NVIDIA Chat

NVIDIA LLM API 是一个代理人工智能推理引擎，提供来自 various providers 的各种模型。

NVIDIA LLM API is a proxy AI Inference Engine offering a wide range of models from various providers.

Spring AI 通过重用现有的 OpenAI 客户端与 NVIDIA LLM API 集成。为此，您需要将 base-url 设置为 https://integrate.api.nvidia.com ，选择提供的 LLM models 之一并获取其 api-key 。

Spring AI integrates with the NVIDIA LLM API by reusing the existing OpenAI client. For this you need to set the base-url to https://integrate.api.nvidia.com, select one of the provided LLM models and get an api-key for it. image::spring-ai-nvidia-llm-api-1.jpg[]

NVIDIA LLM API 要求明确设置 max-tokens 参数，否则将抛出服务器错误。

NVIDIA LLM API requires the max-tokens parameter to be explicitly set or server error will be thrown.

查看 NvidiaWithOpenAiChatModelIT.java 测试，了解如何将 NVIDIA LLM API 与 Spring AI 结合使用的示例。

Check the NvidiaWithOpenAiChatModelIT.java tests for examples of using NVIDIA LLM API with Spring AI.

Prerequisite

  • 创建 NVIDIA 账户并充值足够额度。

  • Create NVIDIA account with sufficient credits.

  • 选择要使用的 LLM 模型。例如，下图中的 meta/llama-3.1-70b-instruct 。

  • Select a LLM Model to use. For example the meta/llama-3.1-70b-instruct in the screenshot below.

  • 从所选模型的页面，您可以获取访问此模型的 api-key 。

  • From the selected model’s page, you can get the api-key for accessing this model.

spring ai nvidia registration

Auto-configuration

Spring AI 自动配置、启动器模块的工件名称发生了重大变化。请参阅 upgrade notes 以获取更多信息。

There has been a significant change in the Spring AI auto-configuration, starter modules' artifact names. Please refer to the upgrade notes for more information.

Spring AI 为 OpenAI 聊天客户端提供了 Spring Boot 自动配置。要启用它，请将以下依赖项添加到项目的 Maven pom.xml 文件中：

Spring AI provides Spring Boot auto-configuration for the OpenAI Chat Client. To enable it add the following dependency to your project’s Maven pom.xml file:

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-starter-model-openai</artifactId>
</dependency>

或添加到 Gradle build.gradle 构建文件中。

or to your Gradle build.gradle build file.

dependencies {
    implementation 'org.springframework.ai:spring-ai-starter-model-openai'
}

  1. 参见 Dependency Management 部分，将 Spring AI BOM 添加到你的构建文件中。

Refer to the Dependency Management section to add the Spring AI BOM to your build file.

Chat Properties

Retry Properties

前缀 spring.ai.retry 用作属性前缀，允许您配置OpenAI聊天模型的重试机制。

The prefix spring.ai.retry is used as the property prefix that lets you configure the retry mechanism for the OpenAI chat model.

Property Description Default

spring.ai.retry.max-attempts

Maximum number of retry attempts.

10

spring.ai.retry.backoff.initial-interval

Initial sleep duration for the exponential backoff policy.

2 sec.

spring.ai.retry.backoff.multiplier

Backoff interval multiplier.

5

spring.ai.retry.backoff.max-interval

Maximum backoff duration.

3 min.

spring.ai.retry.on-client-errors

If false, throw a NonTransientAiException, and do not attempt retry for 4xx client error codes

false

spring.ai.retry.exclude-on-http-codes

List of HTTP status codes that should not trigger a retry (e.g. to throw NonTransientAiException).

empty

spring.ai.retry.on-http-codes

List of HTTP status codes that should trigger a retry (e.g. to throw TransientAiException).

empty

Connection Properties

spring.ai.openai 前缀用作可让你连接到 Open AI 的属性前缀。

The prefix spring.ai.openai is used as the property prefix that lets you connect to OpenAI.

