企业级java+LangChain4j-RAG系统 限流熔断降级

企业级javaLangChain4j-RAG系统 限流熔断降级1. 文档说明本文档基于SpringBoot3 LangChain4j Milvus/Chroma MySQL Redis企业级AI知识库RAG项目整合了目前业界所有主流接口限流、熔断、降级方案包含完整可运行源码、配置、场景选型规范、生产落地标准、面试核心知识点。所有代码无缝替换Sentinel、零冲突、可直接部署上线适配AI问答、文档解析、大文件分片上传全业务场景。2. 核心概念区分生产必备2.1 限流RateLimit控制接口QPS防止请求量过大压垮服务解决流量风暴、恶意刷接口问题。适用AI高频问答、文档上传、批量解析接口。2.2 熔断CircuitBreaker依赖服务大模型API、向量库、数据库超时/报错率过高时自动切断请求避免请求堆积、线程阻塞防止服务雪崩。AI项目刚需大模型接口不稳定、响应慢、极易超时。2.3 降级Fallback服务熔断/异常时返回预设兜底结果保证服务可用、不报错、不雪崩。3. 主流技术方案能力全景对比技术方案限流熔断降级分布式集群性能运维成本适用场景Resilience4j✅✅ 全能需Redis配合极高极低单体/微服务、AI项目首选Sentinel✅✅✅高中需控制台阿里生态、需动态规则可视化Redisson✅ 分布式❌✅ 强适配高极低集群全局限流Bucket4j✅ 高性能❌支持Redis极致高极低大文件上传、高并发接口Guava RateLimiter✅ 单机❌❌极高0小型内部项目、简单防刷RedisLua✅ 原生❌✅高极低零框架、极简技术栈Hystrix✅✅✅低高老旧项目新项目禁用4. 项目选型决策流程图通用复用开始选型 → 判断是否需要熔断降级/超时防雪崩4.1 不需要熔断仅限流单机小项目 → Guava RateLimiter高并发/大文件上传 → Bucket4j集群多实例 → Redisson / RedisLua零框架自研 → RedisLua4.2 需要熔断降级AI项目必选阿里生态、需要可视化控制台 → Sentinel非阿里生态、轻量无绑定 → Resilience4j单体部署 → 直接 Resilience4j 全套集群部署 → Resilience4j(熔断) Redisson(分布式限流)5. 本RAG项目 最终生产标准技术栈永久固定方案无需反复选型熔断、降级、超时、防雪崩Resilience4jSpring官方、无厂商绑定单机接口QPS限流Resilience4j 内置限流集群分布式限流Redisson大文件分片上传高并发限流Bucket4j极简备选Guava、RedisLua6. 完整项目依赖pom.xml整合所有限流熔断方案、RAG核心依赖可直接覆盖原有pom?xml version1.0 encodingUTF-8? project xmlnshttp://maven.apache.org/POM/4.0.0 xmlns:xsihttp://www.w3.org/2001/XMLSchema-instance xsi:schemaLocationhttp://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd modelVersion4.0.0/modelVersion parent groupIdorg.springframework.boot/groupId artifactIdspring-boot-starter-parent/artifactId version3.2.6/version relativePath/ /parent groupIdcom.ai/groupId artifactIdlangchain4j-enterprise-rag/artifactId version1.0.0/version nameLangChain4j企业级RAG系统/name properties java.version17/java.version langchain4j.version0.32.0/langchain4j.version mybatis-plus.version3.5.5/mybatis-plus.version fastjson2.version2.0.52/fastjson2.version /properties dependencies !-- SpringBoot基础 -- dependency groupIdorg.springframework.boot/groupId artifactIdspring-boot-starter-web/artifactId /dependency dependency groupIdorg.springframework.boot/groupId artifactIdspring-boot-starter-test/artifactId scopetest/scope /dependency !-- 数据库 -- dependency groupIdcom.mysql/groupId artifactIdmysql-connector-j/artifactId scoperuntime/scope /dependency dependency groupIdcom.baomidou/groupId artifactIdmybatis-plus-boot-starter/artifactId version${mybatis-plus.version}/version /dependency !-- LangChain4j RAG核心 -- dependency groupIddev.langchain4j/groupId artifactIdlangchain4j-spring-boot-starter/artifactId version${langchain4j.version}/version /dependency dependency groupIddev.langchain4j/groupId artifactIdlangchain4j-tongyi/artifactId version${langchain4j.version}/version /dependency dependency groupIddev.langchain4j/groupId artifactIdlangchain4j-milvus/artifactId version${langchain4j.version}/version /dependency dependency groupIddev.langchain4j/groupId artifactIdlangchain4j-chroma/artifactId version${langchain4j.version}/version /dependency dependency groupIddev.langchain4j/groupId artifactIdlangchain4j-document-parser-apache-tika/artifactId version${langchain4j.version}/version /dependency !-- 限流熔断全套方案 -- dependency groupIdorg.springframework.cloud/groupId artifactIdspring-cloud-starter-circuitbreaker-resilience4j/artifactId version3.2.1/version /dependency dependency groupIdorg.redisson/groupId artifactIdredisson-spring-boot-starter/artifactId version3.27.0/version /dependency dependency groupIdcom.github.vladimir-bukhtoyarov/groupId artifactIdbucket4j-core/artifactId version7.6.0/version /dependency dependency groupIdcom.google.guava/groupId artifactIdguava/artifactId version32.1.3-jre/version /dependency !