[{"data":1,"prerenderedAt":1759},["ShallowReactive",2],{"header-counts":3,"footer-counts":6,"compare-anythingllm-vs-fastgpt":8,"compare-a-anythingllm":9,"compare-b-fastgpt":583},{"tools":4,"reviews":5},98,27,{"tools":4,"reviews":5,"playbooks":7,"news":5},22,null,{"id":10,"title":11,"alternatives":12,"api_compatible":8,"body":16,"category":545,"chinese_friendly":531,"cover":546,"description":547,"domestic":548,"extension":549,"faq":8,"free":548,"github":526,"languages":550,"lastVerified":552,"meta":553,"models":8,"navigation":554,"notSuitable":8,"opensource":554,"path":555,"pillar":556,"platforms":557,"priceTable":8,"pricing":562,"published":563,"relatedPlaybooks":8,"relatedReviews":8,"score":564,"self_host":548,"seo":567,"seoTitle":568,"slug":569,"sources":570,"stem":573,"suitable":8,"tagline":574,"tags":575,"updated":552,"verdict":581,"website":518,"__hash__":582},"tools\u002Ftools\u002Fagent\u002Fplatform\u002Fanythingllm.md","AnythingLLM",[13,14,15],"agent\u002Fplatform\u002Fdify","agent\u002Fplatform\u002Ffastgpt","agent\u002Fplatform\u002Flangflow",{"type":17,"value":18,"toc":529},"minimark",[19,24,28,31,34,93,96,151,157,161,169,194,199,219,222,251,254,380,383,424,428,457,461,467,473,479,485,488,504,507,512],[20,21,23],"h2",{"id":22},"tldr","TL;DR",[25,26,27],"p",{},"AnythingLLM 是 Mintplex Labs 出品的开源私有部署 LLM 平台，MIT 协议，主打\"一站式 RAG 知识库 + Agent + 多用户权限管理\"。桌面应用 \u002F Docker 双部署模式，接入 OpenAI \u002F Claude \u002F Ollama \u002F Azure 等任意模型，Workspaces 隔离不同知识库，内置向量数据库。适合需要私有化部署 AI 知识库且不写代码的团队。",[25,29,30],{},"适合：企业内网知识库、团队共享 AI 助手、需要多用户权限控制的私有化场景。不适合：需要复杂 Agent 编排（用 Dify \u002F Langflow）、需要极致 RAG 召回精度（用 RAGFlow \u002F FastGPT）、需要大规模并发生产服务。",[20,32,33],{"id":33},"核心能力",[35,36,37,45,51,57,63,69,75,81,87],"ul",{},[38,39,40,44],"li",{},[41,42,43],"strong",{},"私有化部署","：Docker \u002F 桌面应用（Win\u002FMac\u002FLinux），数据完全在内网",[38,46,47,50],{},[41,48,49],{},"Workspaces 知识库隔离","：不同工作区独立向量库 + 文档 + 对话历史",[38,52,53,56],{},[41,54,55],{},"多用户权限管理","：管理员 \u002F 用户 \u002F 多工作区角色分配，适合团队使用",[38,58,59,62],{},[41,60,61],{},"任意模型接入","：OpenAI \u002F Claude \u002F Azure \u002F Ollama \u002F LM Studio \u002F 本地模型",[38,64,65,68],{},[41,66,67],{},"多向量数据库","：内置 LanceDB，可选 Chroma \u002F Pinecone \u002F Weaviate \u002F Qdrant",[38,70,71,74],{},[41,72,73],{},"文档处理","：PDF \u002F Word \u002F Excel \u002F TXT \u002F Markdown \u002F 网页链接，自动切片 + 向量化",[38,76,77,80],{},[41,78,79],{},"Agent 能力","：内置 Web 搜索 \u002F RAG 搜索 \u002F SQL 查询等工具调用",[38,82,83,86],{},[41,84,85],{},"嵌入向量","：支持自定义 embedding 模型，兼容 OpenAI \u002F 本地嵌入",[38,88,89,92],{},[41,90,91],{},"API 接口","：提供完整 REST API，可集成到外部系统",[20,94,95],{"id":95},"价格",[97,98,99,114],"table",{},[100,101,102],"thead",{},[103,104,105,109,111],"tr",{},[106,107,108],"th",{},"方案",[106,110,95],{},[106,112,113],{},"核心功能",[115,116,117,129,140],"tbody",{},[103,118,119,123,126],{},[120,121,122],"td",{},"开源版",[120,124,125],{},"$0",[120,127,128],{},"完整功能，MIT 协议，自托管",[103,130,131,134,137],{},[120,132,133],{},"Cloud",[120,135,136],{},"$30\u002F月起",[120,138,139],{},"托管服务，免去运维，含团队协作",[103,141,142,145,148],{},[120,143,144],{},"Enterprise",[120,146,147],{},"联系销售",[120,149,150],{},"SSO \u002F 审计日志 \u002F 私有部署支持",[152,153,154],"blockquote",{},[25,155,156],{},"价格信息基于 2026-07 官网，可能调整。",[20,158,160],{"id":159},"体验与评测资料整理","体验与评测（资料整理）",[152,162,163],{},[25,164,165,166],{},"说明：本节基于官方文档与公开评测整理，非本站独立实测环境，具体数据请以官方为准。