WhatsApp GPT 4o AI Chatbot In C Full Tutorial

July 2, 2025

Back to Blog

A general-purpose, customizable WhatsApp AI Chatbot in C# 🔷 that can understand text 📝, audio 🎵 and images 🖼️, and reply to your clients 💬 about anything related to your business 🏢 directly on WhatsApp ✅. Powered by OpenAI GPT4o 🚀 (other models can be used too) and Wassenger WhatsApp API 🔗.

Now supports GPT-4o with text + audio + image input 📝🎵🖼️, audio responses 🔊, and improved RAG + MCP with function calling 🛠️ and external API calls support 🌐

Find other AI Chatbot implementations in Python, Node.js and PHP

🚀 Get started for free with Wassenger WhatsApp API in minutes by connecting your existing WhatsApp number and obtain your API key ✨

Features

  • 🤖 Fully featured chatbot for your WhatsApp number connected to Wassenger
  • 💬 Automatic replies to incoming messages from users
  • 🌍 Multi-language support — understands and replies in 90+ different languages
  • 🎤 Audio input/output — transcription and text-to-speech capabilities
  • 🖼️ Image processing — can analyze and understand images
  • 👥 Human handoff — allows users to request human assistance
  • ⚙️ Customizable AI behavior and instructions
  • 🔧 Function calling capabilities for external data integration
  • 📊 Memory management with conversation history and rate limiting
  • 🚦 Smart routing with webhook handling and error management
  • 🔒 Secure with proper error handling and logging
  • 🔄 Modern C# with .NET 9, dependency injection, and async/await patterns

Contents

Quick Start

  • Clone the repository:
git clone https://github.com/wassengerhq/whatsapp-chatgpt-bot-csharp.git cd whatsapp-chatgpt-bot-csharp

cp.env.example.env # Edit.env file with your API keys(see Configuration section)
  • Run the bot (local development mode):
cd src/WhatsAppChatBot dotnet run

Requirements

Configuration

Edit the .env file with your API credentials:

# Required: Wassenger API key
API_KEY=your_wassenger_api_key_here
# Required: OpenAI API key
OPENAI_API_KEY=your_openai_api_key_here
# OpenAI model to use(gpt-4o, gpt-4, gpt-3.5-turbo)
OPENAI_MODEL=gpt-4o
# Required for local development: Ngrok auth token
NGROK_TOKEN=your_ngrok_token_here
# Optional: Specific WhatsApp device ID
DEVICE=
# Optional: Webhook URL for production deployment
WEBHOOK_URL=https://yourdomain.com/webhook
# Server configuration
PORT=8080
LOG_LEVEL=Information
# Development mode(auto-initializes services)
DEV=true

API Keys Setup

Wassenger API Key:

  • Sign up at Wassenger (free trial available)
  • Go to API Keys
  • Create a new API key and copy it to API_KEY in .env

OpenAI API Key:

  • Sign up at OpenAI (free credits available)
  • Go to API Keys
  • Create a new API key and copy it to OPENAI_API_KEY in .env

Ngrok Token (for local development):

Bot Customization

Edit src/WhatsAppChatBot/Config/BotConfig.cs to customize:

  • Bot instructions and personality
  • Welcome and help messages
  • Supported features (audio, images, etc.)
  • Rate limits and quotas
  • Whitelisted/blacklisted numbers
  • Labels and metadata settings

Usage

Local Development

Start the development server:

cd src/WhatsAppChatBot dotnet run

The bot will:

  • Start a local HTTP server on port 8080
  • Optionally create an Ngrok tunnel automatically
  • Register the webhook with Wassenger
  • Begin processing WhatsApp messages

Send a message to your WhatsApp number connected to Wassenger to test the bot.

Production Deployment

Set environment variables on your server:

export WEBHOOK_URL=https://yourdomain.com/webhook
export API_KEY=your_wassenger_api_key
export OPENAI_API_KEY=your_openai_api_key
export PRODUCTION=true

Build and run:

dotnet build -c Release dotnet run - configuration Release

Make sure your server can receive POST requests at /webhook

Deployment

You can deploy this bot to any cloud platform that supports .NET 8.

Docker Deployment

# Build the Docker image
docker build -t whatsapp-chatbot.
# Run the container
docker run -d \
--name whatsapp-chatbot \
-p 8080:8080 \
-e API_KEY=your_wassenger_api_key \
-e OPENAI_API_KEY=your_openai_api_key \
-e WEBHOOK_URL=https://yourdomain.com/webhook \
-e PRODUCTION=true \
whatsapp-chatbot

Render

# Create render.yaml for automated deployment
cat > render.yaml << EOF
services:
- type: web
name: whatsapp-chatbot
env: docker
dockerfilePath:./Dockerfile
envVars:
- key: API_KEY
value: your_wassenger_api_key
- key: OPENAI_API_KEY
value: your_openai_api_key
- key: PRODUCTION
value: true
- key: PORT
value: 8080
EOF
# Connect your GitHub repo to Render and deploy automatically
# Or deploy manually:
# 1.Push to GitHub
# 2.Connect repo in Render dashboard
# 3.Set environment variables in Render UI

