公司网站的宣传栏怎么做,建设一个百度百科类网站,苏州市住建局官网,企业宣传方案模板核心组件 API 由非流式处理方案和 和 流式处理方案组成。 在1.0.0版本中#xff0c;顾问链AdvisorChain相关接口已经弃用#xff0c;可能是老版本的思想不太合伦理吧 可以使用下面的方式实现多个顾问按oder顺序访问模型 public ChatController(ChatClient.Builder chatClien… 核心组件 API 由非流式处理方案和 和 流式处理方案组成。 在1.0.0版本中顾问链AdvisorChain相关接口已经弃用可能是老版本的思想不太合伦理吧 可以使用下面的方式实现多个顾问按oder顺序访问模型 public ChatController(ChatClient.Builder chatClientBuilder) {MySimpleLoggerAdvisor advisor3 new MySimpleLoggerAdvisor(3);MySimpleLoggerAdvisor advisor2 new MySimpleLoggerAdvisor(2);MySimpleLoggerAdvisor advisor1 new MySimpleLoggerAdvisor(1);this.chatClient chatClientBuilder//此处执行顺序由order决定并非添加顺序决定.defaultAdvisors(List.of(advisor3,advisor2,advisor1)).defaultSystem(You are a helpful assistant).build();} 下图说明了顾问链和聊天模型之间的交互 顾问advice之间的request和response 基于order 对称比如三个女孩子按顺序123追你你给出的答复顺序则应该是321 交互返回 Spring AI 提供了两种类型的内存顾问程序来维护对话上下文 顾问存储机制模板占位符PromptChatMemoryAdvisor内存中或自定义instructions,memoryVectorStoreChatMemoryAdvisor向量数据库instructions,long_term_memory 下面是一个简单顾问的实现用于参考学习 package com.example.advisor;import org.springframework.ai.chat.client.ChatClientRequest;
import org.springframework.ai.chat.client.ChatClientResponse;
import org.springframework.ai.chat.client.advisor.api.CallAdvisor;
import org.springframework.ai.chat.client.advisor.api.CallAdvisorChain;
import org.springframework.ai.chat.client.advisor.api.StreamAdvisor;
import org.springframework.ai.chat.client.advisor.api.StreamAdvisorChain;
import reactor.core.publisher.Flux;public class MySimpleLoggerAdvisor implements CallAdvisor, StreamAdvisor {private Integer order;public MySimpleLoggerAdvisor() {super();}public MySimpleLoggerAdvisor(Integer preOrder) {order preOrder;}public ChatClientResponse adviseCall(ChatClientRequest chatClientRequest, CallAdvisorChain callAdvisorChain) {System.out.println(BEFORE: {} chatClientRequest);System.out.println(do something order this.order);ChatClientResponse chatClientResponse callAdvisorChain.nextCall(chatClientRequest);System.out.println(AFTER: {} chatClientResponse);System.out.println(was do something order this.order);return chatClientResponse;}Overridepublic String getName() {return MySimpleLoggerAdvisor;}Overridepublic int getOrder() {return this.order null ? 0 : this.order;}// Override
// public AdvisedResponse aroundCall(AdvisedRequest advisedRequest, CallAroundAdvisorChain chain) {
//
// logger.debug(BEFORE: {}, advisedRequest);
//
// AdvisedResponse advisedResponse chain.nextAroundCall(advisedRequest);
//
// logger.debug(AFTER: {}, advisedResponse);
//
// return advisedResponse;
// }
//Overridepublic FluxChatClientResponse adviseStream(ChatClientRequest chatClientRequest, StreamAdvisorChain streamAdvisorChain) {System.out.println(BEFORE: {} chatClientRequest);System.out.println(do something);FluxChatClientResponse chatClientResponse streamAdvisorChain.nextStream(chatClientRequest);System.out.println(AFTER: {} chatClientResponse);System.out.println(was do something);return chatClientResponse;}// Override
// public FluxAdvisedResponse aroundStream(AdvisedRequest advisedRequest, StreamAroundAdvisorChain chain) {
//
// logger.debug(BEFORE: {}, advisedRequest);
//
// FluxAdvisedResponse advisedResponses chain.nextAroundStream(advisedRequest);
//
// return new MessageAggregator().aggregateAdvisedResponse(advisedResponses,
// advisedResponse - logger.debug(AFTER: {}, advisedResponse));
// }
} 最后分析一下顾问模块的依赖关系chatclient客户端是依赖于它的他和chatclient客户端也同时依赖于spring-ai-模型Core Advisor 框架在spring-ai-模型中得到定义和泛化
