README.md

metadata

title: WhatsApp Bot
emoji: 💬
colorFrom: green
colorTo: blue
sdk: docker
app_port: 7860
pinned: false
thumbnail: >-
  https://cdn-uploads.huggingface.co/production/uploads/69ef44f7daf9d56653d76e81/D9XBNpMMZAIZyMhg2nLS1.jpeg

💬 WhatsApp Bot on Hugging Face

A WhatsApp chatbot powered by AI, deployed as a Docker Space on Hugging Face.

Architecture

WhatsApp Cloud API (Meta)
       │
       ▼ HTTPS webhooks
https://miftahulkhairim-whatsapp-bot.hf.space/webhook
       │
       ▼
HF Docker Space (FastAPI, port 7860)
  ├── GET  /webhook  → Meta webhook verification
  ├── POST /webhook  → Receive message → AI reply → Send via WhatsApp API
  └── GET  /         → Dashboard UI

Setup Guide

1. Meta Developer Portal Setup

1. Go to developers.facebook.com → Create App → Choose Business type
2. Add the WhatsApp product to your app
3. In WhatsApp → Getting Started, note your:
   • Phone Number ID
   • WhatsApp Business Account ID
   • Temporary Access Token (for testing)
4. Go to WhatsApp → Configuration → Webhook:
   • Callback URL: https://miftahulkhairim-whatsapp-bot.hf.space/webhook
   • Verify Token: Choose any secret string (e.g., my_verify_token_2024)
   • Subscribe to: messages

2. HF Space Secrets

Go to Space Settings → Repository Secrets and add:

Secret Name	Value
WHATSAPP_VERIFY_TOKEN	Your chosen verify token string
WHATSAPP_TOKEN	Meta access token (from Developer Portal)
PHONE_NUMBER_ID	Your WhatsApp Phone Number ID
HF_TOKEN	Your HF token (for AI inference)

3. Deploy

The Space auto-builds and deploys when you push changes.

Features

• 🤖 AI-powered responses using Hugging Face Inference API
• 💬 Handles text messages from WhatsApp
• 📊 Web dashboard showing bot status and recent messages
• 🔒 Secure webhook verification
• ⚡ Async message processing for fast responses

Notes

• Free Spaces sleep after ~15 min of inactivity. Consider upgrading to paid hardware for always-on availability.
• Access tokens from Meta expire. Use a System User permanent token for production.