ZhiPu AI Chat

Spring AI 支持智谱 AI 的各种 AI 语言模型。您可以与智谱 AI 语言模型交互，并基于智谱 AI 模型创建多语言对话助手。

Spring AI supports the various AI language models from ZhiPu AI. You can interact with ZhiPu AI language models and create a multilingual conversational assistant based on ZhiPuAI models.

Prerequisites

你需要使用智谱AI创建一个API来访问智谱AI语言模型。

You will need to create an API with ZhiPuAI to access ZhiPu AI language models.

在` ZhiPu AI registration page 创建一个账户并在 API Keys page `生成令牌。

Create an account at ZhiPu AI registration page and generate the token on the API Keys page.

Spring AI 项目定义了一个名为 spring.ai.zhipuai.chat.api-key 的配置属性，您应该将其设置为从 API 密钥页面获取的 API 密钥值。

The Spring AI project defines a configuration property named spring.ai.zhipuai.api-key that you should set to the value of the API Key obtained from the API Keys page.

你可以在` application.properties `文件中设置此配置属性：

You can set this configuration property in your application.properties file:

spring.ai.zhipuai.api-key=<your-zhipuai-api-key>

为了在处理 API 密钥等敏感信息时增强安全性，您可以使用 Spring 表达式语言 (SpEL) 引用自定义环境变量：

For enhanced security when handling sensitive information like API keys, you can use Spring Expression Language (SpEL) to reference a custom environment variable:

# In application.yml
spring:
  ai:
    zhipuai:
      api-key: ${ZHIPUAI_API_KEY}
# In your environment or .env file
export ZHIPUAI_API_KEY=<your-zhipuai-api-key>

你也可以在应用程序代码中以编程方式设置此配置：

You can also set this configuration programmatically in your application code:

// Retrieve API key from a secure source or environment variable
String apiKey = System.getenv("ZHIPUAI_API_KEY");

Add Repositories and BOM

Spring AI 工件发布在 Maven Central 和 Spring Snapshot 存储库中。请参阅“添加 Spring AI 仓库”部分，将这些仓库添加到您的构建系统。

Spring AI artifacts are published in Maven Central and Spring Snapshot repositories. Refer to the Artifact Repositories section to add these repositories to your build system.

为了帮助进行依赖项管理，Spring AI 提供了一个 BOM（物料清单）以确保在整个项目中使用一致版本的 Spring AI。有关将 Spring AI BOM 添加到你的构建系统的说明，请参阅 Dependency Management 部分。

To help with dependency management, Spring AI provides a BOM (bill of materials) to ensure that a consistent version of Spring AI is used throughout the entire project. Refer to the Dependency Management section to add the Spring AI BOM to your build system.

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 为智谱 AI 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您项目的 Maven pom.xml 文件中：

Spring AI provides Spring Boot auto-configuration for the ZhiPuAI 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-zhipuai</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-zhipuai'
}

  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，可让您配置智谱 AI 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 ZhiPu AI 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

前缀 spring.ai.zhiPu 用作属性前缀，可让您连接到智谱 AI。

The prefix spring.ai.zhiPu is used as the property prefix that lets you connect to ZhiPuAI.

Property Description Default

spring.ai.zhipuai.base-url

The URL to connect to

[role="bare"]https://open.bigmodel.cn/api/paas

spring.ai.zhipuai.api-key

The 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，请设置 spring.ai.model.chat=zhipuai（默认已启用）

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

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

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

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.zhipuai.chat 是属性前缀，可让您配置智谱 AI 的聊天模型实现。

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

Property Description Default

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

Enable ZhiPuAI chat model.

true

spring.ai.model.chat

Enable ZhiPuAI chat model.

zhipuai

spring.ai.zhipuai.chat.base-url

Optional overrides the spring.ai.zhipuai.base-url to provide chat specific url

[role="bare"]https://open.bigmodel.cn/api/paas

spring.ai.zhipuai.chat.api-key

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

-

spring.ai.zhipuai.chat.options.model

This is the ZhiPuAI Chat model to use

GLM-3-Turbo (the GLM-3-Turbo, GLM-4, GLM-4-Air, GLM-4-AirX, GLM-4-Flash, and GLM-4V point to the latest model versions)

spring.ai.zhipuai.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.

-

spring.ai.zhipuai.chat.options.temperature

What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

0.7

spring.ai.zhipuai.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..

1.0

spring.ai.zhipuai.chat.options.stop

The model will stop generating characters specified by stop, and currently only supports a single stop word in the format of ["stop_word1"]

-

spring.ai.zhipuai.chat.options.user

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

-

spring.ai.zhipuai.chat.options.requestId

The parameter is passed by the client and must ensure uniqueness. It is used to distinguish the unique identifier for each request. If the client does not provide it, the platform will generate it by default.

