Spring Boot 接入Ollama实现与Deepseek简单对话

编程教程 (12) 2025-02-20 17:40:45

Ollama 环境准备

Spring Boot项目接入Ollama

Spring Boot 项目创建

提示：此处需spring boot 3.x + jdk 17

创建项目时候的几个核心依赖：

spring-boot-starter-web spring-ai-ollama-spring-boot-starter 详细参考下面片段（版本实时变化注意更新）

<properties>
        <java.version>17</java.version>
        <spring-ai.version>1.0.0-M6</spring-ai.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <scope>annotationProcessor</scope>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</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>

Ollama 配置

配置ollama服务地址和端口以及默认模型

spring:
  application:
    name: demo-boot-ollama
  ai:
    ollama:
      init:
        pull-model-strategy: never #默认不拉取没有的模型
      base-url: http://192.168.31.162:11434
      chat:
        options:
          model: deepseek-r1:8b

与Ollama 对话

@RestController
public class OllamaController {

    @Resource
    OllamaChatModel ollamaChatModel;

    @GetMapping(value = "/ai/ollama/default")
    public Object ollama(@RequestParam(value = "msg")String msg) {
        String called = ollamaChatModel.call(msg);
        System.out.println(called);
        return called;
    }

    @GetMapping(value = "/ai/ollama/custom")
    public Object ollamaConfig(@RequestParam(value = "msg")String msg){
        ChatResponse chatResponse=ollamaChatModel.call(new Prompt(msg,
                 OllamaOptions.builder()
                         .model("deepseek-r1:14b")//使用哪个大模型
                         .temperature(0.4)//温度，温度值越高，准确率下降，温度值越低，准确率上升
                         .build()
                 ));//温度，温度值越高，准确率下降，温度值越低，准确率上升
        System.out.println(chatResponse.getResult().getOutput().getText());
        return chatResponse.getResult().getOutput().getText();
    }
}

两个简单对话实现，第一个使用默认的application配置模型对话，第二个自定义对话模型和其他参数；

Spring Boot Ollama 更多配置参考：Ollama Chat :: Spring AI Reference

浏览器访问测试：

Spring Boot 接入Ollama实现与Deepseek简单对话_图示-8dd3c3d993cc42ea91d93c893ceecb1c.png — 简单自定义对话

另一个demo

@RestController
public class ChatController {

    /**
     * 注入application.yml配置的模型
     */
    @Resource
    OllamaChatModel chatModel;

    @GetMapping("/ai/generate")
    public Map<String,String> generate(@RequestParam(value = "message", defaultValue = "请讲一个笑话") String message) {
        return Map.of("generation", this.chatModel.call(message));
    }

    //流返回
    @GetMapping("/ai/generateStream")
    public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "请讲一个笑话") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));
        return this.chatModel.stream(prompt);
    }

}

Spring Boot 接入Ollama实现与Deepseek简单对话_图示-3ed2f9ffbdc34a4692b0dd3350938336.png — 聊天

使用单例测试方式对话，且指定格式化输出内容：

    @Resource
    OllamaChatModel ollamaChatModel;

    @Test
    public void chat() throws JsonProcessingException {
        String jsonSchema = """
        {
            "type": "object",
            "properties": {
                "steps": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "explanation": { "type": "string" },
                            "output": { "type": "string" }
                        },
                        "required": ["explanation", "output"],
                        "additionalProperties": false
                    }
                },
                "final_answer": { "type": "string" }
            },
            "required": ["steps", "final_answer"],
            "additionalProperties": false
        }
        """;

        Prompt prompt = new Prompt("8x + 7 = -23 , 请计算x的值",
                OllamaOptions.builder()
//                        .model(OllamaModel.LLAMA3_2.getName())
                        .model("deepseek-r1:8b")
                        .format(new ObjectMapper().readValue(jsonSchema, Map.class))
                        .build());

        ChatResponse response = this.ollamaChatModel.call(prompt);
        System.out.println(response.getResult().getOutput().getText());
    }

执行结果参考：