EP Docs Chatbot

An AI-powered chatbot that helps users find and understand Elastic Path documentation. Built with Next.js 13, OpenAI GPT-4, and MongoDB Vector Search.

Features

• 🤖 Natural language interactions with documentation
• 🔍 Semantic search across EP Commerce Cloud (EPCC) and Subscription Management (EPSM) docs
• 🛠️ Built-in tools for API reference and technical content retrieval
• 📊 DataDog integration for LLM observability
• ⚡ Real-time streaming responses
• 🎨 Clean, modern UI with syntax highlighting

Tech Stack

• Framework: Next.js 13 (App Router)
• Language: TypeScript
• AI/LLM: OpenAI GPT-4
• Database: MongoDB Atlas (Vector Search)
• Styling: Tailwind CSS
• Monitoring: DataDog

Getting Started

1. Clone the repository:

git clone https://github.com/elasticpath/ep-docs-chatbot.git
cd ep-docs-chatbot

2. Install dependencies:

npm install

3. Set up your environment variables:

cp .env.example .env

4. Add your API keys to the .env file:

OPENAI_API_KEY=your_openai_api_key
MONGODB_URI=your_mongodb_connection_string
NEXT_PUBLIC_SITE=EPCC
DD_API_KEY=your_datadog_api_key

5. Start the development server:

npm run dev

Open http://localhost:3000 to start chatting!

Environment Variables

• OPENAI_API_KEY: Your OpenAI API key
• MONGODB_URI: MongoDB connection string
• NEXT_PUBLIC_SITE: Site to search ('EPCC' or 'EPSM')
• DD_API_KEY: DataDog API key (optional)

Contributing

1. Create a new branch
2. Make your changes
3. Submit a pull request

License

MIT License