Dockerfile

# Hugging Face Spaces Dockerfile
FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies including GDAL for contextily/maps
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    gdal-bin \
    libgdal-dev \
    python3-gdal \
    && rm -rf /var/lib/apt/lists/*

# Set GDAL environment variables
ENV GDAL_CONFIG=/usr/bin/gdal-config
ENV CPLUS_INCLUDE_PATH=/usr/include/gdal
ENV C_INCLUDE_PATH=/usr/include/gdal

# Copy requirements
COPY requirements.txt .

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

# Copy application code
COPY . .

# Create data directory in a writable location for HF Spaces
# HF Spaces has persistent storage at /data
RUN mkdir -p /data && chmod 777 /data

# Create cache directory for Hugging Face models
RUN mkdir -p /data/.cache/huggingface && chmod -R 777 /data/.cache

# Create models directory for fine-tuned models
RUN mkdir -p /data/models/finetuned && chmod -R 777 /data/models

# Create model cache in container (not in /data) to save persistent storage
RUN mkdir -p /app/.cache && chmod -R 777 /app/.cache

# Create matplotlib config directory (prevent permission errors)
RUN mkdir -p /tmp/matplotlib && chmod 777 /tmp/matplotlib
ENV MPLCONFIGDIR=/tmp/matplotlib

# Pre-download models into container image to avoid using /data storage
ENV HF_HOME=/app/.cache/huggingface

# Download zero-shot models (for immediate analysis capability)
# These are loaded on first analysis, pre-downloading saves time and /data space
RUN python -c "from transformers import pipeline; \
    print('Downloading BART-large-MNLI...'); \
    pipeline('zero-shot-classification', model='facebook/bart-large-mnli', device=-1); \
    print('Downloading DeBERTa-v3-base-MNLI...'); \
    pipeline('zero-shot-classification', model='MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli', device=-1); \
    print('Downloading DistilBART-MNLI...'); \
    pipeline('zero-shot-classification', model='valhalla/distilbart-mnli-12-3', device=-1); \
    print('All models downloaded successfully')" \
    && chmod -R 777 /app/.cache

# Hugging Face Spaces uses port 7860
EXPOSE 7860

# Set runtime environment variables
ENV FLASK_ENV=production
ENV PYTHONUNBUFFERED=1
ENV PORT=7860
ENV DATABASE_PATH=/data/app.db
# Keep model cache in container, only store database and fine-tuned models in /data
ENV HF_HOME=/app/.cache/huggingface
ENV HUGGINGFACE_HUB_CACHE=/app/.cache/huggingface

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
  CMD curl -f http://localhost:7860/login || exit 1

# Run the application
CMD ["python", "app_hf.py"]