[{"data":1,"prerenderedAt":121},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-ma-en-open-webui":6,"promo-bar-likely":120},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"key":7,"data":8},"marketplace-app-ma-en-open-webui",{"slug":9,"slugs":10,"categorySlugs":11,"name":16,"description":17,"phase":18,"unavailableReason":19,"docsUrl":20,"logo":21,"github":22,"tagline":23,"longDescription":24,"features":25,"useCases":32,"steps":42,"faq":61,"specs":77,"requirements":85,"compatibleOs":89,"relatedApps":91,"relatedPosts":114,"category":117},"open-webui",{"fr":9,"en":9,"ar":9,"es":9},{"fr":12,"en":13,"ar":14,"es":15},"ia","artificial-intelligence","الذكاء-الاصطناعي","inteligencia-artificial","Open WebUI","Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.",1,null,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fhow-to-host-open-webui-on-a-vps","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopen-webui.svg","https:\u002F\u002Fgithub.com\u002Fopen-webui\u002Fopen-webui","Web interface for your LLMs — Ollama, OpenAI, Mistral — hosted on your own server.","Open WebUI is a source-available chat interface, compatible with Ollama and the OpenAI APIs, that lets you interact with language models from your browser. Deployed on your VPS, it replaces ChatGPT without sending your data to third parties: your conversations, documents and history stay on your infrastructure.\n\nIt is the ideal tool for teams that want to experiment with local LLMs (Llama 3, Mistral, Gemma) or remote ones while keeping full control of their exchanges. Open WebUI supports RAG (Retrieval-Augmented Generation), multi-model conversations and session sharing between users.",[26,27,28,29,30,31],"Compatible with Ollama (local models) and the OpenAI\u002FAnthropic API","Built-in RAG: query your PDF documents, texts and knowledge bases","Multi-user management with roles and permissions","Persistent conversation history, exportable","Multimodal support: text, images, code","Responsive interface, light\u002Fdark theme",[33,36,39],{"title":34,"body":35},"Internal team","Deploy a shared AI assistant for your team, connected to your internal documents, without exposing your data to OpenAI.",{"title":37,"body":38},"Development & testing","Test different LLM models side by side before integrating one of them into your application.",{"title":40,"body":41},"Intelligent knowledge base","Upload your PDFs, procedures and technical docs — ask questions in natural language.",[43,46,49,52,55,58],{"title":44,"body":45},"What the installation does for you","When the VPS is created, ServOrbit installs Docker if it is missing, then starts the official `ghcr.io\u002Fopen-webui\u002Fopen-webui:main` container, with its data in the `open-webui` volume. The interface listens on `127.0.0.1:3000`, the server's loopback interface: nothing is published on its IP address. Ollama is not included: Open WebUI alone needs 2 GB of RAM, and if you add Ollama on the same VPS, plan for at least 8 GB more for it.",{"title":47,"body":48},"Find the address and access details","The “Open WebUI is installed” email and your VPS page in the client area, under “Installed applications”, tell you how to open the app: its address when a domain is in place, otherwise the SSH tunnel command and the port. You will also find the link to this guide and the “Support” button there.",{"title":50,"body":51},"Open Open WebUI without a domain","From your computer, run `ssh -L 3000:127.0.0.1:3000 root@\u003Cvps-ip>`, keep the session open, then open `http:\u002F\u002Flocalhost:3000`. The port may have been reassigned during installation: use the one shown in your client area, 3000 being only the catalogue default.",{"title":53,"body":54},"Log in for the first time","Do it right away: the first account created on the sign-up screen becomes the administrator, and the following ones stay pending your approval. Then connect your models in the admin panel, under Connections: an API key from OpenAI or a compatible service, or the address of an Ollama instance reachable from the container.",{"title":56,"body":57},"Publish over HTTPS on a domain","When Open WebUI is installed from your client area with a chosen address — your own domain or a free ServOrbit subdomain — the platform sets up the nginx vhost and the Let's Encrypt certificate. An installation made when the VPS was created, or without an address, is published from the VPS page: the “Attach a domain” button in the app's block (a domain from your account, the free subdomain, or a name you point to the server).",{"title":59,"body":60},"Appendix: redo everything by hand","To reinstall without the platform: install Docker, then run `docker run -d --name open-webui --restart unless-stopped -p 127.0.0.1:3000:8080 -v open-webui:\u002Fapp\u002Fbackend\u002Fdata --add-host=host.docker.internal:host-gateway ghcr.io\u002Fopen-webui\u002Fopen-webui:main`. Put a reverse proxy in front (nginx, for example) with a Let's Encrypt certificate (`certbot --nginx -d \u003Cdomain>`).",[62,65,68,71,74],{"q":63,"a":64},"What is Open WebUI?","Open WebUI is a self-hosted web interface for interacting with LLMs (Large Language Models) such as Llama, Mistral or GPT-4. It works like ChatGPT but runs on your own server.",{"q":66,"a":67},"What is the minimum RAM for Open WebUI?","Open WebUI alone needs 2 GB of RAM: that is the figure to keep if you connect it to a remote API, OpenAI or compatible. Ollama is not installed with Open WebUI. If you add it on the same VPS to run a local model, add the two needs together: 2 GB for Open WebUI and at least 8 GB for Ollama with a model of 7 to 8 billion parameters.",{"q":69,"a":70},"Is Open WebUI free?","Yes. Open WebUI's source code is available under a house BSD-3-style licence, with a clause forbidding the removal or replacement of the \"Open WebUI\" branding. You only pay for the VPS resources. If you use the OpenAI API, the API calls are billed by OpenAI — not by Open WebUI.",{"q":72,"a":73},"How does it differ from ChatGPT?","ChatGPT is hosted by OpenAI and all your data is sent to it. Open WebUI is self-hosted on your server: zero data transfer, full privacy, local models possible.",{"q":75,"a":76},"Can several models be used at once?","Yes. Open WebUI supports multiple connections (Ollama + OpenAI + Anthropic in parallel). You select the model for each conversation.",{"ram":78,"cpu":79,"stack":80,"port":84},"2 GB","2 vCPU",[81,82,83],"Docker","Python","Ollama (optional)","3000",{"ramMB":86,"vcpu":87,"diskMB":88},2048,2,0,[90],"ubuntu-24.04",[92,100,106],{"name":93,"slug":94,"categorySlug":13,"categoryName":95,"categoryColor":96,"logo":97,"tagline":98,"description":99},"Dify","dify","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":101,"slug":102,"categorySlug":13,"categoryName":95,"categoryColor":96,"logo":103,"tagline":104,"description":105},"OpenClaw","openclaw","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fopenclaw.svg","Your personal AI assistant, self-hosted and reachable on your messaging apps — WhatsApp, Telegram, Discord and 50+ channels.","Your open-source personal AI assistant, reachable from WhatsApp, Telegram, Discord and 50+ messaging apps. Self-hosted on your VPS — your conversations stay with you.",{"name":107,"slug":107,"categorySlug":108,"categoryName":109,"categoryColor":110,"logo":111,"tagline":112,"description":113},"n8n","automation-workflows","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.",[115,116],"heberger-open-webui","heberger-application-ia",{"key":12,"slug":13,"name":95,"objective":118,"icon":119,"color":96},"Build, host and run AI solutions.","ai",true,1794270879995]