-- 工具类 -- dependency groupIdorg.projectlombok/groupId artifactIdlombok/artifactId optionaltrue/optional /dependency dependency groupIdcom.alibaba.fastjson2/groupId artifactIdfastjson2/artifactId version${fastjson2.version}/version /dependency dependency groupIdcn.hutool/groupId artifactIdhutool-all/artifactId version5.8.30/version /dependency /dependencies build plugins plugin groupIdorg.springframework.boot/groupId artifactIdspring-boot-maven-plugin/artifactId configuration excludes exclude groupIdorg.projectlombok/groupId artifactIdlombok/artifactId /exclude /excludes /configuration /plugin /plugins /build /project7. 全局配置文件application-dev.ymlspring: datasource: url: jdbc:mysql://127.0.0.1:3306/rag_db?useUnicodetruecharacterEncodingutf8serverTimezoneAsia/ShanghaiallowMultiQueriestrue username: root password: 123456 driver-class-name: com.mysql.cj.jdbc.Driver data: redis: host: 127.0.0.1 port: 6379 password: database: 0 # 通义千问大模型配置 langchain4j: tongyi: api-key: sk-xxx你的keyxxx model-name: qwen-turbo timeout: 60s # 向量库配置 milvus: host: 127.0.0.1 port: 19530 collection-name: enterprise_knowledge chroma: host: 127.0.0.1 port: 8000 # Resilience4j 熔断限流核心配置 resilience4j: circuitbreaker: instances: aiChatCircuit: slidingWindowSize: 10 failureRateThreshold: 50 waitDurationInOpenState: 10000 permittedNumberOfCallsInHalfOpen: 3 uploadCircuit: slidingWindowSize: 10 failureRateThreshold: 50 ratelimiter: instances: aiChatLimit: limitForPeriod: 5 limitRefreshPeriod: 1000 timeoutDuration: 2000 uploadLimit: limitForPeriod: 2 limitRefreshPeriod: 10008. 全套配置类源码8.1 Bucket4jConfig.java 高性能限流配置package com.ai.rag.config; import io.github.bucket4j.Bandwidth; import io.github.bucket4j.Bucket; import io.github.bucket4j.Refill; import org.springframework.context.annotation.Bean; import org.springframework.context.annotation.Configuration; import java.time.Duration; Configuration public class Bucket4jConfig { Bean public Bucket aiChatBucket() { Bandwidth bandwidth Bandwidth.classic(5, Refill.greedy(5, Duration.ofSeconds(1))); return Bucket.builder().addLimit(bandwidth).build(); } Bean public Bucket uploadBucket() { Bandwidth bandwidth Bandwidth.classic(2, Refill.greedy(2, Duration.ofSeconds(1))); return Bucket.builder().addLimit(bandwidth).build(); } }8.2 GuavaLimitConfig.java 轻量单机限流配置package com.ai.rag.config; import com.google.common.util.concurrent.RateLimiter; import org.springframework.context.annotation.Bean; import org.springframework.context.annotation.Configuration; Configuration public class GuavaLimitConfig { Bean public RateLimiter aiGuavaLimiter() { return RateLimiter.create(5.0); } Bean public RateLimiter uploadGuavaLimiter() { return RateLimiter.create(2.0); } }9. 全套限流工具类9.1 RedisLimitUtil.java Redisson分布式限流package com.ai.rag.util; import org.redisson.api.RRateLimiter; import org.redisson.api.RateIntervalUnit; import org.redisson.api.RateType; import org.redisson.api.RedissonClient; import org.springframework.stereotype.Component; import javax.annotation.Resource; Component public class RedisLimitUtil { Resource private RedissonClient redissonClient; public boolean tryLimit(String key, int qps) { RRateLimiter limiter redissonClient.getRateLimiter(key); limiter.trySetRate(RateType.OVERALL, qps, 1, RateIntervalUnit.SECONDS); return limiter.tryAcquire(1); } }9.2 LuaLimitUtil.java RedisLua原生限流package com.ai.rag.util; import org.springframework.data.redis.core.StringRedisTemplate; import org.springframework.data.redis.core.script.DefaultRedisScript; import org.springframework.stereotype.Component; import javax.annotation.Resource; import java.util.List; Component public class LuaLimitUtil { Resource private StringRedisTemplate stringRedisTemplate; private static final String LUA_SCRIPT local key KEYS[1] local limit tonumber(ARGV[1]) local curr redis.call(get, key) or 0 if curr 1 limit then return 0 else redis.call(incr, key) redis.call(expire, key, 1) return 1 end; public boolean tryLimit(String key, int limit) { DefaultRedisScriptLong script new DefaultRedisScript(); script.setScriptText(LUA_SCRIPT); script.setResultType(Long.class); Long result stringRedisTemplate.execute(script, List.of(key), String.valueOf(limit)); return result ! null result 1; } }10. 