Property Description Default

spring.ai.openai.base-url

The URL to connect to. Must be set to https://integrate.api.nvidia.com

-

spring.ai.openai.api-key

The NVIDIA API Key

-

Configuration Properties

聊天自动配置的启用和禁用现在通过前缀为 spring.ai.model.chat 的顶级属性进行配置。

Enabling and disabling of the chat auto-configurations are now configured via top level properties with the prefix spring.ai.model.chat.

要启用，spring.ai.model.chat=openai（默认启用）

To enable, spring.ai.model.chat=openai (It is enabled by default)

要禁用，spring.ai.model.chat=none（或任何与 openai 不匹配的值）

To disable, spring.ai.model.chat=none (or any value which doesn’t match openai)

此更改旨在允许配置多个模型。

This change is done to allow configuration of multiple models.

前缀 spring.ai.openai.chat 是允许您为 OpenAI 配置聊天模型实现的属性前缀。

The prefix spring.ai.openai.chat is the property prefix that lets you configure the chat model implementation for OpenAI.

Property Description Default

spring.ai.openai.chat.enabled (Removed and no longer valid)

Enable OpenAI chat model.

true

spring.ai.model.chat

Enable OpenAI chat model.

openai

spring.ai.openai.chat.base-url

Optional overrides the spring.ai.openai.base-url to provide chat specific url. Must be set to https://integrate.api.nvidia.com

-

spring.ai.openai.chat.api-key

Optional overrides the spring.ai.openai.api-key to provide chat specific api-key

-

spring.ai.openai.chat.options.model

The NVIDIA LLM model to use

-

spring.ai.openai.chat.options.temperature

The sampling temperature to use that controls the apparent creativity of generated completions. Higher values will make output more random while lower values will make results more focused and deterministic. It is not recommended to modify temperature and top_p for the same completions request as the interaction of these two settings is difficult to predict.

0.8

spring.ai.openai.chat.options.frequencyPenalty

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

0.0f

spring.ai.openai.chat.options.maxTokens

The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length.

NOTE: NVIDIA LLM API requires the max-tokens parameter to be explicitly set or server error will be thrown.

spring.ai.openai.chat.options.n

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

1

spring.ai.openai.chat.options.presencePenalty

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

-

spring.ai.openai.chat.options.responseFormat

An object specifying the format that the model must output. Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

-

spring.ai.openai.chat.options.seed

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

-

spring.ai.openai.chat.options.stop

Up to 4 sequences where the API will stop generating further tokens.

-

spring.ai.openai.chat.options.topP

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

-

spring.ai.openai.chat.options.tools

A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.

-

spring.ai.openai.chat.options.toolChoice

Controls which (if any) function is called by the model. none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function. Specifying a particular function via {"type: "function", "function": {"name": "my_function"}} forces the model to call that function. none is the default when no functions are present. auto is the default if functions are present.

-

spring.ai.openai.chat.options.user

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

-

spring.ai.openai.chat.options.functions

List of functions, identified by their names, to enable for function calling in a single prompt requests. Functions with those names must exist in the functionCallbacks registry.

-

spring.ai.openai.chat.options.stream-usage

(For streaming only) Set to add an additional chunk with token usage statistics for the entire request. The choices field for this chunk is an empty array and all other chunks will also include a usage field, but with a null value.

false

spring.ai.openai.chat.options.proxy-tool-calls

If true, the Spring AI will not handle the function calls internally, but will proxy them to the client. Then is the client’s responsibility to handle the function calls, dispatch them to the appropriate function, and return the results. If false (the default), the Spring AI will handle the function calls internally. Applicable only for chat models with function calling support

false

以 spring.ai.openai.chat.options 开头的所有属性都可以通过将请求特定 Runtime Options 添加到 Prompt 调用在运行时被覆盖。

All properties prefixed with spring.ai.openai.chat.options can be overridden at runtime by adding a request specific Runtime Options to the Prompt call.

Runtime Options

OpenAiChatOptions.java 提供模型配置，如要使用的模型、温度、频率惩罚等。

The OpenAiChatOptions.java provides model configurations, such as the model to use, the temperature, the frequency penalty, etc.

