A starter application for an AI-powered chatbot with Next.js, Lakebase Postgres (pgvector), OpenAI, and LlamaIndex.

It implements a chat interface that takes the user's input, embeds it, and retrieves relevant information from the Neon database using similarity search. It then uses the OpenAI chat API to generate a contextually appropriate response based on the retrieved data and chat history.

To follow along with this guide, you will need:

• A Neon account. If you do not have one, sign up at Neon. Your Neon project comes with a ready-to-use Postgres database named neondb. We'll use this database in the following examples.
• An OpenAI API key. If you do not have an OpenAI account, sign up and navigate to the API keys page to create an API key.
• Node.js and npm installed on your machine.

npx degit neondatabase/examples/ai/llamaindex/chatbot-nextjs ./chatbot-nextjs

1. Create a .env file:

cp .env.example .env

2. Update the environment variables with your OpenAI API Key and Lakebase Postgres URL.

3. Install the dependencies:

npm install

4. Run the application:

npm run dev

• Neon AI documentation
• pgvector documentation
• OpenAI documentation
• Llama Index documentation
• Next.js documentation

• Rishi Raj Jain (@rishi_raj_jain_)