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.",
        OllamaOptions.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

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

var userMessage = new UserMessage("Explain what do you see on this picture?",
        new Media(MimeTypeUtils.IMAGE_PNG, this.imageResource));

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

图片显示了一个小金属篮子，里面装满了成熟的香蕉和红苹果。篮子放在一个表面上，
看起来像是一个桌子或台面，因为背景中似乎有一个厨房橱柜或抽屉的暗示。
篮子后面还有一个金戒指可见，这可能表明这张照片是在一个有金属装饰或固定装置的区域拍摄的。
整体环境暗示这是一个家庭环境，水果被展示出来，可能是为了方便或美观目的。

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(
                        OllamaOptions.builder()
                            .model(OllamaModel.MISTRAL)
                            .temperature(0.9)
                            .build())
                    .build();

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

// 或者使用流式响应
Flux<ChatResponse> response = this.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(OllamaOptions.builder().temperature(0.9).build())
    .build();

ChatResponse response = this.ollamaApi.chat(this.request);

// 流式请求
var request2 = ChatRequest.builder("orca-mini")
    .ttream(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(OllamaOptions.builder().temperature(0.9).build().toMap())
    .build();

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