8GB on disk)
RUN python3 -c "from transformers import AutoModelForCausalLM, AutoTokenizer; \
    AutoModelForCausalLM.from_pretrained('THUDM/glm-4v-9b', trust_remote_code=True)"

# Create a simple FastAPI app wrapper
COPY app.py .

EXPOSE 7860

CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]