Ollama 聊天

ollama pull <model-name>

ollama pull hf.co/<username>/<model-repository>

ChatResponse response = chatModel.call(
    new Prompt(
        "Generate the names of 5 famous pirates.",
        OllamaChatOptions.builder()
            .model(OllamaModel.LLAMA3_1)
            .temperature(0.4)
            .build()
    ));

spring:
  ai:
    ollama:
      init:
        pull-model-strategy: always
        timeout: 60s
        max-retries: 1

spring:
  ai:
    ollama:
      init:
        pull-model-strategy: always
        chat:
          additional-models:
            - llama3.2
            - qwen2.5

spring:
  ai:
    ollama:
      init:
        pull-model-strategy: always
        chat:
          include: false

ChatResponse response = chatModel.call(
    new Prompt(
        "单词 'strawberry' 中有多少个字母 'r'？",
        OllamaChatOptions.builder()
            .model("qwen3")
            .enableThinking()
            .build()
    ));

// 访问思考过程
String thinking = response.getResult().getMetadata().get("thinking");
String answer = response.getResult().getOutput().getContent();

ChatResponse response = chatModel.call(
    new Prompt(
        "2 + 2 等于多少？",
        OllamaChatOptions.builder()
            .model("deepseek-r1")
            .disableThinking()
            .build()
    ));

// 低思考级别
ChatResponse response = chatModel.call(
    new Prompt(
        "生成一个简短的标题",
        OllamaChatOptions.builder()
            .model("gpt-oss")
            .thinkLow()
            .build()
    ));

// 中等思考级别
ChatResponse response = chatModel.call(
    new Prompt(
        "分析这个数据集",
        OllamaChatOptions.builder()
            .model("gpt-oss")
            .thinkMedium()
            .build()
    ));

// 高思考级别
ChatResponse response = chatModel.call(
    new Prompt(
        "解决这个复杂问题",
        OllamaChatOptions.builder()
            .model("gpt-oss")
            .thinkHigh()
            .build()
    ));

ChatResponse response = chatModel.call(
    new Prompt(
        "计算 17 × 23",
        OllamaChatOptions.builder()
            .model("deepseek-r1")
            .enableThinking()
            .build()
    ));

// 获取推理过程
String thinking = response.getResult().getMetadata().get("thinking");
System.out.println("推理过程: " + thinking);
// 输出示例: "17 × 20 = 340, 17 × 3 = 51, 340 + 51 = 391"

// 获取最终答案
String answer = response.getResult().getOutput().getContent();
System.out.println("答案: " + answer);
// 输出示例: "答案是 391"

Flux<ChatResponse> stream = chatModel.stream(
    new Prompt(
        "解释量子纠缠",
        OllamaChatOptions.builder()
            .model("qwen3")
            .enableThinking()
            .build()
    ));

stream.subscribe(response -> {
    String thinking = response.getResult().getMetadata().get("thinking");
    String content = response.getResult().getOutput().getContent();

    if (thinking != null && !thinking.isEmpty()) {
        System.out.println("[思考] " + thinking);
    }
    if (content != null && !content.isEmpty()) {
        System.out.println("[响应] " + content);
    }
});

var imageResource = new ClassPathResource("/multimodal.test.png");

var userMessage = new UserMessage(
    "解释你在这张图片中看到了什么？",
    new Media(MimeTypeUtils.IMAGE_PNG, this.imageResource)
);

ChatResponse response = chatModel.call(
    new Prompt(this.userMessage,
        OllamaChatOptions.builder().model(OllamaModel.LLAVA).build())
);

The image shows a small metal basket filled with ripe bananas and red apples. The basket is placed on a surface,
which appears to be a table or countertop, as there's a hint of what seems like a kitchen cabinet or drawer in
the background. There's also a gold-colored ring visible behind the basket, which could indicate that this
photo was taken in an area with metallic decorations or fixtures. The overall setting suggests a home environment
where fruits are being displayed, possibly for convenience or aesthetic purposes.

