Create Dockerfile

Dockerfile

@@ -0,0 +1,122 @@
+# Use Ubuntu as base image for better Docker-in-Docker support
+FROM ubuntu:22.04
+
+# Avoid prompts from apt
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    curl \
+    git \
+    sudo \
+    ca-certificates \
+    gnupg \
+    lsb-release \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Docker
+RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg \
+    && echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null \
+    && apt-get update \
+    && apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user
+RUN useradd -m -s /bin/bash -u 1001 firecrawl \
+    && usermod -aG docker firecrawl \
+    && echo 'firecrawl ALL=(ALL) NOPASSWD: /usr/bin/dockerd' >> /etc/sudoers
+
+# Set working directory
+WORKDIR /home/firecrawl
+
+# Switch to non-root user for cloning
+USER firecrawl
+
+# Clone Firecrawl repository
+RUN git clone https://github.com/mendableai/firecrawl.git /home/firecrawl/firecrawl
+
+# Set working directory to firecrawl
+WORKDIR /home/firecrawl/firecrawl
+
+# Copy .env.example to .env in the API directory
+RUN if [ -f apps/api/.env.example ]; then \
+        cp apps/api/.env.example apps/api/.env; \
+    fi
+
+# Create startup script
+USER root
+RUN cat > /start-firecrawl.sh << 'EOF'
+#!/bin/bash
+set -e
+
+echo "🔥 Starting Firecrawl Self-Host Setup 🔥"
+echo "==========================================="
+
+# Start Docker daemon in background if not running
+if ! pgrep dockerd > /dev/null; then
+    echo "Starting Docker daemon..."
+    sudo dockerd --host=unix:///var/run/docker.sock --host=tcp://0.0.0.0:2376 &
+    sleep 5
+fi
+
+# Wait for Docker to be ready
+echo "Waiting for Docker to be ready..."
+timeout=30
+while [ $timeout -gt 0 ]; do
+    if docker info > /dev/null 2>&1; then
+        echo "Docker is ready!"
+        break
+    fi
+    sleep 1
+    timeout=$((timeout-1))
+done
+
+if [ $timeout -eq 0 ]; then
+    echo "Error: Docker failed to start within 30 seconds"
+    exit 1
+fi
+
+cd /home/firecrawl/firecrawl
+
+echo "Prerequisites check:"
+echo "✓ Docker and Docker Compose are installed"
+echo "✓ Repository cloned to /home/firecrawl/firecrawl"
+
+if [ -f apps/api/.env ]; then
+    echo "✓ Environment file exists at apps/api/.env"
+else
+    echo "⚠ No .env file found, using defaults"
+fi
+
+echo ""
+echo "Building Firecrawl services..."
+echo "Running: docker compose build"
+docker compose build
+
+echo ""
+echo "Starting Firecrawl services..."
+echo "Running: docker compose up"
+echo ""
+
+# Run docker compose
+exec docker compose up "$@"
+EOF
+
+RUN chmod +x /start-firecrawl.sh \
+    && chown firecrawl:firecrawl /start-firecrawl.sh
+
+# Switch back to non-root user
+USER firecrawl
+
+# Expose common ports used by Firecrawl
+EXPOSE 3002 8080 6379 5432
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD docker compose ps -q | xargs docker inspect --format='{{.State.Health.Status}}' | grep -v healthy && exit 1 || exit 0
+
+# Set entrypoint
+ENTRYPOINT ["/start-firecrawl.sh"]
+
+# Default command (can be overridden)
+CMD []