Ask Naval

A Question Answering (QA) chatbot built with Vercel, OpenAI, and Steamship

Components

• Next.js
• OpenAI API (REST endpoint)
• API Routes (Edge runtime)
• Steamship API (AI orchestration stack)

How to Use

Run create-next-app

Execute create-next-app with npm or Yarn to bootstrap the example:

npx create-next-app --example https://github.com/steamship-core/vercel-examples/tree/main/prompt-app
# or
yarn create next-app --example https://github.com/steamship-core/vercel-examples/tree/prompt-app

Deploy your Steamship Stack

Steamship is an AI orchestration stack that auto-manages prompts, image generation, embeddings, vector search, and more. Think of it as a host for Vercel-style API functions, but with a managed, stateful, AI stack built-in.

Deploy your Steamship stack from this project's root folder with:

pip install steamship
cd steamship
ship deploy

Set your environment variables

Rename .env.example to .env.local:

cp .env.example .env.local

Then:

1. update STEAMSHIP_API_KEY with your Steamship API Key.
2. update STEAMSHIP_PACKAGE_HANDLE with the package name you selected when deploying your Steamship Stack

Run or Deploy your Next.js Stack

Run your Next.js stack in development mode:

npm install
npm run dev

# or

yarn
yarn dev

The app should be up and running at http://localhost:3000.

When you like what you see, deploy it to the cloud with Vercel (Documentation).