🤖 WhatsApp AI Executive Assistant

AI-powered WhatsApp chatbot built using Groq Llama-3.1-8B + LangChain — acts as a personal executive assistant with memory, scheduling & email automation.

---

📌 About This Project

This AI-powered WhatsApp Assistant functions like a personal executive assistant.
It can:

• Schedule meetings
• Send emails
• Remember past conversations
• Run LangChain tools
• Use Groq's ultra-fast Llama-3.1-8B model
• Store long-term memory in SQLite

Perfect for business automation, personal workflow automation, and AI-driven productivity.

---

🧠 Features

• 📱 WhatsApp Integration using Twilio
• 🧠 Persistent Memory (SQLite)
• 📅 Meeting Scheduler Tool
• 📧 Email Sending Tool
• ⚡ Groq Llama-3.1-8B Instant Model
• 🔗 LangChain Agent with Custom Tools
• 🔒 Environment-based secure configuration
• 🌐 ngrok tunneling for webhook testing

---

🚀 Tech Stack / Tools Used

---

📂 Project Structure

WhatsApp_AI_Executive_Assistan/
├── .venv/                    Virtual environment  
├── main.py                   Flask server (webhook handler)  
├── agent.py                  LangChain agent logic (Groq LLM)  
├── tools.py                  Custom tools (email, scheduling)  
├── requirements.txt          Python dependencies  
├── .env                      API keys (DO NOT COMMIT)  
├── chat_history.db           SQLite memory database  
└── README.md                 Documentation  

---

🛠️ Installation

Create and activate virtual environment:

Windows:

python -m venv .venv
.venv\Scripts\activate

Mac/Linux:

python -m venv .venv
source .venv/bin/activate

Install packages:

pip install -r requirements.txt

---

🔐 Configure API Keys

Create a .env file:

TWILIO_ACCOUNT_SID=your_twilio_sid_here
TWILIO_AUTH_TOKEN=your_twilio_token_here

GROQ_API_KEY=your_groq_api_key_here
MODEL_NAME=llama-3.1-8b-instant

How to get Groq API Key:

1. Visit https://console.groq.com
2. Click API Keys
3. Create a new key
4. Paste it into .env

---

▶️ Run the Server

python main.py

Server runs at:

http://localhost:5000

Webhook endpoint:

/bot

---

🌐 Expose Localhost Using ngrok

ngrok http 5000

Copy the HTTPS URL and set it in Twilio webhook:

https://your-ngrok-url.ngrok.io/bot

---

📲 Setup Twilio WhatsApp Sandbox

1. Visit https://www.twilio.com
2. Go to Messaging → Try it out → WhatsApp
3. Join the sandbox
4. Set webhook:

https://your-ngrok-url.ngrok.io/bot

---

🧠 How Memory Works

Each WhatsApp user has a session ID:

whatsapp:+92300xxxxxxx

Memory is stored in the database:

chat_history.db

Even after restarting the server, the bot remembers previous conversations.

---

🧪 Testing

✔ Memory Test:

1. Send: My secret code is Blue-Owl
2. Stop the server
3. Start the server again
4. Send: What is my secret code?

Expected: Blue-Owl

---

✔ Tools Test:

• “Schedule a meeting with Ali on Monday at 2 PM”
• “Send an email to hr@company.com saying I will be late.”

---

📦 Requirements

• Python 3.11+
• Groq API key
• Twilio WhatsApp Sandbox
• ngrok

---

🧹 Recommended .gitignore

.env
.venv/
__pycache__/
*.pyc
chat_history.db
*.db
.DS_Store

---

🛠 Troubleshooting

❌ python-dotenv Error

✔ Ensure .env only contains valid key-value pairs.

❌ Webhook Not Receiving Messages

✔ ngrok must be running
✔ Twilio webhook URL must match
✔ WhatsApp sandbox must be joined

❌ Model Issues

✔ MODEL_NAME must be llama-3.1-8b-instant
✔ Groq API key must be valid

---

🧑‍💻 Author

Muhammad Umer Iqbal — AI Engineer

---

📄 License

MIT License