Dockerfile

# GNoME Materials Discovery MCP Service
# Dockerfile for HuggingFace Spaces Deployment

# Use Python 3.11 slim image
FROM python:3.11-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PYTHONIOENCODING=utf-8 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    GNOME_DATA_DIR=/app/gnome_data \
    GNOME_MODEL_DIR=/app/models \
    HF_HOME=/app/huggingface

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    wget \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/*

# Create app directory
WORKDIR /app

# Create data directories first
RUN mkdir -p /app/gnome_data /app/models

# Copy requirements first for better caching
COPY requirements.txt .

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Download core dataset during Docker build
# This ensures data is available immediately when Space starts
RUN echo "Downloading GNoME core dataset..." && \
    python download_data.py && \
    echo "Dataset download complete!"

# Expose port for SSE
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# Run the MCP server
CMD ["python", "entrypoint.py"]