启动时，可以使用 OpenAiChatModel(api, options) 构造函数或 spring.ai.openai.chat.options.* 属性配置默认选项。

On start-up, the default options can be configured with the OpenAiChatModel(api, options) constructor or the spring.ai.openai.chat.options.* properties.

在运行时，可以通过向 Prompt 调用中添加新的请求特定选项来覆盖默认选项。例如，覆盖特定请求的默认模型和温度：

At run-time you can override the default options by adding new, request specific, options to the Prompt call. For example to override the default model and temperature for a specific request:

ChatResponse response = chatModel.call(
    new Prompt(
        "Generate the names of 5 famous pirates.",
        OpenAiChatOptions.builder()
            .model("mixtral-8x7b-32768")
            .temperature(0.4)
        .build()
    ));

除了模型特定的 OpenAiChatOptions ，您还可以使用通过 ChatOptions#builder() 创建的便携式 ChatOptions 实例。

In addition to the model specific OpenAiChatOptions you can use a portable ChatOptions instance, created with the ChatOptions#builder().

Function Calling

NVIDIA LLM API 在选择支持的模型时支持工具/函数调用。

NVIDIA LLM API supports Tool/Function calling when selecting a model that supports it.

spring ai nvidia function calling

您可以使用 ChatModel 注册自定义 Java 函数，并让所提供的模型智能地选择输出包含调用一个或多个注册函数的参数的 JSON 对象。这是一种将 LLM 功能与外部工具和 API 连接起来的强大技术。

You can register custom Java functions with your ChatModel and have the provided model intelligently choose to output a JSON object containing arguments to call one or many of the registered functions. This is a powerful technique to connect the LLM capabilities with external tools and APIs.

Tool Example

以下是使用 NVIDIA LLM API 函数调用与 Spring AI 的一个简单示例：

Here’s a simple example of how to use NVIDIA LLM API function calling with Spring AI:

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("What is the weather in Amsterdam and Paris?")
                .functions("weatherFunction") // reference by bean name.
                .call()
                .content();

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

    @Bean
    @Description("Get the weather in location")
    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);
        }
    }
}

在此示例中，当模型需要天气信息时，它将自动调用 weatherFunction bean，然后该 bean 可以获取实时天气数据。预期响应如下所示：“阿姆斯特丹目前的气温是 20 摄氏度，巴黎目前的气温是 25 摄氏度。”

In this example, when the model needs weather information, it will automatically call the weatherFunction bean, which can then fetch real-time weather data. The expected response looks like this: "The weather in Amsterdam is currently 20 degrees Celsius, and the weather in Paris is currently 25 degrees Celsius."

阅读更多关于 OpenAI Function Calling 的信息。

Read more about OpenAI Function Calling.

Sample Controller

Create 一个新的 Spring Boot 项目，并将 spring-ai-starter-model-openai 添加到您的 pom（或 gradle）依赖项中。

Create a new Spring Boot project and add the spring-ai-starter-model-openai to your pom (or gradle) dependencies.

在 src/main/resources 目录下添加一个 application.properties 文件，以启用和配置 OpenAI 聊天模型：

Add a application.properties file, under the src/main/resources directory, to enable and configure the OpenAi chat model:

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

# The NVIDIA LLM API doesn't support embeddings, so we need to disable it.
spring.ai.openai.embedding.enabled=false

# The NVIDIA LLM API requires this parameter to be set explicitly or server internal error will be thrown.
spring.ai.openai.chat.options.max-tokens=2048

将 api-key 替换为您的 NVIDIA 凭据。

replace the api-key with your NVIDIA credentials.

NVIDIA LLM API 要求明确设置 max-token 参数，否则将抛出服务器错误。

NVIDIA LLM API requires the max-token parameter to be explicitly set or server error will be thrown.

以下是一个简单的 @Controller 类示例，该类使用聊天模型进行文本生成。

Here is an example of a simple @Controller class that uses the chat model for text generations.

@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 = "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);
    }
}