[{"data":1,"prerenderedAt":101},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-flowise":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"name":8,"description":9,"phase":10,"docsUrl":11,"logo":12,"github":13,"tagline":14,"longDescription":15,"features":16,"useCases":23,"steps":33,"faq":46,"specs":62,"compatibleOs":70,"relatedApps":72,"relatedPosts":96,"category":98},"flowise","Flowise","Build LLM automation pipelines with drag-and-drop. Visual LangChain chains, connected to your existing tools.",1,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fheberger-flowise-vps","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fflowise.svg","https:\u002F\u002Fgithub.com\u002FFlowiseAI\u002FFlowise","Build LLM pipelines and AI chatbots with drag-and-drop — visual LangChain.","Flowise is an open-source tool that lets you build LLM applications (chatbots, agents, RAG pipelines) through a visual interface based on LangChain. Without writing any code, you can chain components — LLMs, vector databases, document parsers, API tools — to create functional AI applications.\n\nSelf-hosted on your VPS, Flowise gives you access to the full power of LangChain without the complexity of Python code. It supports many LLMs (OpenAI, Anthropic, Mistral, Ollama) and vector databases (Pinecone, Chroma, Qdrant). Ideal for teams who want to prototype AI applications quickly.",[17,18,19,20,21,22],"Drag-and-drop interface based on LangChain","Support for 20+ LLMs and 10+ vector databases","Visual RAG: connect your documents in a few clicks","One-click API deployment and chatbot widget","Flow sharing between team members","Marketplace of ready-to-use templates",[24,27,30],{"title":25,"body":26},"Document chatbot","Build, in a few hours, a chatbot able to answer questions about your internal PDFs.",{"title":28,"body":29},"Analysis pipeline","Automate the extraction of structured information from unstructured text (emails, contracts, reports).",{"title":31,"body":32},"Rapid AI prototype","Test complex LLM architectures without code before rewriting them cleanly in your application.",[34,37,40,43],{"title":35,"body":36},"Deploy Flowise","VPS with 2 GB RAM minimum. Run `docker run -d -p 3000:3000 flowiseai\u002Fflowise`. Flowise starts with its built-in SQLite database.",{"title":38,"body":39},"Configure persistence","In production, mount a Docker volume at `\u002Froot\u002F.flowise` to persist your flows and data across restarts.",{"title":41,"body":42},"Expose over HTTPS","Nginx reverse proxy + Certbot. Enable authentication in the environment variables (FLOWISE_USERNAME, FLOWISE_PASSWORD).",{"title":44,"body":45},"Create your first flow","In the editor, drag in an LLM, a conversation memory, and a prompt — connect them and test the chat in a few minutes.",[47,50,53,56,59],{"q":48,"a":49},"What is Flowise?","Flowise is an open-source tool that provides a visual interface for LangChain. It lets you build LLM applications (chatbots, RAG, agents) without writing any code.",{"q":51,"a":52},"Flowise vs Dify: which to choose?","Flowise is closer to LangChain — ideal for developers who want to build complex LLM pipelines. Dify is more oriented toward the finished product, with user management, monitoring, and deployment. The two are complementary.",{"q":54,"a":55},"How much RAM for Flowise?","Flowise itself runs with 1 GB of RAM. In practice, 2 GB is recommended for comfortable use, 4 GB if you pair it with a local vector database.",{"q":57,"a":58},"Does Flowise support Ollama?","Yes. You can connect a local Ollama instance — on the same VPS or a separate server — and use any open-source model in your flows.",{"q":60,"a":61},"Can Flowise flows be exported?","Yes. Flows can be exported as JSON. You can save them, share them, or import them into another Flowise instance.",{"ram":63,"cpu":64,"stack":65,"port":69},"2 GB","1 vCPU",[66,67,68],"Docker","Node.js","SQLite \u002F PostgreSQL","3000",[71],"ubuntu-24.04",[73,81,90],{"name":74,"slug":74,"categorySlug":75,"categoryName":76,"categoryColor":77,"logo":78,"tagline":79,"description":80},"n8n","automatisation","Automation & Workflows","text-brand-action bg-brand-action\u002F10","https:\u002F\u002Fcdn.simpleicons.org\u002Fn8n","Automate your business processes with 400+ integrations — 100% self-hosted on your VPS.","Automate your workflows across applications without code. Over 400 integrations, 100% self-hosted on your VPS.",{"name":82,"slug":83,"categorySlug":84,"categoryName":85,"categoryColor":86,"logo":87,"tagline":88,"description":89},"Dify","dify","ia","Artificial Intelligence","text-purple-400 bg-purple-500\u002F10","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fdify.svg","Build LLM applications with drag-and-drop — chatbots, agents, RAG pipelines — no backend required.","Build LLM applications visually: chatbots, RAG agents, pipelines — without writing any backend code.",{"name":91,"slug":92,"categorySlug":84,"categoryName":85,"categoryColor":86,"logo":93,"tagline":94,"description":95},"Open WebUI","open-webui","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopen-webui.svg","Web interface for your LLMs — Ollama, OpenAI, Mistral — hosted on your own server.","Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.",[97],"heberger-application-ia",{"key":75,"slug":75,"name":76,"objective":99,"icon":100,"color":77},"Automate business processes.","automation",1785628464515]