终极整合Controller5套方案全覆盖默认启用 Resilience4j 熔断限流同时预留其余4套方案接口无缝切换package com.ai.rag.controller; import com.ai.rag.common.R; import com.ai.rag.service.DocumentService; import com.ai.rag.service.RagQaService; import com.ai.rag.util.LuaLimitUtil; import com.ai.rag.util.RedisLimitUtil; import com.google.common.util.concurrent.RateLimiter; import io.github.bucket4j.Bucket; import lombok.RequiredArgsConstructor; import org.springframework.web.bind.annotation.*; import org.springframework.web.multipart.MultipartFile; import javax.annotation.Resource; RestController RequestMapping(/api/rag) RequiredArgsConstructor public class RagController { private final DocumentService documentService; private final RagQaService ragQaService; Resource private Bucket aiChatBucket; Resource private Bucket uploadBucket; Resource private RateLimiter aiGuavaLimiter; Resource private RateLimiter uploadGuavaLimiter; Resource private RedisLimitUtil redisLimitUtil; Resource private LuaLimitUtil luaLimitUtil; // 1. Resilience4j 熔断限流 【生产默认主方案】 GetMapping(/chat) io.github.resilience4j.ratelimiter.annotation.RateLimiter(name aiChatLimit) io.github.resilience4j.circuitbreaker.annotation.CircuitBreaker(name aiChatCircuit, fallbackMethod chatFallback) public RString chat(RequestParam String sessionId, RequestParam String question) { return R.ok(ragQaService.chat(sessionId, question)); } PostMapping(/upload) io.github.resilience4j.ratelimiter.annotation.RateLimiter(name uploadLimit) io.github.resilience4j.circuitbreaker.annotation.CircuitBreaker(name uploadCircuit, fallbackMethod uploadFallback) public RString upload(RequestParam MultipartFile file) throws Exception { documentService.uploadAndEmbed(file); return R.ok(文档上传并完成向量化); } // 2. Bucket4j 高性能限流接口 GetMapping(/chat/bucket4j) public RString chatByBucket4j(RequestParam String sessionId, RequestParam String question) { if (!aiChatBucket.tryConsume(1)) { return R.fail(【Bucket4j】AI问答接口访问限流); } return R.ok(ragQaService.chat(sessionId, question)); } // 3. Guava 轻量限流接口 GetMapping(/chat/guava) public RString chatByGuava(RequestParam String sessionId, RequestParam String question) { if (!aiGuavaLimiter.tryAcquire()) { return R.fail(【Guava】AI问答访问频繁请稍后); } return R.ok(ragQaService.chat(sessionId, question)); } // 4. Redisson 分布式限流接口 GetMapping(/chat/redisson) public RString chatByRedisson(RequestParam String sessionId, RequestParam String question) { if (!redisLimitUtil.tryLimit(ai:chat:cluster:limit, 5)) { return R.fail(【Redisson】集群访问限流); } return R.ok(ragQaService.chat(sessionId, question)); } // 5. Redis-Lua 原生限流接口 GetMapping(/chat/lua) public RString chatByLua(RequestParam String sessionId, RequestParam String question) { if (!luaLimitUtil.tryLimit(ai:chat:lua:limit, 5)) { return R.fail(【Lua】接口请求受限); } return R.ok(ragQaService.chat(sessionId, question)); } DeleteMapping(/clear) public RString clear() { documentService.clearVectorStore(); return R.ok(向量库清空成功); } // 统一降级兜底方法 public RString chatFallback(String sessionId, String question, Throwable e) { return R.fail(AI服务繁忙已熔断降级保护请稍后重试); } public RString uploadFallback(MultipartFile file, Throwable e) { return R.fail(文档上传服务异常已降级); } }11. 生产避坑规范❌ 禁止仅用限流无熔断AI大模型超时堆积必雪崩❌ 集群环境禁止使用Guava/本地Bucket4j限流失效❌ 新项目禁止使用Hystrix、老旧自研熔断✅ 职责拆分熔断统一Resilience4j限流按场景拆分✅ 大文件上传独立限流不占用问答接口流量配额✅ 集群环境必须搭配Redisson实现全局流量管控12. 项目启动顺序启动 Redis、MySQL、Milvus/Chroma 向量库修改yml中大通义千问API密钥刷新Maven依赖启动SpringBoot项目默认接口/api/rag/chat自带熔断限流降级13. 接口测试清单Resilience4j默认GET /api/rag/chatBucket4jGET /api/rag/chat/bucket4jGuavaGET /api/rag/chat/guavaRedisson分布式GET /api/rag/chat/redissonLua原生GET /api/rag/chat/lua文档上传POST /api/rag/upload清空向量库DELETE /api/rag/clear