NVIDIA 聊天

ChatResponse response = chatModel.call(
    new Prompt(
        "生成 5 个著名海盗的名字。",
        OpenAiChatOptions.builder()
            .model("mixtral-8x7b-32768")
            .temperature(0.4)
        .build()
    ));

spring.ai.openai.api-key=${NVIDIA_API_KEY}
spring.ai.openai.base-url=https://integrate.api.nvidia.com
spring.ai.openai.chat.options.model=meta/llama-3.1-70b-instruct
spring.ai.openai.chat.options.max-tokens=2048

@SpringBootApplication
public class NvidiaLlmApplication {

    public static void main(String[] args) {
        SpringApplication.run(NvidiaLlmApplication.class, args);
    }

    @Bean
    CommandLineRunner runner(ChatClient.Builder chatClientBuilder) {
        return args -> {
            var chatClient = chatClientBuilder.build();

            var response = chatClient.prompt()
                .user("阿姆斯特丹和巴黎的天气怎么样？")
                .functions("weatherFunction") // 按 bean 名称引用。
                .call()
                .content();

            System.out.println(response);
        };
    }

    @Bean
    @Description("获取某个位置的天气")
    public Function<WeatherRequest, WeatherResponse> weatherFunction() {
        return new MockWeatherService();
    }

    public static class MockWeatherService implements Function<WeatherRequest, WeatherResponse> {

        public record WeatherRequest(String location, String unit) {}
        public record WeatherResponse(double temp, String unit) {}

        @Override
        public WeatherResponse apply(WeatherRequest request) {
            double temperature = request.location().contains("Amsterdam") ? 20 : 25;
            return new WeatherResponse(temperature, request.unit);
        }
    }
}

spring.ai.openai.api-key=${NVIDIA_API_KEY}
spring.ai.openai.base-url=https://integrate.api.nvidia.com
spring.ai.openai.chat.options.model=meta/llama-3.1-70b-instruct

# NVIDIA LLM API 不支持嵌入，因此我们需要禁用它。
spring.ai.openai.embedding.enabled=false

# NVIDIA LLM API 要求显式设置此参数，否则将引发服务器内部错误。
spring.ai.openai.chat.options.max-tokens=2048

@RestController
public class ChatController {

    private final OpenAiChatModel chatModel;

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

    @GetMapping("/ai/generate")
    public Map generate(@RequestParam(value = "message", defaultValue = "给我讲个笑话") String message) {
        return Map.of("generation", this.chatModel.call(message));
    }

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