Spring AI Introduction — Build AI-Powered Java Apps with Spring Boot

Spring AI Introduction — Build AI-Powered Java Apps with Spring Boot

Spring AI is an official Spring project that brings Artificial Intelligence capabilities into the Spring ecosystem. It provides a consistent, portable API to work with large language models (LLMs), embedding models, vector stores, and AI tools — the same way Spring Data provides a consistent API for databases. You write your code once and swap providers (OpenAI, Anthropic, Ollama, Google Gemini) by changing configuration.

This tutorial sets up a Spring Boot project with Spring AI, calls an LLM, and prints a response. By the end you will have a working AI-powered REST endpoint.

What Spring AI Provides

Spring AI
├── Chat Models        → OpenAI, Anthropic Claude, Ollama, Google Gemini, Azure OpenAI
├── Embedding Models   → Convert text to vectors for semantic search
├── Vector Stores      → PGVector, ChromaDB, Pinecone, Redis
├── Document Readers   → PDF, HTML, Text, Markdown loaders
├── Prompt Templates   → Dynamic prompt construction
├── Output Parsers     → Map AI response → Java object / List / Map
├── Tool/Function Call → Give AI access to your Java methods
└── MCP Support        → Model Context Protocol server and client

Maven Dependencies (pom.xml)

<properties>
    <java.version>17</java.version>
    <spring-ai.version>1.0.0</spring-ai.version>
</properties>

<dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-bom</artifactId>
            <version>${spring-ai.version}</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    </dependencies>
</dependencyManagement>

<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>

    <!-- Spring AI OpenAI starter -->
    <dependency>
        <groupId>org.springframework.ai</groupId>
        <artifactId>spring-ai-openai-spring-boot-starter</artifactId>
    </dependency>
</dependencies>

application.properties

spring.ai.openai.api-key=${OPENAI_API_KEY}
spring.ai.openai.chat.options.model=gpt-4o-mini
spring.ai.openai.chat.options.temperature=0.7

Set the environment variable before running: set OPENAI_API_KEY=sk-... on Windows or export OPENAI_API_KEY=sk-... on Linux/Mac.

AiService.java

package com.java9r.ai;

import org.springframework.ai.chat.client.ChatClient;
import org.springframework.stereotype.Service;

@Service
public class AiService {

    private final ChatClient chatClient;

    // Spring AI auto-configures ChatClient.Builder — inject and build here
    public AiService(ChatClient.Builder builder) {
        this.chatClient = builder.build();
    }

    public String ask(String question) {
        return chatClient.prompt()
                .user(question)
                .call()
                .content();
    }
}

AiController.java

package com.java9r.ai;

import org.springframework.web.bind.annotation.*;

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

    private final AiService aiService;

    public AiController(AiService aiService) {
        this.aiService = aiService;
    }

    @GetMapping("/ask")
    public String ask(@RequestParam String q) {
        return aiService.ask(q);
    }
}

Main Application Class

package com.java9r.ai;

import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

@SpringBootApplication
public class SpringAiApp {
    public static void main(String[] args) {
        SpringApplication.run(SpringAiApp.class, args);
    }
}

Test the Endpoint

GET http://localhost:8080/ai/ask?q=What+is+Spring+AI+in+one+sentence

Output

Spring AI is a Spring Framework project that provides a unified, portable API
for integrating AI capabilities — such as chat, embeddings, and function calling
— into Java applications using familiar Spring patterns.

How ChatClient Works

ChatClient.Builder (auto-configured by Spring AI)
    ↓
chatClient.prompt()          → start building a prompt
    .system("You are ...")   → optional system message
    .user("question")        → user message
    .call()                  → send to AI model
    .content()               → get string response
               OR
    .chatResponse()          → get full ChatResponse with metadata
    .entity(MyClass.class)   → parse response into a Java object

Key Points

• Spring AI auto-configures ChatClient.Builder — inject it, call .build() once per service
• The model and temperature set in application.properties are defaults; you can override per-call
• Switching from OpenAI to another provider only requires changing the starter dependency and properties — your service code stays the same
• Spring AI requires Java 17+ and Spring Boot 3.2+