\n",[41,167,168],{},"亮点：",[35,170,171,179,182,185,188,191],{},[38,172,173,174,178],{},"Docker 部署极快，一条 ",[175,176,177],"code",{},"docker-compose up"," 起来就能用",[38,180,181],{},"Workspaces 隔离设计实用，不同部门知识库互不干扰",[38,183,184],{},"接 Ollama 本地模型完全离线运行，数据不出内网",[38,186,187],{},"桌面应用适合个人用户，安装即用零配置",[38,189,190],{},"文档上传后自动切片 + 向量化，问答效果在通用场景下可接受",[38,192,193],{},"多用户权限管理是开源 RAG 平台中少有的完整实现",[25,195,196],{},[41,197,198],{},"踩坑：",[35,200,201,204,207,210,213,216],{},[38,202,203],{},"文档切片策略偏简单（固定长度），复杂表格 \u002F 图文混排召回效果一般",[38,205,206],{},"大文件（100MB+ PDF）处理偶尔超时，需调超时参数",[38,208,209],{},"Agent 能力有限，复杂工具链编排不如 Dify",[38,211,212],{},"向量库默认 LanceDB 在数据量大时查询变慢，建议切 Qdrant \u002F Chroma",[38,214,215],{},"UI 偶有卡顿，文档列表加载慢",[38,217,218],{},"中文文档的 OCR 需要额外配置，默认对扫描件支持有限",[20,220,221],{"id":221},"上手",[223,224,225,232,239,242,245,248],"ol",{},[38,226,227,228,231],{},"Docker 部署：",[175,229,230],{},"docker-compose up -d","（官方提供 docker-compose.yml）",[38,233,234,235,238],{},"首次访问 ",[175,236,237],{},"http:\u002F\u002Flocalhost:3001","，创建管理员账号",[38,240,241],{},"Settings → LLM Provider 配置模型（OpenAI API Key 或 Ollama 地址）",[38,243,244],{},"创建 Workspace → 上传文档（PDF\u002FWord\u002FTXT）",[38,246,247],{},"等待文档向量化完成，在 Chat 中开始问答",[38,249,250],{},"Settings → Users 添加团队成员并分配工作区权限",[20,252,253],{"id":253},"对比",[97,255,256,274],{},[100,257,258],{},[103,259,260,263,265,268,271],{},[106,261,262],{},"维度",[106,264,11],{},[106,266,267],{},"Dify",[106,269,270],{},"FastGPT",[106,272,273],{},"Langflow",[115,275,276,291,307,321,337,351,364],{},[103,277,278,281,284,287,289],{},[120,279,280],{},"部署门槛",[120,282,283],{},"极低",[120,285,286],{},"中",[120,288,286],{},[120,290,286],{},[103,292,293,296,299,302,304],{},[120,294,295],{},"多用户权限",[120,297,298],{},"✅ 完整",[120,300,301],{},"✅",[120,303,301],{},[120,305,306],{},"❌",[103,308,309,312,314,317,319],{},[120,310,311],{},"RAG 精度",[120,313,286],{},[120,315,316],{},"高",[120,318,316],{},[120,320,286],{},[103,322,323,326,329,332,334],{},[120,324,325],{},"Agent 编排",[120,327,328],{},"基础",[120,330,331],{},"强",[120,333,286],{},[120,335,336],{},"强（可视化）",[103,338,339,342,345,347,349],{},[120,340,341],{},"模型接入",[120,343,344],{},"丰富",[120,346,344],{},[120,348,344],{},[120,350,344],{},[103,352,353,356,358,360,362],{},[120,354,355],{},"桌面应用",[120,357,301],{},[120,359,306],{},[120,361,306],{},[120,363,306],{},[103,365,366,369,372,375,378],{},[120,367,368],{},"协议",[120,370,371],{},"MIT",[120,373,374],{},"Apache 2.0",[120,376,377],{},"FastGPT Open",[120,379,371],{},[20,381,382],{"id":382},"避坑",[35,384,385,391,397,403,412,418],{},[38,386,387,390],{},[41,388,389],{},"切片策略默认偏简单","：对结构化文档（表格\u002F代码）效果差，可调 chunk size",[38,392,393,396],{},[41,394,395],{},"LanceDB 大数据量变慢","：文档超过 1 万条建议切 Qdrant 或 Chroma",[38,398,399,402],{},[41,400,401],{},"大文件超时","：调整 Docker 超时配置，或拆分文档上传",[38,404,405,408,409],{},[41,406,407],{},"Ollama 连接","：Docker 内访问宿主机 Ollama 需用 ",[175,410,411],{},"host.docker.internal",[38,413,414,417],{},[41,415,416],{},"embedding 模型选择","：中文场景建议用 bge-large-zh 而非默认 OpenAI embedding",[38,419,420,423],{},[41,421,422],{},"不要当生产级 Agent 平台用","：Agent 能力是辅助，复杂编排上 Dify",[20,425,427],{"id":426},"适合-不适合","适合 \u002F 不适合",[35,429,430,433,436,439,442,445,448,451,454],{},[38,431,432],{},"✅ 企业内网私有化 AI 知识库",[38,434,435],{},"✅ 团队共享 AI 助手 + 多用户权限管理",[38,437,438],{},"✅ 接 Ollama 完全离线运行",[38,440,441],{},"✅ 个人桌面端快速体验 RAG",[38,443,444],{},"✅ 需要快速验证 RAG 概念的原型项目",[38,446,447],{},"❌ 需要复杂 Agent 工作流编排（用 Dify \u002F Langflow）",[38,449,450],{},"❌ 需要极致 RAG 召回精度（用 RAGFlow \u002F FastGPT）",[38,452,453],{},"❌ 大规模并发生产服务（架构未做高可用）",[38,455,456],{},"❌ 需要深度文档解析（复杂表格\u002F公式\u002F扫描件）",[20,458,460],{"id":459},"faq","FAQ",[25,462,463,466],{},[41,464,465],{},"Q: AnythingLLM 和 Dify 怎么选？","\nA: AnythingLLM 更轻量，部署快、有桌面应用、多用户权限开箱即用，适合快速搭建团队知识库。Dify 功能更全面，Agent 编排、工作流、API 发布能力更强，适合需要构建复杂 AI 应用的团队。简单知识库选 AnythingLLM，复杂应用选 Dify。",[25,468,469,472],{},[41,470,471],{},"Q: 可以完全离线使用吗？","\nA: 可以。接 Ollama 本地模型 + 用本地 embedding 模型（如 bge-large-zh）+ 内置 LanceDB 向量库，整个系统完全离线运行，数据不出内网。适合数据敏感的企业场景。",[25,474,475,478],{},[41,476,477],{},"Q: 免费开源版有什么限制？","\nA: MIT 协议开源版功能完整，无用户数 \u002F 文档数 \u002F API 调用限制。