简单把玩下SpringAI

最新推荐文章于 2024-09-17 16:52:57 发布

Gao__xi

最新推荐文章于 2024-09-17 16:52:57 发布

阅读量500

点赞数 5

文章标签：人工智能 spring

本文链接：https://blog.csdn.net/Gao__xi/article/details/138219117

版权

Hello大家好，今天写一些不烧脑的文章，我们来体验一下Spring的新框架Spring AI，只是简单玩玩不深入😏

Spring AI 简介

Spring AI是为了简化人工智能相关应用程序的开发
Spring AI的诞生，灵感来自于LangChain等项目

Ollama的初体验

是什么

简单使用

下载并傻瓜式安装
选择模型，拉取并运行

ollama pull qwen
ollama pull llama3

使用体验

ollama run qwen

Spring AI项目搭建

环境

JDK17
SpringBoot3.2.5

pom.xml

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

Controller

@RestController
public class ChatController {

    private final OllamaChatClient chatClient;

    public ChatController(OllamaChatClient chatClient) {
        this.chatClient = chatClient;
    }

    @GetMapping("/ai/chat")
    public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        return Map.of("generation", chatClient.call(message));
    }

    @GetMapping("/ai/genClothes")
    public Map genCompanyName(@RequestParam("message") String message) {
        String template = "今天温度是 %s 摄氏度，上衣应该穿什么？裤子应该穿什么？鞋子穿什么？请回答的简单一些";
        ChatResponse response = chatClient.call(
            new Prompt(
                String.format(template, message),
                OllamaOptions.create()
                .withModel("qwen")
                .withTemperature((float) 0.4)
            ));
        return Map.of("name", response.getResult().getOutput().getContent());
    }
}

application.yml

spring:
  ai:
    ollama:
      base-url: http://localhost:11434
      chat:
        enabled: true
        options:
          model: llama3
          temperature: 0.5