Spring AI with OpenAI

This project contains a web service that will accept HTTP GET requests at http://localhost:8080/cat-jokes.

There is optional message parameter whose default value is "Tell me a cat joke".

The response to the request is from the OpenAI ChatGPT Service.

Prerequisites

Before using the AI commands, make sure you have a developer token from OpenAI.

Create an account at OpenAI Signup and generate the token at API Keys.

The Spring AI project defines a configuration property named spring.ai.openai.api-key that you should set to the value of the API Key obtained from openai.com.

Exporting an environment variable is one way to set that configuration property.

export SPRING_AI_OPENAI_API_KEY=<INSERT KEY HERE>

Setting the API key is all you need to run the application. However, you can find more information on setting started in the Spring AI reference documentation section on OpenAI Chat.

Building and running

./mvnw spring-boot:run

Access the endpoint

To get a response to the default request of "Tell me a joke"

curl localhost:8080/cat-jokes

A sample response is

Sure, here's one for you:

Why was the cat sitting on the computer?

Because it wanted to keep an eye on the mouse!

Now using the message request parameter

curl --get  --data-urlencode 'message=Tell me a joke about a cow.' localhost:8080/cat-jokes 

A sample response is

Why did the cow go to space?

Because it wanted to see the mooooon!

Alternatively use the httpie client

http localhost:8080/cat-jokes message=='Tell me a joke about a cow.'