Cloud 版和 Enterprise 版主要是托管服务和企业管理功能（SSO \u002F 审计日志），功能层面开源版已够用。",[25,480,481,484],{},[41,482,483],{},"Q: 支持中文文档吗？","\nA: 支持，但效果取决于 embedding 模型。默认 OpenAI embedding 对中文尚可，追求精度建议切换 bge-large-zh 或 m3e 模型。OCR 扫描件需额外配置 Tesseract 或接入外部 OCR 服务。",[20,486,487],{"id":487},"相关阅读",[25,489,490,495,496,495,500],{},[491,492,494],"a",{"href":493},"\u002Fagent\u002Fplatform\u002Fragflow.html","RAGFlow"," · ",[491,497,499],{"href":498},"\u002Fagent\u002Fplatform\u002Fflowise.html","Flowise",[491,501,503],{"href":502},"\u002Fagent\u002Fgeneral\u002Fperplexity.html","Perplexity",[20,505,506],{"id":506},"来源",[152,508,509],{},[25,510,511],{},"本文的价格、版本号与性能数据均参考以下官方渠道整理，可能随时间变动，请以官方实时信息为准。",[35,513,514,522],{},[38,515,516],{},[491,517,521],{"href":518,"rel":519},"https:\u002F\u002Fuseanything.com",[520],"nofollow","官网",[38,523,524],{},[491,525,528],{"href":526,"rel":527},"https:\u002F\u002Fgithub.com\u002FMintplex-Labs\u002Fanything-llm",[520],"GitHub",{"title":530,"searchDepth":531,"depth":531,"links":532},"",3,[533,535,536,537,538,539,540,541,542,543,544],{"id":22,"depth":534,"text":23},2,{"id":33,"depth":534,"text":33},{"id":95,"depth":534,"text":95},{"id":159,"depth":534,"text":160},{"id":221,"depth":534,"text":221},{"id":253,"depth":534,"text":253},{"id":382,"depth":534,"text":382},{"id":426,"depth":534,"text":427},{"id":459,"depth":534,"text":460},{"id":487,"depth":534,"text":487},{"id":506,"depth":534,"text":506},"platform","\u002Fimg\u002Ftools\u002Fanythingllm.webp","AnythingLLM 真实评测：Mintplex Labs 出品的开源私有部署 LLM 平台（MIT 协议），一站式 RAG 知识库 + Agent + 多用户权限管理。支持 Docker\u002F桌面部署，接入 OpenAI\u002FClaude\u002FOllama 等任意模型，适合企业内网私有化 AI 知识库场景。",false,"md",[551],"en","2026-07-30",{},true,"\u002Ftools\u002Fagent\u002Fplatform\u002Fanythingllm","agent",[558,559,560,561],"windows","macos","linux","docker","Free \u002F 开源（MIT）\u002F Cloud","2026-07-05",{"power":531,"ux":565,"price":566,"cn_support":531,"stability":531},4,5,{"title":11,"description":547},"AnythingLLM - 开源私有部署 LLM 平台评测 | AIHO","agent\u002Fplatform\u002Fanythingllm",[571,572],{"title":521,"url":518},{"title":528,"url":526},"tools\u002Fagent\u002Fplatform\u002Fanythingllm","开源私有部署 LLM 平台，一站式 RAG + Agent + 多用户",[576,577,578,579,580],"agent-platform","opensource","self-host","rag","multi-user","需要快速搭建私有化 AI 知识库且要求多用户权限管理的企业团队首选，MIT 协议 + 桌面\u002FDocker 双模式 + 任意模型接入降低了部署门槛，但 RAG 精度和 Agent 编排能力不及 Dify\u002FFastGPT 等专业平台。","iKAMhkQImqK_QZGWLaE4i_9IjAMMpCeSwojp4L34T6A",{"id":584,"title":270,"alternatives":585,"api_compatible":588,"body":590,"category":545,"chinese_friendly":566,"cover":1679,"description":1680,"domestic":548,"extension":549,"faq":8,"free":548,"github":1638,"languages":1681,"lastVerified":8,"meta":1683,"models":1684,"navigation":554,"notSuitable":1691,"opensource":554,"path":1695,"pillar":556,"platforms":1696,"priceTable":1697,"pricing":1721,"published":1722,"relatedPlaybooks":1723,"relatedReviews":1725,"score":1730,"self_host":554,"seo":1731,"seoTitle":1732,"slug":14,"sources":1733,"stem":1744,"suitable":1745,"tagline":1751,"tags":1752,"updated":1756,"verdict":1757,"website":1631,"__hash__":1758},"tools\u002Ftools\u002Fagent\u002Fplatform\u002Ffastgpt.md",[13,586,15,587],"agent\u002Fplatform\u002Fcoze","agent\u002Fplatform\u002Fn8n",[589],"openai",{"type":17,"value":591,"toc":1661},[592,594,628,639,642,647,650,664,667,693,697,704,736,743,747,801,808,811,814,817,824,870,877,881,912,916,1047,1050,1053,1057,1065,1191,1206,1209,1373,1384,1419,1425,1428,1504,1506,1509,1529,1532,1550,1552,1622,1624,1649,1657],[20,593,23],{"id":22},[595,596,601,617],"div",{"className":597},[598,599,600],"card","p-5","my-4",[25,602,603,606,607,612,613,616],{},[41,604,605],{},"一句话："," labring 团队开源的 LLM 知识库 RAG 平台，27k+ GitHub star（截至 2026-03 数据，",[491,608,611],{"href":609,"rel":610},"https:\u002F\u002Fcloud.tencent.com\u002Fdeveloper\u002Farticle\u002F2632669",[520],"腾讯云 2026-03 教程"," 引用），Apache 2.0 许可证可商用。",[41,614,615],{},"核心优势是 RAG 链路工程做得极细","——问题预处理、混合检索、重排序、上下文组装、答案生成每一步都可视化调参。",[25,618,619,620,623,624,627],{},"最大价值在 ",[41,621,622],{},"国内企业知识库 + 私有部署"," 场景。