Heroku

# Login and create app
heroku login
heroku create your-whatsapp-bot
# Set environment variables
heroku config:set API_KEY=your_wassenger_api_key
heroku config:set OPENAI_API_KEY=your_openai_api_key
heroku config:set PRODUCTION=true
# Create heroku.yml for container deployment
cat > heroku.yml << EOF
build:
docker:
web: Dockerfile
run:
web: dotnet run --configuration Release
EOF
# Set stack to container
heroku stack:set container
# Deploy
git add.
git commit -m "Deploy to Heroku"
git push heroku main

Railway

# Install Railway CLI
npm install -g @railway/cli
# Login and deploy
railway login
railway new
# Deploy with environment variables
railway add --name API_KEY --value your_wassenger_api_key
railway add --name OPENAI_API_KEY --value your_openai_api_key
railway add --name PRODUCTION --value true
# Deploy from current directory
railway up

Fly.io

# Install flyctl
curl -L https://fly.io/install.sh | sh
# Initialize and configure
flyctl auth login
flyctl launch --name whatsapp-chatbot
# Create fly.toml configuration
cat > fly.toml << EOF
app = "whatsapp-chatbot"
primary_region = "iad"
[build]
dockerfile = "Dockerfile"
[env]
PRODUCTION = "true"
PORT = "8080"
[[services]]
http_checks = []
internal_port = 8080
processes = ["app"]
protocol = "tcp"
script_checks = []
[[services.ports]]
force_https = true
handlers = ["http"]
port = 80
[[services.ports]]
handlers = ["tls", "http"]
port = 443
EOF
# Set secrets
flyctl secrets set API_KEY=your_wassenger_api_key
flyctl secrets set OPENAI_API_KEY=your_openai_api_key
# Deploy
flyctl deploy

Azure App Service

# Create resource group
az group create --name rg-whatsapp-bot --location "East US"
# Create App Service plan
az appservice plan create --name asp-whatsapp-bot --resource-group rg-whatsapp-bot --sku B1 --is-linux
# Create web app
az webapp create --resource-group rg-whatsapp-bot --plan asp-whatsapp-bot --name your-app-name --runtime "DOTNETCORE:8.0"
# Configure app settings
az webapp config appsettings set --resource-group rg-whatsapp-bot --name your-app-name --settings \
API_KEY=your_wassenger_api_key \
OPENAI_API_KEY=your_openai_api_key \
PRODUCTION=true
# Deploy
dotnet publish -c Release
cd src/WhatsAppChatBot/bin/Release/net9.0/publish
zip -r../../../../../deploy.zip.
az webapp deployment source config-zip --resource-group rg-whatsapp-bot --name your-app-name --src deploy.zip

Architecture

The C# implementation follows modern .NET patterns and clean architecture:

src/
├── WhatsAppChatBot/
│ ├── Api/ # API clients
│ │ ├── OpenAIClient.cs # OpenAI API integration
│ │ └── WassengerClient.cs # Wassenger API integration
│ ├── Bot/ # Core bot logic
│ │ ├── ChatBot.cs # Main bot processing
│ │ └── FunctionHandler.cs # Function calling system
│ ├── Config/ # Configuration management
│ │ └── BotConfig.cs # Centralized configuration
│ ├── Controllers/ # HTTP layer
│ │ └── WebhookController.cs # API endpoints and webhook handling
│ ├── Models/ # Data models
│ │ ├── OpenAIModels.cs # OpenAI API models
│ │ ├── WassengerModels.cs # Wassenger API models
│ │ └── WebhookModels.cs # Webhook and general models
│ ├── Services/ # Business services
│ │ ├── MemoryStore.cs # In-memory caching and state
│ │ └── NgrokTunnel.cs # Development tunnel management
│ ├── Program.cs # Application entry point
│ ├── appsettings.json # Application configuration
│ └── WhatsAppChatBot.csproj # Project file
├──.env.example # Environment template
├── Dockerfile # Docker configuration
└── README.md

Testing

The project includes built-in health checks and validation:

API Connection Test

# Test the API endpoints
curl http://localhost:8080/

Webhook Test

# Simulate a webhook request
curl -X POST http://localhost:8080/webhook \
-H "Content-Type: application/json" \
-d '{
"event": "message:in:new", 
"data": {
"chat": {"id": "test", "fromNumber": "123", "type": "chat"}, 
"fromNumber": "123", 
"body": "Hello"
}
}'

Send Message Test

curl -X POST http://localhost:8080/message \
-H "Content-Type: application/json" \
-d '{
"phone": "1234567890", 
"message": "Test message", 
"device": "your-device-id"
}'

Development

Project Structure

The solution follows clean architecture principles:

  • Controllers: Handle HTTP requests and responses
  • Services: Business logic and external service integration
  • Models: Data transfer objects and domain models
  • Configuration: Centralized configuration management
  • Dependency Injection: Built-in .NET DI container

