在大模型应用（如智能客服、聊天机器人、内容生成平台）中，SafeGuardAdvisor 这类敏感词过滤组件的核心价值，是在大模型交互全链路中建立合规与安全屏障，既规避业务合规风险，也保障用户体验和平台声誉

语法:

new SafeGuardAdvisor(List.of("曹操"))

应用

package com.xzx.springai;

import org.junit.jupiter.api.Test;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.ai.chat.client.advisor.SafeGuardAdvisor;
import org.springframework.ai.chat.client.advisor.SimpleLoggerAdvisor;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.test.context.SpringBootTest;

import java.util.List;

@SpringBootTest
public class TestAdvisor {
    @Test
    public void test(@Autowired ChatClient.Builder chatClientBuilder) {
        ChatClient chatClient = chatClientBuilder
                .defaultAdvisors(new SafeGuardAdvisor(List.of("董卓"),"含有敏感词",1))
                .build();
        String content = chatClient.prompt().user("董卓大奸臣").call().content();
        System.out.println(content);
    }
}