代价是 ",[41,625,626],{},"配置门槛","：docker 基础 + 网络知识 + 一定运维能力。",[152,629,630],{},[25,631,632,633,638],{},"来源说明：本文基于 fastgpt.io 官方页面、github.com\u002Flabring\u002FFastGPT 仓库、",[491,634,637],{"href":635,"rel":636},"https:\u002F\u002Fwww.nanhuantech.com\u002Fzh\u002Fai-reviews\u002Ffastgpt-2025-review",[520],"南环 AI 2026-05 评测","、腾讯云开发者社区 2026-03 部署教程综合整理。版本迭代较快，命令和价格请以最新官方文档为准。",[20,640,641],{"id":641},"核心特性",[643,644,646],"h3",{"id":645},"知识库管理核心能力","知识库管理（核心能力）",[25,648,649],{},"支持文件类型：",[35,651,652,655,658,661],{},[38,653,654],{},"文档：PDF \u002F Word \u002F Markdown \u002F TXT \u002F HTML",[38,656,657],{},"表格：Excel \u002F CSV",[38,659,660],{},"网页：URL 抓取 + 定时同步",[38,662,663],{},"API：通过接口推送内容",[25,665,666],{},"处理流程：上传 → 文本切分 → 向量化 → 存储 → 可用于问答。支持：",[35,668,669,675,681,687],{},[38,670,671,674],{},[41,672,673],{},"文件夹分组","：不同主题 \u002F 部门分类",[38,676,677,680],{},[41,678,679],{},"多种分块策略","：默认按段落 \u002F 按 token 数 \u002F 自定义",[38,682,683,686],{},[41,684,685],{},"批量导入","：脚本化大批量同步",[38,688,689,692],{},[41,690,691],{},"定时同步","：网页源自动更新",[643,694,696],{"id":695},"rag-流程编排最强卖点","RAG 流程编排（最强卖点）",[25,698,699,703],{},[491,700,702],{"href":635,"rel":701},[520],"南环 AI 2026 评测"," 总结的 FastGPT RAG 链路：",[223,705,706,712,718,724,730],{},[38,707,708,711],{},[41,709,710],{},"问题预处理","：改写 \u002F 扩展 \u002F 错词纠正（提升召回率）",[38,713,714,717],{},[41,715,716],{},"检索策略","：语义检索 \u002F 关键词 BM25 \u002F 混合检索，可调相似度阈值",[38,719,720,723],{},[41,721,722],{},"重排序（Rerank）","：对初步检索结果二次排序，提升相关性",[38,725,726,729],{},[41,727,728],{},"上下文组装","：最优 chunk + 问题 → prompt",[38,731,732,735],{},[41,733,734],{},"答案生成","：调大模型基于检索结果回答 + 引用标注",[25,737,738,739,742],{},"每一步都可视化调参，这是 FastGPT 比 Coze \u002F Dify 在 ",[41,740,741],{},"纯知识库 QA 精度","上更高的原因。",[643,744,746],{"id":745},"多模型支持不绑定厂商","多模型支持（不绑定厂商）",[97,748,749,759],{},[100,750,751],{},[103,752,753,756],{},[106,754,755],{},"模型类别",[106,757,758],{},"支持",[115,760,761,769,777,785,793],{},[103,762,763,766],{},[120,764,765],{},"国产闭源",[120,767,768],{},"豆包 \u002F 通义千问 \u002F 文心一言 \u002F 智谱 GLM \u002F Moonshot Kimi \u002F MiniMax",[103,770,771,774],{},[120,772,773],{},"开源",[120,775,776],{},"LLaMA \u002F Qwen \u002F ChatGLM \u002F DeepSeek 等可自部署",[103,778,779,782],{},[120,780,781],{},"OpenAI 系",[120,783,784],{},"GPT-5 \u002F GPT-5 mini \u002F o3",[103,786,787,790],{},[120,788,789],{},"Claude 系",[120,791,792],{},"Sonnet 4 \u002F Opus 4 \u002F Haiku",[103,794,795,798],{},[120,796,797],{},"嵌入 \u002F 重排",[120,799,800],{},"BGE \u002F m3e \u002F OpenAI text-embedding-3",[25,802,803,804,807],{},"可以在 ",[41,805,806],{},"应用级别","为不同知识库 \u002F 不同场景配置不同模型，做\"低成本 embedding + 高质量 LLM 生成\"组合。",[643,809,810],{"id":810},"工作流与高级编排",[25,812,813],{},"新版本（v4.14.x）支持类似 Dify 的工作流节点编排——条件分支、循环、HTTP 调用、代码节点。能做\"分类 → 路由到不同子知识库 → 不同模型回答\"这类复杂场景。",[643,815,816],{"id":816},"多向量库选择",[25,818,819,823],{},[491,820,822],{"href":609,"rel":821},[520],"腾讯云教程"," 公开的 4 种向量后端：",[97,825,826,836],{},[100,827,828],{},[103,829,830,833],{},[106,831,832],{},"后端",[106,834,835],{},"适用",[115,837,838,846,854,862],{},[103,839,840,843],{},[120,841,842],{},"PgVector",[120,844,845],{},"5000 万索引以下，新手 \u002F 小规模",[103,847,848,851],{},[120,849,850],{},"Milvus",[120,852,853],{},"亿级以上，高性能",[103,855,856,859],{},[120,857,858],{},"Zilliz Cloud",[120,860,861],{},"Milvus 全托管 SaaS",[103,863,864,867],{},[120,865,866],{},"SeekDB \u002F OceanBase",[120,868,869],{},"企业级国产化",[25,871,872,873,876],{},"部署时选对应 ",[175,874,875],{},"docker-compose.{pgvector|milvus|...