Key Classes

  • ChatBot - Main bot processing logic with message filtering and routing
  • OpenAIClient - OpenAI API integration with chat, audio, and image support
  • WassengerClient - Wassenger API integration for WhatsApp messaging
  • FunctionHandler - AI function calling system for external integrations
  • WebhookController - HTTP request routing and webhook handling
  • BotConfig - Centralized configuration management with environment variables
  • MemoryStore - In-memory caching and conversation state management
  • NgrokTunnel - Development tunneling for local testing

Running in Development

# Run with hot reload
dotnet watch run
# Run with specific environment
dotnet run --environment Development
# Run tests(if you add them)
dotnet test

Adding NuGet Packages

dotnet add package PackageName

Customization

Bot Instructions

Edit the AI behaviour in Config/BotConfig.cs:

private const string DefaultBotInstructions =
"You are a helpful assistant...";

Function Calling

Add custom functions in Bot/FunctionHandler.cs:

["getBusinessHours"] = new()
{
Name = "getBusinessHours", 
Description = "Get business operating hours", 
Parameters = new { type = "object", properties = new { } }, 
Handler = GetBusinessHours
}

Rate Limits

Adjust limits in Config/BotConfig.cs:

public class LimitsConfig
{
public int MaxInputCharacters { get; set; } = 1000;
public int MaxOutputTokens { get; set; } = 1000;
public int ChatHistoryLimit { get; set; } = 20;
//...more limits
}

Adding New API Integrations

  1. Create a new client in the Api/ folder
  2. Define models in Models/
  3. Register in Program.cs dependency injection
  4. Use in ChatBot or create new services

API Endpoints

  • GET / - Bot information and status
  • POST /webhook - Webhook for incoming WhatsApp messages
  • POST /message - Send message endpoint
  • GET /sample - Send a sample message
  • GET /files/{id} - Temporary file downloads

Swagger Documentation

When running in development mode, visit:

Troubleshooting

Common Issues

  1. “No active WhatsApp numbers”
  • Verify your Wassenger API key
  • Check that you have a connected WhatsApp device in Wassenger

2. “WhatsApp number is not online”

  • Ensure your WhatsApp device is connected and online in the Wassenger dashboard

3. Webhook not receiving messages

  • Check that your webhook URL is accessible from the internet
  • Verify firewall settings
  • Check logs for webhook registration errors

4. OpenAI API errors

  • Verify your OpenAI API key is valid
  • Ensure the model name is correct
  • Check your OpenAI account usage and billing

Debug Mode

Enable detailed logging by setting it in .env:

LOG_LEVEL=Debug

Or in appsettings.Development.json:

{
  "Logging": {
    "LogLevel": {
      "Default": "Debug"
    }
  }
}

Common Environment Issues

  • Port already in use: Change PORT in .env
  • Ngrok not found: Install ngrok or set NGROK_PATH
  • .NET version: Ensure .NET 8.0 SDK is installed

Resources

Contributing

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Make your changes
  4. Add tests if applicable
  5. Commit your changes (git commit -m 'Add some amazing feature')
  6. Push to the branch (git push origin feature/amazing-feature)
  7. Open a Pull Request

Development Guidelines

  • Follow C# coding conventions
  • Use async/await for all I/O operations
  • Add XML documentation for public APIs
  • Include unit tests for new functionality
  • Update the README for new features

Performance & Scalability

This C# implementation offers several advantages:

  • High Performance: .NET 8 runtime optimizations and compiled code
  • Memory Efficient: Proper disposal patterns and memory management
  • Concurrent Processing: Async/await and Task-based processing
  • Scalable: Built-in dependency injection and service lifetime management
  • Production Ready: Comprehensive logging, error handling, and health checks

Security Features

  • Input Validation: All webhook inputs are validated
  • Rate Limiting: Built-in message quotas and conversation limits
  • Secure Configuration: Environment-based secrets management
  • Error Handling: Comprehensive exception handling without information leakage
  • HTTP Security: Modern ASP.NET Core security defaults

More Articles & Tutorials

How Clinics Are Saving Up 25 Hours Weekly With WhatsApp Automation

How Clinics Are Saving Up 25 Hours Weekly With WhatsApp Automation

October 21, 2025
How Real Estate Agents Are Conquering The Market By Automating WhatsApp

How Real Estate Agents Are Conquering The Market By Automating WhatsApp

October 17, 2025
Connect WhatsApp With AI In 5 Minutes MCP

Connect WhatsApp With AI In 5 Minutes MCP

October 10, 2025
How To Build A WhatsApp Group Moderator With AI

How To Build A WhatsApp Group Moderator With AI

October 8, 2025
I Automated 50 WhatsApp Groups Here S The Code

I Automated 50 WhatsApp Groups Here S The Code

October 6, 2025
How To Make Money With Wassenger Flows While Your Competitors Are Still Doing Everything Manually

How To Make Money With Wassenger Flows While Your Competitors Are Still Doing Everything Manually

October 3, 2025

Ready to transform your WhatsApp communication?

Start automating your customer interactions today with Wassenger

Get Started Free