Build Your First AI API Using Spring Boot and OpenAI

Artificial Intelligence is now a practical tool for developers, not just a complex research topic. As a Java developer, you can easily integrate AI into your backend using simple API calls.

In this guide, you will learn how to build your first AI-powered API using Spring Boot and OpenAI, in a clean and practical way.

---

🚀 Understanding the Approach

We are building a simple REST API that:

• Accepts a prompt
• Sends it to an AI service
• Returns the response

Flow:

User → Spring Boot API → OpenAI API → Response → User

⚙️ Project Setup

Create a Spring Boot project with:

• Java 11+
• Spring Web dependency
• Maven

---

📦 Maven Dependency

    
        org.springframework.boot
        spring-boot-starter-web
    

🧩 Request & Response Classes

package com.kscodes.ai;

public class AIRequest {

    private String prompt;

    //Getters and Setters
}

package com.kscodes.ai;

public class AIResponse {

    private String response;

    public AIResponse(String response) {
        this.response = response;
    }

    public String getResponse() {
        return response;
    }
}

🧠 AI Service (Core Logic)

package com.kscodes.ai;

import org.springframework.stereotype.Service;

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

@Service
public class AIService {

    private static final String API_URL = "https://api.openai.com/v1/chat/completions";
    private static final String API_KEY = System.getenv("OPENAI_API_KEY");

    public String generateResponse(String prompt) {

        try {
            String requestBody = "
            {
              "model": "gpt-4o-mini",
              "messages": [
                {
                  "role": "user",
                  "content": "%s"
                }
              ],
              "temperature": 0.7
            }
            ".formatted(prompt);

            HttpRequest request = HttpRequest.newBuilder()
                    .uri(URI.create(API_URL))
                    .header("Authorization", "Bearer " + API_KEY)
                    .header("Content-Type", "application/json")
                    .POST(HttpRequest.BodyPublishers.ofString(requestBody))
                    .build();

            HttpClient client = HttpClient.newHttpClient();
            HttpResponse response =
                    client.send(request, HttpResponse.BodyHandlers.ofString());

            return response.body();

        } catch (Exception e) {
            e.printStackTrace();
            return "Error while calling AI service";
        }
    }
}

🌐 REST Controller

package com.kscodes.ai;

import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.*;

@RestController
@RequestMapping("/ai")
public class AIController {

    @Autowired
    private AIService aiService;

    @PostMapping("/generate")
    public AIResponse generate(@RequestBody AIRequest request) {

        String aiResult = aiService.generateResponse(request.getPrompt());

        return new AIResponse(aiResult);
    }
}

▶️ Testing the API

Endpoint:

POST http://localhost:8080/ai/generate

Request Body:

{
  "prompt": "Explain Spring Boot in simple terms"
}

🔐 Important Best Practice

Never hardcode your API key:

export OPENAI_API_KEY=your_key_here

💡 Real-World Use Cases

You can extend this API to build:

• Chatbots
• Document summarization
• Email generation
• Customer support automation

For example:
👉 Insurance apps can summarize policy documents instantly.

---

🎯 Why This Matters

This pattern is the foundation of AI integration in backend systems.

Once you understand this:

• You can plug AI into any microservice
• You can scale AI features easily
• You can build enterprise-grade AI solutions

---

📝 Summary

• Built a Spring Boot AI API
• Integrated OpenAI using HttpClient
• Created clean Controller + Service structure
• Followed secure API practices

💬 Final Thought

AI is just another service in your architecture.

Once you know how to call it properly,
you can build powerful, intelligent applications with ease.