}.yml","。",[643,878,880],{"id":879},"api-与-mcp","API 与 MCP",[35,882,883,889,895,906],{},[38,884,885,888],{},[41,886,887],{},"对话 API","：流式 \u002F 非流式 HTTP，OpenAI 兼容",[38,890,891,894],{},[41,892,893],{},"知识库检索 API","：单独调检索（不走生成）做 hybrid pipeline",[38,896,897,900,901,905],{},[41,898,899],{},"MCP Server","：3005 端口暴露 MCP SSE 服务，可被 ",[491,902,904],{"href":903},"\u002Fcoding\u002Fcli\u002Fclaude-code.html","Claude Code"," 等客户端直接接入",[38,907,908,911],{},[41,909,910],{},"Webhook","：回调通知",[20,913,915],{"id":914},"部署-10-分钟docker","部署 10 分钟（Docker）",[917,918,922],"pre",{"className":919,"code":920,"language":921,"meta":530,"style":530},"language-bash shiki shiki-themes github-light github-dark","# 克隆代码\ngit clone https:\u002F\u002Fgithub.com\u002Flabring\u002FFastGPT.git\ncd FastGPT\n\n# 切到最新稳定版（参考 GitHub releases）\ngit switch -c 4.14.7.2\n\n# 选向量库版本（个人 \u002F 小规模选 pg）\ncd deploy\u002Fdocker\u002Fcn\nwget https:\u002F\u002Fdoc.fastgpt.cn\u002Fdeploy\u002Fconfig\u002Fconfig.json\n\n# 启动\ndocker-compose -f docker-compose.pg.yml up -d\n\n# 访问 http:\u002F\u002F\u003Cip>:3000，默认账号 root \u002F 1234\n","bash",[175,923,924,933,946,955,960,965,979,984,990,998,1007,1012,1018,1036,1041],{"__ignoreMap":530},[925,926,929],"span",{"class":927,"line":928},"line",1,[925,930,932],{"class":931},"sJ8bj","# 克隆代码\n",[925,934,935,939,943],{"class":927,"line":534},[925,936,938],{"class":937},"sScJk","git",[925,940,942],{"class":941},"sZZnC"," clone",[925,944,945],{"class":941}," https:\u002F\u002Fgithub.com\u002Flabring\u002FFastGPT.git\n",[925,947,948,952],{"class":927,"line":531},[925,949,951],{"class":950},"sj4cs","cd",[925,953,954],{"class":941}," FastGPT\n",[925,956,957],{"class":927,"line":565},[925,958,959],{"emptyLinePlaceholder":554},"\n",[925,961,962],{"class":927,"line":566},[925,963,964],{"class":931},"# 切到最新稳定版（参考 GitHub releases）\n",[925,966,968,970,973,976],{"class":927,"line":967},6,[925,969,938],{"class":937},[925,971,972],{"class":941}," switch",[925,974,975],{"class":950}," -c",[925,977,978],{"class":950}," 4.14.7.2\n",[925,980,982],{"class":927,"line":981},7,[925,983,959],{"emptyLinePlaceholder":554},[925,985,987],{"class":927,"line":986},8,[925,988,989],{"class":931},"# 选向量库版本（个人 \u002F 小规模选 pg）\n",[925,991,993,995],{"class":927,"line":992},9,[925,994,951],{"class":950},[925,996,997],{"class":941}," deploy\u002Fdocker\u002Fcn\n",[925,999,1001,1004],{"class":927,"line":1000},10,[925,1002,1003],{"class":937},"wget",[925,1005,1006],{"class":941}," https:\u002F\u002Fdoc.fastgpt.cn\u002Fdeploy\u002Fconfig\u002Fconfig.json\n",[925,1008,1010],{"class":927,"line":1009},11,[925,1011,959],{"emptyLinePlaceholder":554},[925,1013,1015],{"class":927,"line":1014},12,[925,1016,1017],{"class":931},"# 启动\n",[925,1019,1021,1024,1027,1030,1033],{"class":927,"line":1020},13,[925,1022,1023],{"class":937},"docker-compose",[925,1025,1026],{"class":950}," -f",[925,1028,1029],{"class":941}," docker-compose.pg.yml",[925,1031,1032],{"class":941}," up",[925,1034,1035],{"class":950}," -d\n",[925,1037,1039],{"class":927,"line":1038},14,[925,1040,959],{"emptyLinePlaceholder":554},[925,1042,1044],{"class":927,"line":1043},15,[925,1045,1046],{"class":931},"# 访问 http:\u002F\u002F\u003Cip>:3000，默认账号 root \u002F 1234\n",[25,1048,1049],{},"最低配置：2C4G + 20GB 硬盘 + Docker 28+ + Docker Compose 2.20+。",[25,1051,1052],{},"进入后台 → 账号 → 模型提供商 → 配置至少 1 个对话模型 + 1 个嵌入模型 → 即可开始建知识库。",[20,1054,1056],{"id":1055},"云版-vs-自托管对比","云版 vs 自托管对比",[25,1058,1059,1064],{},[491,1060,1063],{"href":1061,"rel":1062},"https:\u002F\u002Ffastgpt.io\u002Fzh\u002Fprice",[520],"fastgpt.io 官方定价"," 公开数据：",[97,1066,1067,1094],{},[100,1068,1069],{},[103,1070,1071,1074,1076,1079,1082,1085,1088,1091],{},[106,1072,1073],{},"套餐",[106,1075,95],{},[106,1077,1078],{},"AI 