Dockerfile

FROM python:3.11-slim

# Install system dependencies
# libgl1-mesa-glx is obsolete in newer Debian (Trixie), replaced by libgl1 and libglx-mesa0
RUN apt-get update && apt-get install -y \
    git \
    wget \
    libgl1 \
    libglx-mesa0 \
    libglib2.0-0 \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Set working directory
WORKDIR /app

# Copy the GroundingDINO code first
RUN git clone https://github.com/IDEA-Research/GroundingDINO.git .

# Install dependencies and the package
RUN pip install --no-cache-dir torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
RUN pip install --no-cache-dir transformers==4.35.2
RUN pip install --no-cache-dir fastapi uvicorn python-multipart supervision opencv-python-headless huggingface_hub

# Install GroundingDINO package without CUDA extensions for CPU mode
ENV CUDA_HOME=""
RUN pip install --no-cache-dir -e .

# Create weights directory and download Swin-B weights
RUN mkdir -p weights && \
    wget -q -O weights/groundingdino_swinb_cogcoor.pth https://github.com/IDEA-Research/GroundingDINO/releases/download/v0.1.0-alpha2/groundingdino_swinb_cogcoor.pth && \
    cp groundingdino/config/GroundingDINO_SwinB_cfg.py weights/GroundingDINO_SwinB_cfg.py

# Copy the application code
COPY main.py .

# Expose port 7860 (Hugging Face Spaces default)
EXPOSE 7860

# Run the application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]