{"id":"4db092bf-f69a-4b0a-b760-aee0193edf2b","slug":"crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-","name":"AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","description":"一个开箱即用的完整智能客服服务：基于 FastAPI + LangChain RAG + CrewAI 多 Agent 构建， 提供意图识别路由、知识库问答、多智能体协作、SSE 流式对话等核心客服能力，并内置 检索工程（BM25+RRF+reranker）、稳定性工程（重试/限流/语义缓存）、可观测性（实时监控控制台） 与效果评估体系（RAGAS 评测闭环），可直接部署上线，也可作为独立 AI 服务被现有业务系统（如 Spring Cloud / Node.js 后端）通过 HTTP/SSE 集成调用。","canonicalUrl":"https://www.xpersona.co/skill/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-","sourceUrl":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","homepage":null,"source":"GITHUB_REPOS","vendor":{"slug":"liubaijiangde-bot","label":"Liubaijiangde Bot","url":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-"},"protocols":["OPENCLEW"],"capabilities":["crewai","multi-agent"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-10-09T15:56:32.444Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Liubaijiangde Bot"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Liubaijiangde Bot","href":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","sourceUrl":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T15:56:32.451Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T15:56:32.451Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"59 GitHub stars","href":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","sourceUrl":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T15:56:32.451Z","isPublic":true},{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["59 GitHub stars","Trust evidence available"],"agentCard":{"name":"AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","description":"一个开箱即用的完整智能客服服务：基于 FastAPI + LangChain RAG + CrewAI 多 Agent 构建， 提供意图识别路由、知识库问答、多智能体协作、SSE 流式对话等核心客服能力，并内置 检索工程（BM25+RRF+reranker）、稳定性工程（重试/限流/语义缓存）、可观测性（实时监控控制台） 与效果评估体系（RAGAS 评测闭环），可直接部署上线，也可作为独立 AI 服务被现有业务系统（如 Spring Cloud / Node.js 后端）通过 HTTP/SSE 集成调用。","source":"GITHUB_REPOS","sourceId":"crewai:1329315609","repository":"https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-","documentation":"https://www.xpersona.co/skill/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-/agent/crewai-liubaijiangde-bot-ai-robot-fastapi-langchain-rag-crewai-","protocols":["OPENCLEW"],"capabilities":["crewai","multi-agent"],"languages":["python"],"install":{"command":"git clone https://github.com/liubaijiangde-bot/AI-Robot-FastAPI-LangChain-RAG-CrewAI-Agent-.git","ecosystem":"git"},"examples":[{"kind":"example","language":"text","snippet":"客户端（小程序 / Web / 后端服务）\n  │  POST /api/v1/chat | /chat/stream | /ingest\n  ▼\nFastAPI (app/main.py)\n  │  ── 请求日志中间件（耗时统计） / 滑动窗口限流中间件 / 统一异常兜底\n  │\n  ├─ CrewAI 可用 → 多 Agent（意图识别官 → 客服执行员，独立线程）\n  │                  ├─ search_knowledge（RAG 检索增强生成）\n  │                  ├─ query_order（Mock，生产 HTTP 对接 order-server）\n  │                  └─ after_sale_rule（售后规则）\n  │\n  └─ 降级 → 内置 LangChain 路由（意图分类 + RAG/闲聊，逻辑与 Crew 一致）\n        │\n  └─ 稳定性层：语义缓存（首轮双门限）→ 重试（LLM/Embedding）→ 限流（入口）\n        │\n  └─ RAG 链路：\n      文档解析(pypdf/python-docx) → 分块(Recursive / Markdown 标题)\n        → Embedding(OpenAI 兼容) → 向量检索\n        → 混合：jieba+BM25 词面检索 → RRF 融合 → bge-reranker 重排\n        → RAG 生成（带会话记忆）\n        │\n  └─ 可观测：traces 链路追踪 → /dashboard 控制台 / /api/v1/traces / /api/v1/stats"},{"kind":"example","language":"text","snippet":"客户端 ──POST /api/v1/chat──▶ 限流中间件（放行/429）\n      ──▶ 语义缓存检查（仅首轮无上下文：embedding → 双门限；命中直接返回）\n      ──▶ 意图分类（LLM：knowledge/order/chat）\n      ──▶ 执行：knowledge → 混合检索(向量+BM25→RRF→重排) → RAG 生成\n              order     → 订单工具（Mock/HTTP）\n              chat      → LLM 闲聊\n      ──▶ 写会话记忆 + 写语义缓存（知识类） + 记录链路追踪\n      ──▶ 200 JSON {reply, intent, sources, engine, cache_hit}"}]}}