积分",[106,1080,1081],{},"知识库索引",[106,1083,1084],{},"团队",[106,1086,1087],{},"Agent",[106,1089,1090],{},"知识库",[106,1092,1093],{},"QPM",[115,1095,1096,1122,1146,1170],{},[103,1097,1098,1101,1104,1107,1110,1113,1116,1119],{},[120,1099,1100],{},"免费",[120,1102,1103],{},"¥0",[120,1105,1106],{},"100",[120,1108,1109],{},"600",[120,1111,1112],{},"1",[120,1114,1115],{},"10",[120,1117,1118],{},"3",[120,1120,1121],{},"30",[103,1123,1124,1126,1129,1132,1135,1138,1141,1143],{},[120,1125,328],{},[120,1127,1128],{},"¥99\u002F月",[120,1130,1131],{},"4000",[120,1133,1134],{},"6000",[120,1136,1137],{},"5",[120,1139,1140],{},"50",[120,1142,1121],{},[120,1144,1145],{},"300",[103,1147,1148,1151,1154,1157,1160,1162,1165,1167],{},[120,1149,1150],{},"高级",[120,1152,1153],{},"¥599\u002F月",[120,1155,1156],{},"25000",[120,1158,1159],{},"36000",[120,1161,1140],{},[120,1163,1164],{},"200",[120,1166,1106],{},[120,1168,1169],{},"1500",[103,1171,1172,1175,1178,1181,1183,1185,1187,1189],{},[120,1173,1174],{},"定制",[120,1176,1177],{},"议价",[120,1179,1180],{},"弹性",[120,1182,1180],{},[120,1184,1180],{},[120,1186,1180],{},[120,1188,1180],{},[120,1190,1180],{},[25,1192,1193,1196,1197,1200,1201,1205],{},[41,1194,1195],{},"云版适合","：不想运维、量小、要快速上线\n",[41,1198,1199],{},"自托管适合","：量大（10 万+ 日问答）、数据敏感、要深度定制——按 ",[491,1202,1204],{"href":635,"rel":1203},[520],"南环评测"," 估算：\"日均 10 万次问答的企业场景，商业 SaaS 年费数十万，自建 FastGPT + 开源模型只需数万硬件投入\"",[20,1207,1208],{"id":1208},"与同类怎么选",[97,1210,1211,1234],{},[100,1212,1213],{},[103,1214,1215,1217,1219,1224,1230,1232],{},[106,1216,262],{},[106,1218,270],{},[106,1220,1221],{},[491,1222,267],{"href":1223},"\u002Fagent\u002Fplatform\u002Fdify.html",[106,1225,1226],{},[491,1227,1229],{"href":1228},"\u002Fagent\u002Fplatform\u002Fcoze.html","Coze",[106,1231,494],{},[106,1233,11],{},[115,1235,1236,1256,1272,1291,1309,1325,1341,1356],{},[103,1237,1238,1241,1244,1247,1250,1253],{},[120,1239,1240],{},"核心定位",[120,1242,1243],{},"知识库 QA",[120,1245,1246],{},"综合 LLMOps",[120,1248,1249],{},"Bot + 工作流",[120,1251,1252],{},"文档解析+RAG",[120,1254,1255],{},"桌面级 KB",[103,1257,1258,1260,1263,1265,1267,1269],{},[120,1259,773],{},[120,1261,1262],{},"✅ Apache 2.0",[120,1264,1262],{},[120,1266,306],{},[120,1268,1262],{},[120,1270,1271],{},"✅ MIT",[103,1273,1274,1277,1280,1283,1286,1289],{},[120,1275,1276],{},"私有部署",[120,1278,1279],{},"★★★★★ docker",[120,1281,1282],{},"★★★★★",[120,1284,1285],{},"⚠️ 仅企业版",[120,1287,1288],{},"★★★★☆",[120,1290,1282],{},[103,1292,1293,1296,1299,1301,1304,1307],{},[120,1294,1295],{},"RAG 深度",[120,1297,1298],{},"★★★★★ 最细",[120,1300,1288],{},[120,1302,1303],{},"★★★☆☆",[120,1305,1306],{},"★★★★★ 文档解析最强",[120,1308,1303],{},[103,1310,1311,1314,1316,1318,1320,1322],{},[120,1312,1313],{},"工作流",[120,1315,1288],{},[120,1317,1282],{},[120,1319,1288],{},[120,1321,1303],{},[120,1323,1324],{},"★★☆☆☆",[103,1326,1327,1329,1332,1334,1337,1339],{},[120,1328,221],{},[120,1330,1331],{},"★★★☆☆ 需 docker",[120,1333,1288],{},[120,1335,1336],{},"★★★★★ 最简单",[120,1338,1303],{},[120,1340,1288],{},[103,1342,1343,1346,1348,1350,1352,1354],{},[120,1344,1345],{},"中文优化",[120,1347,1282],{},[120,1349,1288],{},[120,1351,1282],{},[120,1353,1288],{},[120,1355,1303],{},[103,1357,1358,1361,1364,1366,1368,1371],{},[120,1359,1360],{},"多平台发布",[120,1362,1363],{},"⚠️ API 为主",[120,1365,1288],{},[120,1367,1282],{},[120,1369,1370],{},"⚠️",[120,1372,1370],{},[25,1374,1375,1378,1379,1383],{},[41,1376,1377],{},"怎么选","（综合 ",[491,1380,1382],{"href":635,"rel":1381},[520],"南环 AI 评测","）：",[35,1385,1386,1392,1400,1407,1413],{},[38,1387,1388,1391],{},[41,1389,1390],{},"核心需求是 RAG 精度"," → FastGPT",[38,1393,1394,1397,1398],{},[41,1395,1396],{},"需要丰富插件 + 复杂工作流 + 多平台发布"," → ",[491,1399,267],{"href":1223},[38,1401,1402,1397,1405],{},[41,1403,1404],{},"零代码、快速发布到飞书 \u002F 微信",[491,1406,1229],{"href":1228},[38,1408,1409,1412],{},[41,1410,1411],{},"文档解析（含 