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("how can I solve 8x + 7 = -23",
        OllamaChatOptions.builder()
            .model(OllamaModel.LLAMA3_2.getName())
            .format(new ObjectMapper().readValue(jsonSchema, Map.class))
            .build());

ChatResponse response = this.ollamaChatModel.call(this.prompt);

record MathReasoning(
    @JsonProperty(required = true, value = "steps") Steps steps,
    @JsonProperty(required = true, value = "final_answer") String finalAnswer) {

    record Steps(
        @JsonProperty(required = true, value = "items") Items[] items) {

        record Items(
            @JsonProperty(required = true, value = "explanation") String explanation,
            @JsonProperty(required = true, value = "output") String output) {
        }
    }
}

var outputConverter = new BeanOutputConverter<>(MathReasoning.class);

Prompt prompt = new Prompt("how can I solve 8x + 7 = -23",
        OllamaChatOptions.builder()
            .model(OllamaModel.LLAMA3_2.getName())
            .format(outputConverter.getJsonSchemaMap())
            .build());

ChatResponse response = this.ollamaChatModel.call(this.prompt);
String content = this.response.getResult().getOutput().getText();

MathReasoning mathReasoning = this.outputConverter.convert(this.content);

spring.ai.openai.chat.base-url=http://localhost:11434

spring.ai.openai.chat.options.model=mistral

// 配置 Spring AI OpenAI 客户端指向 Ollama
@Configuration
class OllamaConfig {
    @Bean
    OpenAiChatModel ollamaChatModel() {
        var openAiApi = new OpenAiApi("http://localhost:11434", "ollama");
        return new OpenAiChatModel(openAiApi,
            OpenAiChatOptions.builder()
                .model("deepseek-r1")  // 或 qwen3、deepseek-v3.1 等
                .build());
    }
}

// 使用思维能力模型
ChatResponse response = chatModel.call(
    new Prompt("How many letter 'r' are in the word 'strawberry'?"));

// 从 metadata 中获取推理过程
String reasoning = response.getResult().getMetadata().get("reasoningContent");
if (reasoning != null && !reasoning.isEmpty()) {
    System.out.println("模型的推理过程:");
    System.out.println(reasoning);
}

// 获取最终答案
String answer = response.getResult().getOutput().getContent();
System.out.println("答案: " + answer);

ollama pull hf.co/<username>/<model-repository>

spring.ai.ollama.chat.options.model=hf.co/bartowski/gemma-2-2b-it-GGUF
spring.ai.ollama.init.pull-model-strategy=always

spring:
  ai:
    ollama:
      base-url: http://localhost:11434
      chat:
        options:
          model: mistral
          temperature: 0.7

@RestController
public class ChatController {

    private final OllamaChatModel chatModel;

    @Autowired
    public ChatController(OllamaChatModel chatModel) {
        this.chatModel = chatModel;
    }

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

    @GetMapping("/ai/generateStream")
    public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));
        return this.chatModel.stream(prompt);
    }
}

var ollamaApi = OllamaApi.builder().build();

var chatModel = OllamaChatModel.builder()
                    .ollamaApi(ollamaApi)
                    .defaultOptions(
                        OllamaChatOptions.builder()
                            .model(OllamaModel.MISTRAL)
                            .temperature(0.9)
                            .build())
                    .build();

ChatResponse response = chatModel.call(
    new Prompt("Generate the names of 5 famous pirates."));

// 或者使用流式响应
Flux<ChatResponse> streamResponse = chatModel.stream(
    new Prompt("Generate the names of 5 famous pirates."));

OllamaApi ollamaApi = new OllamaApi("YOUR_HOST:YOUR_PORT");

// 同步请求
var request = ChatRequest.builder("orca-mini")
    .stream(false) // 非流式
    .messages(List.of(
            Message.builder(Role.SYSTEM)
                .content("You are a geography teacher. You are talking to a student.")
                .build(),
            Message.builder(Role.USER)
                .content("What is the capital of Bulgaria and what is the size? "
                        + "What is the national anthem?")
                .build()))
    .options(OllamaChatOptions.builder().temperature(0.9).build())
    .build();

ChatResponse response = ollamaApi.chat(request);

// 流式请求
var request2 = ChatRequest.builder("orca-mini")
    .stream(true) // 流式
    .messages(List.of(
        Message.builder(Role.USER)
            .content("What is the capital of Bulgaria and what is the size? "
                    + "What is the national anthem?")
            .build()))
    .options(OllamaChatOptions.builder().temperature(0.9).build().toMap())
    .build();

Flux<ChatResponse> streamingResponse = ollamaApi.streamingChat(request2);