Access AI-Toolkit UI from Colab with CloudflaredAccess AI-Toolkit UI from Colab with CloudflaredAccess AI-Toolkit UI from Colab with Cloudflared

Running AI tools in Google Colab is powerful, but accessing web interfaces can sometimes be tricky. This guide shows you how to expose the AI-Toolkit UI to the public internet securely using cloudflared.

Quick Command

Copy and paste the following code block into a cell in your Google Colab notebook to start the UI and generate a public access URL.

#@title Run AI Tooklit UI
%cd /content/ai-toolkit/ui

import subprocess
import threading
import time
import socket
import urllib.request

def iframe_thread(port):
  while True:
      time.sleep(0.5)
      sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
      result = sock.connect_ex(('127.0.0.1', port))
      if result == 0:
        break
      sock.close()
  print("\nAI-Toolkit UI finished loading, trying to launch cloudflared (if it gets stuck here cloudflared is having issues)\n")

  p = subprocess.Popen(["cloudflared", "tunnel", "--url", "http://127.0.0.1:{}".format(port)], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
  for line in p.stderr:
    l = line.decode()
    if "trycloudflare.com " in l:
      print("This is the URL to access AI Tookit UI:", l[l.find("http"):], end='')
    #print(l, end='')


threading.Thread(target=iframe_thread, daemon=True, args=(8675,)).start()

# Replace YOUR_SUPER_SECRET_PASSWORD_HERE with your own password
!AI_TOOLKIT_AUTH=YOUR_SUPER_SECRET_PASSWORD_HERE npm run build_and_start

How It Works

1. Port Monitoring: The script runs a background thread that continuously checks if port 8675 (the default port for AI-Toolkit UI) is open on localhost.
2. Cloudflared Tunnel: Once the port is active, it launches cloudflared to create a secure tunnel pointing to http://127.0.0.1:8675.
3. URL Extraction: It parses the output from Cloudflare to find the trycloudflare.com URL and prints it for you to click.
4. Secure Access: The application starts with AI_TOOLKIT_AUTH enabled, ensuring that only users with the password can access your instance.