OCR \u002F 表格 \u002F 公式）是瓶颈"," → RAGFlow",[38,1414,1415,1418],{},[41,1416,1417],{},"桌面 \u002F 单机使用"," → AnythingLLM",[25,1420,1421,1424],{},[41,1422,1423],{},"很多企业同时用","：FastGPT 做知识库底座 + Coze 做前端 Bot 发布 \u002F 工作流编排。",[20,1426,1427],{"id":1427},"避坑清单",[35,1429,1430,1444,1453,1459,1469,1481,1487,1493],{},[38,1431,1432,1435,1436,1439,1440,1443],{},[41,1433,1434],{},"docker-compose 镜像 tag 不一致","：",[491,1437,822],{"href":609,"rel":1438},[520]," 实测的坑——某些版本编排文件的 image tag 与最新 release 不一致，启动报\"镜像找不到\"，手动改 ",[175,1441,1442],{},"image:"," 行为正确版本即可",[38,1445,1446,1449,1450,1452],{},[41,1447,1448],{},"3000 端口冲突","：默认占用 3000（主服务）\u002F 9000（S3 \u002F MinIO）\u002F 3005（MCP）；改 ",[175,1451,1023],{}," 的 ports 映射端口",[38,1454,1455,1458],{},[41,1456,1457],{},"PostgreSQL pgvector 不够用就换 Milvus","：单库索引超 5000 万时 pgvector 查询性能下降，切 Milvus",[38,1460,1461,1464,1465,1468],{},[41,1462,1463],{},"向量库选错代价大","：先评估索引量再选向量后端，迁移要重新 embedding 整库，按 ",[491,1466,1204],{"href":635,"rel":1467},[520],"：\"新手 \u002F 小规模 PgVector，中大规模 Milvus，企业 \u002F 国产 OceanBase\"",[38,1470,1471,1435,1474,1477,1478],{},[41,1472,1473],{},"MinIO 默认密码",[175,1475,1476],{},"minioadmin\u002Fminioadmin","，",[41,1479,1480],{},"部署到公网前必须改",[38,1482,1483,1486],{},[41,1484,1485],{},"分段策略影响巨大","：默认分段对长法律 \u002F 医疗文档不友好，需调\"按章节\"或\"自定义\"",[38,1488,1489,1492],{},[41,1490,1491],{},"嵌入模型 ≠ 对话模型","：经常有人只配 GPT-4 没配 embedding 模型，知识库无法索引——必须同时配两类",[38,1494,1495,1498,1499,1503],{},[41,1496,1497],{},"云版 AI 积分会过期","：未用完不能跨月累积（按 ",[491,1500,1502],{"href":1061,"rel":1501},[520],"fastgpt.io 定价 FAQ","）",[20,1505,427],{"id":426},[25,1507,1508],{},"✅ 适合：",[35,1510,1511,1514,1517,1520,1523,1526],{},[38,1512,1513],{},"企业内部知识库（员工手册 \u002F 制度 \u002F 流程）",[38,1515,1516],{},"产品 FAQ \u002F 用户手册问答",[38,1518,1519],{},"医疗 \u002F 法律 \u002F 金融垂直领域知识系统",[38,1521,1522],{},"数据严格不出网 + Apache 2.0 商用",[38,1524,1525],{},"有 docker 运维基础的技术团队",[38,1527,1528],{},"需要把 RAG 当后端服务的开发者（API 接入业务系统）",[25,1530,1531],{},"❌ 不适合：",[35,1533,1534,1539,1544,1547],{},[38,1535,1536,1537,1503],{},"完全非技术用户（去 ",[491,1538,1229],{"href":1228},[38,1540,1541,1542,1503],{},"主要需求是工作流 + 插件集成（去 ",[491,1543,267],{"href":1223},[38,1545,1546],{},"文档解析 \u002F OCR 是首要痛点（RAGFlow）",[38,1548,1549],{},"不想自己运维 + 量很小（FastGPT 云免费版起步即可）",[20,1551,487],{"id":487},[35,1553,1554,1567,1588,1611],{},[38,1555,1556,1557,1559,1560,1562,1563],{},"同类对比：",[491,1558,267],{"href":1223}," \u002F ",[491,1561,1229],{"href":1228}," \u002F RAGFlow \u002F AnythingLLM \u002F ",[491,1564,1566],{"href":1565},"\u002Fagent\u002Fplatform\u002Fn8n.html","n8n",[38,1568,1569,1570,1559,1574,1559,1578,1559,1581,1559,1584],{},"概念：",[491,1571,1573],{"href":1572},"\u002Fwiki\u002Frag.html","RAG",[491,1575,1577],{"href":1576},"\u002Fwiki\u002Fembedding.html","Embedding",[491,1579,1580],{"href":1576},"Vector Database",[491,1582,1583],{"href":1572},"Reranker",[491,1585,1587],{"href":1586},"\u002Fwiki\u002Fai-agent.html","AI Agent",[38,1589,1590,1591,1559,1595,1559,1599,1559,1603,1559,1607],{},"模型：",[491,1592,1594],{"href":1593},"\u002Fmodels\u002Fdeepseek-v3.html","DeepSeek-V3",[491,1596,1598],{"href":1597},"\u002Fmodels\u002Fqwen-3.html","Qwen3",[491,1600,1602],{"href":1601},"\u002Fmodels\u002Fglm-5.2.html","GLM-5.2",[491,1604,1606],{"href":1605},"\u002Fmodels\u002Fkimi-k2.html","Kimi K2",[491,1608,1610],{"href":1609},"\u002Fmodels\u002Fdoubao-1-5-pro.html","豆包 Doubao",[38,1612,1613,1614,1559,1618],{},"进阶：",[491,1615,1617],{"href":1616},"\u002Fwiki\u002Fcontext-engineering.html","Context Engineering",[491,1619,1621],{"href":1620},"\u002Fwiki\u002Fprompt-engineering.html","Prompt Engineering",[20,1623,506],{"id":506},[35,1625,1626,1633,1640,1646],{},[38,1627,1628,1629],{},"官网：",[491,1630,1631],{"href":1631,"rel":1632},"https:\u002F\u002Ffastgpt.io",[520],[38,1634,1635,1636],{},"GitHub：",[491,1637,1638],{"href":1638,"rel":1639},"https:\u002F\u002Fgithub.com\u002Flabring\u002FFastGPT",[520],[38,1641,1642,1643],{},"定价：",[491,1644,1061],{"href":1061,"rel":1645},[520],[38,1647,1648],{},"第三方评测：南环 AI \u002F 腾讯云开发者社区 \u002F 飞书 AGI 掘金知识库",[25,1650,1651,1652,1656],{},"本卡片由 AIHO 编辑部根据官方公开资料与第三方评测整理。