Getting Started with Spring AI: Build ChatGPT‑Powered Apps in Java

Spring AI Introduction

Spring AI is an application framework for AI engineers that offers a friendly API and abstractions to simplify the development of AI applications. It supports common models and is currently available on https://start.spring.io, hosted in the Spring private repository.

Using the ChatGPT Model

1. Add Dependencies

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

<!-- Configure Spring repository -->
<repositories>
    <repository>
        <id>spring-milestones</id>
        <name>Spring Milestones</name>
        <url>https://repo.spring.io/milestone</url>
        <snapshots>
            <enabled>false</enabled>
        </snapshots>
    </repository>
</repositories>

2. Configure OpenAI Parameters

spring:
  ai:
    openai:
      base-url: # optional proxy such as openai-sb, openai-hk
      api-key: sk-xxxx

API Usage

1. Chat API

@Autowired
private OpenAiChatClient chatClient;

@Test
void testChatClient() {
    String message = "树上有 9 只鸟，猎人开枪打死一只，树上还剩下多少只鸟？";
    System.out.println(chatClient.call(message));
}

2. Image Generation

@Autowired
private OpenAiImageClient openaiImageClient;

@Test
void testImageClient() {
    ImageResponse response = openaiImageClient.call(
        new ImagePrompt("A light cream colored mini golden doodle",
            OpenAiImageOptions.builder()
                .withQuality("hd")
                .withN(4)
                .withHeight(1024)
                .withWidth(1024)
                .build())
    );
}

3. Prompt API

@Test
void testPrompts() {
    String systemText = "You are a helpful AI assistant that helps people find information.
Your name is {name}
You should reply to the user's request with your name.
";
    SystemPromptTemplate systemPromptTemplate = new SystemPromptTemplate(systemText);

    String userText = "Tell me about three famous pirates from the Golden Age of Piracy and why they did.
Write at least a sentence for each pirate.
";

    Message userMessage = new UserMessage(userText);
    Message systemMessage = systemPromptTemplate.createMessage(Map.of("name", "lengleng"));

    Prompt prompt = new Prompt(List.of(userMessage, systemMessage));

    List<Generation> response = chatClient.call(prompt).getResults();

    for (Generation generation : response) {
        System.out.println(generation.getOutput().getContent());
    }
}

Advanced: Building Business Large Models

Goal: In natural language interaction, call external tools to answer questions; convert natural language to API call parameters or database query conditions; extract structured data.

1. Create Function Calling

public class MockMathScoreService implements Function<MockMathScoreService.Request, MockMathScoreService.Response> {

    /** request dimensions: username */
    @JsonInclude(Include.NON_NULL)
    @JsonClassDescription("数学行业")
    public record Request(@JsonProperty(required = true, value = "username")
                          @JsonPropertyDescription("学生姓名") String username) {}

    /** response dimensions: username, score */
    public record Response(String username, double score) {}

    /** data source logic: query local DB by username */
    @Override
    public Response apply(Request request) {
        if (request.username.contains("张三")) {
            return new Response("张三", 100);
        } else if (request.username.contains("李四")) {
            return new Response("李四", 99.5);
        }
        return new Response("null", 0);
    }
}

2. Invoke

@Test
void testCallFunc() {
    String promptText = "张三同学的数学成绩怎么样？";
    UserMessage userMessage = new UserMessage(promptText);

    var promptOptions = OpenAiChatOptions.builder()
        .withFunctionCallbacks(List.of(new FunctionCallbackWrapper<>(
            "MathScoreService",
            "教育行业AI机器人",
            new MockMathScoreService())))
        .build();

    ChatResponse response = chatClient.call(new Prompt(List.of(userMessage), promptOptions));
    System.out.println(response.getResult().getOutput().getContent());
}