-

spring.ai.zhipuai.chat.options.doSample

When do_sample is set to true, the sampling strategy is enabled. If do_sample is false, the sampling strategy parameters temperature and top_p will not take effect.

true

spring.ai.zhipuai.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

您可以覆盖 ChatModel 实现的通用 spring.ai.zhipuai.base-url 和 spring.ai.zhipuai.api-key 。如果设置了 spring.ai.zhipuai.chat.base-url 和 spring.ai.zhipuai.chat.api-key 属性，它们将优先于通用属性。这在您希望对不同模型和不同模型端点使用不同的智谱 AI 账户时非常有用。

You can override the common spring.ai.zhipuai.base-url and spring.ai.zhipuai.api-key for the ChatModel implementations. The spring.ai.zhipuai.chat.base-url and spring.ai.zhipuai.chat.api-key properties if set take precedence over the common properties. This is useful if you want to use different ZhiPuAI accounts for different models and different model endpoints.

所有带 spring.ai.zhipuai.chat.options 前缀的属性都可以在运行时通过向 Prompt 调用添加请求特定的 Runtime Options 来覆盖。

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

Runtime Options

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

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

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

On start-up, the default options can be configured with the ZhiPuAiChatModel(api, options) constructor or the spring.ai.zhipuai.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.",
        ZhiPuAiChatOptions.builder()
            .model(ZhiPuAiApi.ChatModel.GLM_3_Turbo.getValue())
            .temperature(0.5)
        .build()
    ));

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

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

Sample Controller

Create 一个新的 Spring Boot 项目，并将 spring-ai-starter-model-zhipuai 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-zhipuai to your pom (or gradle) dependencies.

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

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

spring.ai.zhipuai.api-key=YOUR_API_KEY
spring.ai.zhipuai.chat.options.model=glm-4-air
spring.ai.zhipuai.chat.options.temperature=0.7

将 api-key 替换为您的智谱 AI 凭据。

replace the api-key with your ZhiPuAI credentials.

这将创建一个 ZhiPuAiChatModel 实现，您可以将其注入到您的类中。这是一个使用聊天模型进行文本生成的简单 @Controller 类的示例。

This will create a ZhiPuAiChatModel implementation that you can inject into your class. Here is an example of a simple @Controller class that uses the chat model for text generations.

@RestController
public class ChatController {

    private final ZhiPuAiChatModel chatModel;

    @Autowired
    public ChatController(ZhiPuAiChatModel 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) {
        var prompt = new Prompt(new UserMessage(message));
        return this.chatModel.stream(prompt);
    }
}

Manual Configuration

ZhiPuAiChatModel 实现了 ChatModel 和 StreamingChatModel ，并使用 Low-level ZhiPuAiApi Client 连接到智谱 AI 服务。

The ZhiPuAiChatModel implements the ChatModel and StreamingChatModel and uses the Low-level ZhiPuAiApi Client to connect to the ZhiPuAI service.

将 spring-ai-zhipuai 依赖项添加到您项目的 Maven pom.xml 文件中：

Add the spring-ai-zhipuai dependency to your project’s Maven pom.xml file:

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-zhipuai</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-zhipuai'
}

  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.

接下来，创建一个 ZhiPuAiChatModel 并将其用于文本生成：

Next, create a ZhiPuAiChatModel and use it for text generations:

var zhiPuAiApi = new ZhiPuAiApi(System.getenv("ZHIPU_AI_API_KEY"));

var chatModel = new ZhiPuAiChatModel(this.zhiPuAiApi, ZhiPuAiChatOptions.builder()
                .model(ZhiPuAiApi.ChatModel.GLM_3_Turbo.getValue())
                .temperature(0.4)
                .maxTokens(200)
                .build());

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

// Or with streaming responses
Flux<ChatResponse> streamResponse = this.chatModel.stream(
    new Prompt("Generate the names of 5 famous pirates."));

ZhiPuAiChatOptions 提供聊天请求的配置信息。 ZhiPuAiChatOptions.Builder 是流畅的选项构建器。

The ZhiPuAiChatOptions provides the configuration information for the chat requests. The ZhiPuAiChatOptions.Builder is fluent options builder.

Low-level ZhiPuAiApi Client

ZhiPuAiApi 提供的是一个轻量级的Java客户端，用于 ZhiPu AI API 。

The ZhiPuAiApi provides is lightweight Java client for ZhiPu AI API.

下面是一个简单的片段，说明如何以编程方式使用 API：

Here is a simple snippet how to use the api programmatically:

ZhiPuAiApi zhiPuAiApi =
    new ZhiPuAiApi(System.getenv("ZHIPU_AI_API_KEY"));

ChatCompletionMessage chatCompletionMessage =
    new ChatCompletionMessage("Hello world", Role.USER);

// Sync request
ResponseEntity<ChatCompletion> response = this.zhiPuAiApi.chatCompletionEntity(
    new ChatCompletionRequest(List.of(this.chatCompletionMessage), ZhiPuAiApi.ChatModel.GLM_3_Turbo.getValue(), 0.7, false));

// Streaming request
Flux<ChatCompletionChunk> streamResponse = this.zhiPuAiApi.chatCompletionStream(
        new ChatCompletionRequest(List.of(this.chatCompletionMessage), ZhiPuAiApi.ChatModel.GLM_3_Turbo.getValue(), 0.7, true));

请查阅 ZhiPuAiApi.java 的JavaDoc以获取更多信息。

Follow the ZhiPuAiApi.java's JavaDoc for further information.

ZhiPuAiApi Samples

  • ZhiPuAiApiIT.java 测试提供了一些使用轻量级库的通用示例。

  • The ZhiPuAiApiIT.java test provides some general examples how to use the lightweight library.