所有事实点均标注来源；如发现价格 \u002F 命令 \u002F 功能与最新官方信息不一致，请通过 ",[491,1653,1655],{"href":1654},"mailto:hello@aiho.net","反馈邮箱"," 反馈。",[1658,1659,1660],"style",{},"html pre.shiki code .sJ8bj, html code.shiki .sJ8bj{--shiki-default:#6A737D;--shiki-dark:#6A737D}html pre.shiki code .sScJk, html code.shiki .sScJk{--shiki-default:#6F42C1;--shiki-dark:#B392F0}html pre.shiki code .sZZnC, html code.shiki .sZZnC{--shiki-default:#032F62;--shiki-dark:#9ECBFF}html pre.shiki code .sj4cs, html code.shiki .sj4cs{--shiki-default:#005CC5;--shiki-dark:#79B8FF}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"title":530,"searchDepth":531,"depth":531,"links":1662},[1663,1664,1672,1673,1674,1675,1676,1677,1678],{"id":22,"depth":534,"text":23},{"id":641,"depth":534,"text":641,"children":1665},[1666,1667,1668,1669,1670,1671],{"id":645,"depth":531,"text":646},{"id":695,"depth":531,"text":696},{"id":745,"depth":531,"text":746},{"id":810,"depth":531,"text":810},{"id":816,"depth":531,"text":816},{"id":879,"depth":531,"text":880},{"id":914,"depth":534,"text":915},{"id":1055,"depth":534,"text":1056},{"id":1208,"depth":534,"text":1208},{"id":1427,"depth":534,"text":1427},{"id":426,"depth":534,"text":427},{"id":487,"depth":534,"text":487},{"id":506,"depth":534,"text":506},"\u002Fimg\u002Ftools\u002Ffastgpt.webp","FastGPT 真实评测：开源 LLM 知识库 RAG 平台，labring 团队出品，27k+ GitHub star。一键 docker-compose 部署、RAG 流程编排可视化、多向量库支持。AIHO 编辑部基于官方文档与社区资料整理，含与 Dify\u002FCoze 对比、避坑指南。",[1682,551],"zh",{},[1685,1686,1687,1688,1689,1690],"deepseek-v3","qwen-max","doubao-pro","gpt-4o","claude-sonnet-4","kimi",[1692,1693,1694],"完全零代码 \u002F 不懂 docker 的用户（去 Coze）","Bot 多平台一键发布场景（Coze 强项）","插件 \u002F 工作流复杂集成（去 Dify）","\u002Ftools\u002Fagent\u002Fplatform\u002Ffastgpt",[558,559,560],[1698,1703,1708,1713,1717],{"plan":1699,"price":1100,"limit":1700,"cn_pay":1701,"note":1702},"Self-host 开源","全功能 + 全数据本地","—","Apache 2.0 可商用",{"plan":1704,"price":1705,"limit":1706,"cn_pay":1701,"note":1707},"云免费版","¥0\u002F月","100 AI 积分 + 600 索引 + 3 知识库","试水",{"plan":1709,"price":1128,"limit":1710,"cn_pay":1711,"note":1712},"云基础版","4000 积分 + 6000 索引 + 50 Agent","✅ 微信\u002F支付宝","中小团队 SaaS",{"plan":1714,"price":1153,"limit":1715,"cn_pay":301,"note":1716},"云高级版","25000 积分 + 36000 索引 + 50 成员 + 200 Agent + 1500 QPM","企业级生产",{"plan":1718,"price":1177,"limit":1719,"cn_pay":301,"note":1720},"云定制版","弹性资源 + 深度技术支持 + 专属客户经理","中大型企业","自托管开源免费 \u002F 云版 ¥0-¥599\u002F月","2026-06-18",[1724],"onboarding\u002Ffastgpt-getting-started",[1726,1727,1728,1729],"fastgpt-deep-review","coze-deep-review","coze-vs-dify","dify-deep-review",{"power":565,"ux":565,"price":566,"cn_support":566,"stability":565},{"title":270,"description":1680},"FastGPT 评测 2026：开源知识库问答平台，AI 工作流引擎，对比 Dify",[1734,1736,1738,1740,1742],{"title":1735,"url":1631},"FastGPT 官网",{"title":1737,"url":1638},"FastGPT GitHub",{"title":1739,"url":1061},"FastGPT 定价页",{"title":1741,"url":635},"FastGPT 2025 测评（南环 AI）",{"title":1743,"url":609},"FastGPT 部署教程（腾讯云）","tools\u002Fagent\u002Fplatform\u002Ffastgpt",[1746,1747,1748,1749,1750],"企业内部知识库（员工手册、规章、流程）","产品文档智能问答（FAQ \u002F 用户手册）","垂直领域知识库（医疗、法律、金融）","数据严格不出网的合规场景","需要精细 RAG 流程编排（重排序、混合检索、阈值调节）","开源知识库问答系统，国内私有部署友好",[576,577,578,579,1753,1754,1755],"china","knowledge-base","labring","2026-06-24","国内企业知识库私有化首选。RAG 召回工程做得很细，可视化调试好用，docker-compose 一键部署。生态插件不如 Dify 丰富。","NAay3javdz1FV9ZaZVXCpoCFdZlJu5B4E0Y3oSzmYLk",1785428440969]