Dockerfile

FROM python:3.10-slim

WORKDIR /app

# Install system dependencies for FAISS, PyTorch, and spaCy
RUN apt-get update && apt-get install -y \
    build-essential \
    git \
    curl \
    wget \
    cmake \
    libopenblas-dev \
    libomp-dev \
    && rm -rf /var/lib/apt/lists/*

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

# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt \
    && python -m spacy download en_core_web_sm

# Copy application code
COPY . .

# Create persistent storage directories for Hugging Face Spaces
RUN mkdir -p /data/artifacts \
    && mkdir -p /cache/models \
    && ln -sf /data/artifacts artifacts  # Symlink to persistent storage

# Set environment variables for Hugging Face Spaces
ENV ARTIFACT_DIR=/data/artifacts \
    HF_HOME=/cache/models \
    TRANSFORMERS_CACHE=/cache/models \
    GRADIO_SERVER_NAME=0.0.0.0 \
    GRADIO_SERVER_PORT=7860 \
    PYTHONUNBUFFERED=1

# Expose port for Gradio
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:7860', timeout=10)"

# Run the application with pre-build step - USING build.py
CMD ["sh", "-c", "python build.py && python app.py"]