Dockerfile

# Multi-stage Dockerfile for workerAI
# Optimized for production deployments

FROM python:3.11-slim as base

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    git \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

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

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

# ==================== Stage 2: Playwright Installation ====================
FROM base as playwright

# Install Playwright system dependencies
RUN apt-get update && apt-get install -y \
    libnss3 \
    libnspr4 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcups2 \
    libdrm2 \
    libdbus-1-3 \
    libxkbcommon0 \
    libxcomposite1 \
    libxdamage1 \
    libxfixes3 \
    libxrandr2 \
    libgbm1 \
    libasound2 \
    libpangocairo-1.0-0 \
    libpango-1.0-0 \
    libcairo2 \
    libatspi2.0-0 \
    libxshmfence1 \
    && rm -rf /var/lib/apt/lists/*

# Install Playwright browsers
RUN playwright install chromium

# ==================== Stage 3: Model Downloading ====================
FROM playwright as models

# Create model cache directory
RUN mkdir -p /app/models

# Pre-download embedding model
RUN python -c "import os; os.environ['SENTENCE_TRANSFORMERS_HOME'] = '/app/models'; from sentence_transformers import SentenceTransformer; SentenceTransformer('all-MiniLM-L6-v2')"

# ==================== Stage 4: Final Application ====================
FROM models as final

# Copy application code
COPY . .

# Create necessary directories
RUN mkdir -p \
    /app/data/chroma_db \
    /app/workspace \
    /app/logs \
    /app/models

# Create non-root user for security
RUN useradd -m -u 1000 workerai && \
    chown -R workerai:workerai /app

# Switch to non-root user
USER workerai

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    SENTENCE_TRANSFORMERS_HOME=/app/models \
    ENVIRONMENT=production \
    LOG_JSON_FORMAT=true

# Expose ports
# 8001: Prometheus metrics
# 8002: Health checks
EXPOSE 8001 8002

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD curl -f http://localhost:8002/health || exit 1

# Default command (can be overridden)
CMD ["python", "-u", "main.py"]