README.md

Phoenix, Vercel AI SDK, Next.js, and OpenAI Generative Example with Telemetry

This example shows how to use the Vercel AI SDK with Next.js and OpenAI to create a sample generative application with OpenTelemetry support.

OTEL spans are processed by the @arizeai/openinference-vercel package and collected and viewable in Arize-Phoenix.

Deploy your own

Deploy the example using Vercel:

How to use

If you don't already have an OpenAI API key do the following to create one:

1. Sign up at OpenAI's Developer Platform.
2. Go to OpenAI's dashboard and create an API KEY.

Local

To run the example locally you need to:

1. Set the required OpenAI environment variable as the token value as shown the example env file but in a new file called .env.local.
2. To run Arize-Phoenix locally run docker run -p 6006:6006 -i -t arizephoenix/phoenix
3. npm ci to install the required dependencies.
4. npm run dev to launch the development server.

To view Arize-Phoenix and the example app visit:

• App: localhost:3000

• Phoenix: localhost:6006 or app.phoenix.arize.com

Learn More

To learn more about Phoenix, OpenAI, Next.js, and the Vercel AI SDK take a look at the following resources:

• Phoenix repository - learn about LLM observability with Phoenix
• Phoenix docs
• @arizeai/openinference-vercel - Check out the OpenInference Vercel support.
• Vercel AI SDK docs
• Vercel AI SDK telemetry support
• Vercel AI Playground
• OpenAI Documentation - learn about OpenAI features and API.
• Next.js Documentation - learn about Next.js features and API.