This version is still in development and is not considered stable yet. For the latest snapshot version, please use Spring AI 1.0.0-SNAPSHOT!spring-doc.cn

ZhiPu AI Chat

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.spring-doc.cn

Prerequisites

You will need to create an API with ZhiPuAI to access ZhiPu AI language models.spring-doc.cn

Create an account at ZhiPu AI registration page and generate the token on the API Keys page. 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 API Keys page. Exporting an environment variable is one way to set that configuration property:spring-doc.cn

export SPRING_AI_ZHIPU_AI_API_KEY=<INSERT KEY HERE>

Add Repositories and BOM

Spring AI artifacts are published in Spring Milestone and Snapshot repositories. Refer to the Repositories section to add these repositories to your build system.spring-doc.cn

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.spring-doc.cn

Auto-configuration

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:spring-doc.cn

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-zhipuai-spring-boot-starter</artifactId>
</dependency>

or to your Gradle build.gradle build file.spring-doc.cn

dependencies {
    implementation 'org.springframework.ai:spring-ai-zhipuai-spring-boot-starter'
}
Refer to the Dependency Management section to add the Spring AI BOM to your build file.

Chat Properties

Retry Properties

The prefix spring.ai.retry is used as the property prefix that lets you configure the retry mechanism for the ZhiPu AI chat model.spring-doc.cn

Property Description Default

spring.ai.retry.max-attemptsspring-doc.cn

Maximum number of retry attempts.spring-doc.cn

10spring-doc.cn

spring.ai.retry.backoff.initial-intervalspring-doc.cn

Initial sleep duration for the exponential backoff policy.spring-doc.cn

2 sec.spring-doc.cn

spring.ai.retry.backoff.multiplierspring-doc.cn

Backoff interval multiplier.spring-doc.cn

5spring-doc.cn

spring.ai.retry.backoff.max-intervalspring-doc.cn

Maximum backoff duration.spring-doc.cn

3 min.spring-doc.cn

spring.ai.retry.on-client-errorsspring-doc.cn

If false, throw a NonTransientAiException, and do not attempt retry for 4xx client error codesspring-doc.cn

falsespring-doc.cn

spring.ai.retry.exclude-on-http-codesspring-doc.cn

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

emptyspring-doc.cn

spring.ai.retry.on-http-codesspring-doc.cn

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

emptyspring-doc.cn

Connection Properties

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

Property Description Default

spring.ai.zhipuai.base-urlspring-doc.cn

The URL to connect tospring-doc.cn

open.bigmodel.cn/api/paasspring-doc.cn

spring.ai.zhipuai.api-keyspring-doc.cn

The API Keyspring-doc.cn

-spring-doc.cn

Configuration Properties

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

Property Description Default

spring.ai.zhipuai.chat.enabledspring-doc.cn

Enable ZhiPuAI chat model.spring-doc.cn

truespring-doc.cn

spring.ai.zhipuai.chat.base-urlspring-doc.cn

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

open.bigmodel.cn/api/paasspring-doc.cn

spring.ai.zhipuai.chat.api-keyspring-doc.cn

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

-spring-doc.cn

spring.ai.zhipuai.chat.options.modelspring-doc.cn

This is the ZhiPuAI Chat model to usespring-doc.cn

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-doc.cn

spring.ai.zhipuai.chat.options.maxTokensspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.zhipuai.chat.options.temperaturespring-doc.cn

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.spring-doc.cn

0.7spring-doc.cn

spring.ai.zhipuai.chat.options.topPspring-doc.cn

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-doc.cn

1.0spring-doc.cn

spring.ai.zhipuai.chat.options.stopspring-doc.cn

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

-spring-doc.cn

spring.ai.zhipuai.chat.options.userspring-doc.cn

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

-spring-doc.cn

spring.ai.zhipuai.chat.options.requestIdspring-doc.cn

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-doc.cn

-spring-doc.cn

spring.ai.zhipuai.chat.options.doSamplespring-doc.cn

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.spring-doc.cn

truespring-doc.cn

spring.ai.zhipuai.chat.options.proxy-tool-callsspring-doc.cn

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 supportspring-doc.cn

falsespring-doc.cn
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.
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

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

On start-up, the default options can be configured with the ZhiPuAiChatModel(api, options) constructor or the spring.ai.zhipuai.chat.options.* properties.spring-doc.cn

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:spring-doc.cn

ChatResponse response = chatModel.call(
    new Prompt(
        "Generate the names of 5 famous pirates.",
        ZhiPuAiChatOptions.builder()
            .withModel(ZhiPuAiApi.ChatModel.GLM_3_Turbo.getValue())
            .withTemperature(0.5)
        .build()
    ));
In addition to the model specific ZhiPuAiChatOptions you can use a portable ChatOptions instance, created with the ChatOptionsBuilder#builder().

Sample Controller

Create a new Spring Boot project and add the spring-ai-zhipuai-spring-boot-starter to your pom (or gradle) dependencies.spring-doc.cn

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

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
replace the api-key with your ZhiPuAI credentials.

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.spring-doc.cn

@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

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

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

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

or to your Gradle build.gradle build file.spring-doc.cn

dependencies {
    implementation 'org.springframework.ai:spring-ai-zhipuai'
}
Refer to the Dependency Management section to add the Spring AI BOM to your build file.

Next, create a ZhiPuAiChatModel and use it for text generations:spring-doc.cn

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

var chatModel = new ZhiPuAiChatModel(this.zhiPuAiApi, ZhiPuAiChatOptions.builder()
                .withModel(ZhiPuAiApi.ChatModel.GLM_3_Turbo.getValue())
                .withTemperature(0.4)
                .withMaxTokens(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."));

The ZhiPuAiChatOptions provides the configuration information for the chat requests. The ZhiPuAiChatOptions.Builder is fluent options builder.spring-doc.cn

Low-level ZhiPuAiApi Client

The ZhiPuAiApi provides is lightweight Java client for ZhiPu AI API.spring-doc.cn

Here is a simple snippet how to use the api programmatically:spring-doc.cn

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));

Follow the ZhiPuAiApi.java's JavaDoc for further information.spring-doc.cn

ZhiPuAiApi Samples