crawl4ai/deploy/docker/Dockerfile

FROM python:3.10-slim

# Set build arguments
ARG APP_HOME=/app
ARG GITHUB_REPO=https://github.com/yourusername/crawl4ai.git
ARG GITHUB_BRANCH=main
ARG USE_LOCAL=false

# 🤓 Environment variables - because who doesn't love a good ENV party?
ENV PYTHONFAULTHANDLER=1 \
    PYTHONHASHSEED=random \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1 \
    PIP_DEFAULT_TIMEOUT=100 \
    DEBIAN_FRONTEND=noninteractive

# Other build arguments
ARG PYTHON_VERSION=3.10
ARG INSTALL_TYPE=default
ARG ENABLE_GPU=false
ARG TARGETARCH

# 🎯 Platform-specific labels - because even containers need ID badges
LABEL maintainer="unclecode"
LABEL description="🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & scraper"
LABEL version="1.0"    

# 📦 Installing system dependencies... please hold, your package is being delivered
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    curl \
    wget \
    gnupg \
    git \
    cmake \
    pkg-config \
    python3-dev \
    libjpeg-dev \
    && rm -rf /var/lib/apt/lists/*

# 🎭 Playwright dependencies - because browsers need their vitamins too
RUN apt-get update && apt-get install -y --no-install-recommends \
    libglib2.0-0 \
    libnss3 \
    libnspr4 \
    libatk1.0-0 \
    libatk-bridge2.0-0 \
    libcups2 \
    libdrm2 \
    libdbus-1-3 \
    libxcb1 \
    libxkbcommon0 \
    libx11-6 \
    libxcomposite1 \
    libxdamage1 \
    libxext6 \
    libxfixes3 \
    libxrandr2 \
    libgbm1 \
    libpango-1.0-0 \
    libcairo2 \
    libasound2 \
    libatspi2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# 🎮 GPU support - because sometimes CPU just doesn't cut it
RUN if [ "$ENABLE_GPU" = "true" ] && [ "$TARGETARCH" = "amd64" ] ; then \
    apt-get update && apt-get install -y --no-install-recommends \
    nvidia-cuda-toolkit \
    && rm -rf /var/lib/apt/lists/* ; \
else \
    echo "Skipping NVIDIA CUDA Toolkit installation (unsupported platform or GPU disabled)"; \
fi

# 🏗️ Platform-specific optimizations - because one size doesn't fit all
RUN if [ "$TARGETARCH" = "arm64" ]; then \
    echo "🦾 Installing ARM-specific optimizations"; \
    apt-get update && apt-get install -y --no-install-recommends \
    libopenblas-dev \
    && rm -rf /var/lib/apt/lists/*; \
elif [ "$TARGETARCH" = "amd64" ]; then \
    echo "🖥️ Installing AMD64-specific optimizations"; \
    apt-get update && apt-get install -y --no-install-recommends \
    libomp-dev \
    && rm -rf /var/lib/apt/lists/*; \
fi

WORKDIR ${APP_HOME}

# 🔄 Installation script - now with retry logic because sometimes Git needs a coffee break
RUN echo '#!/bin/bash\n\
if [ "$USE_LOCAL" = "true" ]; then\n\
    echo "📦 Installing from local source..."\n\
    pip install --no-cache-dir /tmp/project/\n\
else\n\
    echo "🌐 Installing from GitHub..."\n\
    for i in {1..3}; do \n\
        git clone --branch ${GITHUB_BRANCH} ${GITHUB_REPO} /tmp/crawl4ai && break || \n\
        { echo "Attempt $i/3 failed! Taking a short break... ☕"; sleep 5; }; \n\
    done\n\
    pip install --no-cache-dir /tmp/crawl4ai\n\
fi' > /tmp/install.sh && chmod +x /tmp/install.sh

# Copy local project if USE_LOCAL is true
COPY . /tmp/project/

# Copy and install other requirements
COPY deploy/docker/requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Install ML dependencies first for better layer caching
RUN if [ "$INSTALL_TYPE" = "all" ] ; then \
        pip install --no-cache-dir \
            torch \
            torchvision \
            torchaudio \
            scikit-learn \
            nltk \
            transformers \
            tokenizers && \
        python -m nltk.downloader punkt stopwords ; \
    fi

# Install the package
RUN if [ "$INSTALL_TYPE" = "all" ] ; then \
        pip install "/tmp/project/[all]" && \
        python -m crawl4ai.model_loader ; \
    elif [ "$INSTALL_TYPE" = "torch" ] ; then \
        pip install "/tmp/project/[torch]" ; \
    elif [ "$INSTALL_TYPE" = "transformer" ] ; then \
        pip install "/tmp/project/[transformer]" && \
        python -m crawl4ai.model_loader ; \
    else \
        pip install "/tmp/project" ; \
    fi
    
    # 🚀 Installation validation - trust but verify!
RUN pip install --no-cache-dir --upgrade pip && \
    /tmp/install.sh && \
    python -c "import crawl4ai; print('✅ crawl4ai is ready to rock!')" && \
    python -c "from playwright.sync_api import sync_playwright; print('✅ Playwright is feeling dramatic!')"
    
RUN playwright install --with-deps chromium

# Copy application files
COPY deploy/docker/* ${APP_HOME}/

# 🏥 Health check - now with memory validation!
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD bash -c '\
    MEM=$(free -m | awk "/^Mem:/{print \$2}"); \
    if [ $MEM -lt 2048 ]; then \
        echo "⚠️ Warning: Less than 2GB RAM available! Your container might need a memory boost! 🚀"; \
        exit 1; \
    fi && \
    curl -f http://localhost:8000/health || exit 1'

# Entrypoint script
COPY deploy/docker/docker-entrypoint.sh /usr/local/bin/
RUN chmod +x /usr/local/bin/docker-entrypoint.sh
ENTRYPOINT ["docker-entrypoint.sh"]

# Default command - may the server be with you! 🚀
CMD ["gunicorn", \
    "--bind", "0.0.0.0:8000", \
    "--workers", "4", \
    "--threads", "2", \
    "--timeout", "120", \
    "--graceful-timeout", "30", \
    "--log-level", "info", \
    "--worker-class", "uvicorn.workers.UvicornWorker", \
    "server:app"]