Dockerfile

# SPARKNET Dockerfile
# Multi-stage build for optimized production image

# ============== Build Stage ==============
FROM python:3.11-slim as builder

WORKDIR /app

# Install build dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    gcc \
    g++ \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for caching
COPY requirements.txt .
COPY api/requirements.txt ./api_requirements.txt

# Create virtual environment and install dependencies
RUN python -m venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt && \
    pip install --no-cache-dir -r api_requirements.txt

# ============== Production Stage ==============
FROM python:3.11-slim as production

LABEL maintainer="SPARKNET Team"
LABEL description="SPARKNET: Multi-Agentic Document Intelligence Platform"
LABEL version="1.0.0"

WORKDIR /app

# Install runtime dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    # PDF processing
    poppler-utils \
    libpoppler-cpp-dev \
    # Image processing
    libgl1-mesa-glx \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    # OCR support
    tesseract-ocr \
    tesseract-ocr-eng \
    # Utilities
    curl \
    wget \
    && rm -rf /var/lib/apt/lists/*

# Copy virtual environment from builder
COPY --from=builder /opt/venv /opt/venv
ENV PATH="/opt/venv/bin:$PATH"

# Set Python environment
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PYTHONPATH=/app

# Copy application code
COPY src/ ./src/
COPY api/ ./api/
COPY config/ ./config/
COPY demo/ ./demo/

# Create necessary directories
RUN mkdir -p /app/data/vectorstore \
    /app/data/embedding_cache \
    /app/uploads/documents \
    /app/uploads/patents \
    /app/outputs \
    /app/logs

# Set permissions
RUN chmod -R 755 /app

# Expose ports
# 8000 - FastAPI
# 4000 - Streamlit
EXPOSE 8000 4000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:8000/api/health || exit 1

# Default command - run FastAPI
CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000"]

# ============== Development Stage ==============
FROM production as development

# Install development dependencies
RUN pip install --no-cache-dir \
    pytest \
    pytest-asyncio \
    pytest-cov \
    black \
    flake8 \
    mypy \
    ipython \
    jupyter

# Development command with hot reload
CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]