[{"data":1,"prerenderedAt":108},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-dify":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":49,"specs":65,"compatibleOs":75,"relatedApps":77,"relatedPosts":102,"category":105},"dify","Dify","Build LLM applications visually: chatbots, RAG agents, pipelines — without writing any backend code.",1,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fdeployer-dify-vps","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fdify.svg","https:\u002F\u002Fgithub.com\u002Flanggenius\u002Fdify","Build LLM applications with drag-and-drop — chatbots, agents, RAG pipelines — no backend required.","Dify is an open-source LLM application development platform that lets you build chatbots, autonomous agents and RAG pipelines without writing any backend code. Its visual interface lets you connect data sources, define conversational flows and deploy APIs in just a few minutes.\n\nSelf-hosted on a VPS, Dify gives you full control over your data, your prompts and your models. You can connect any LLM (OpenAI, Anthropic, Mistral, local Ollama models) and build professional AI applications without depending on third-party cloud infrastructure.",[17,18,19,20,21,22],"Visual studio to build LLM workflows without code","Native RAG: connect vector databases, PDFs, websites","Multi-model support: OpenAI, Claude, Gemini, Mistral, Ollama","One-click REST API deployment","LLM call monitoring and cost management","User and workspace management",[24,27,30],{"title":25,"body":26},"Business chatbot","Build an intelligent assistant connected to your internal data — documentation, FAQs, CRM — without a single line of backend code.",{"title":28,"body":29},"Document processing pipeline","Automate the analysis, classification and summarization of documents by building a visual workflow.",{"title":31,"body":32},"Rapid AI prototype","Test your LLM application idea in a few hours before investing in custom development.",[34,37,40,43,46],{"title":35,"body":36},"Prepare the VPS","VPS with at least 4 GB RAM, Ubuntu 22.04. Install Docker and Docker Compose.",{"title":38,"body":39},"Clone and configure","Clone the Dify repository. Copy `.env.example` to `.env` and configure your secret key and your database connections.",{"title":41,"body":42},"Start the services","Run `docker compose up -d` from the `docker\u002F` folder. Dify starts up with PostgreSQL, Redis and Weaviate (vector database).",{"title":44,"body":45},"Expose over HTTPS","Configure Nginx as a reverse proxy to Dify's port 80. Obtain an SSL certificate with Certbot.",{"title":47,"body":48},"Connect your LLMs","In the settings, add your API keys (OpenAI, Anthropic…) or the URL of your Ollama instance. Create your first application from the studio.",[50,53,56,59,62],{"q":51,"a":52},"What is Dify?","Dify is an open-source platform that lets you build LLM applications (chatbots, agents, RAG pipelines) through a visual interface, without coding a backend.",{"q":54,"a":55},"What VPS configuration does Dify need?","Dify requires at least 4 GB of RAM and 2 vCPU. It starts PostgreSQL, Redis and a vector database — plan for 8 GB of RAM for comfortable production use.",{"q":57,"a":58},"Dify vs n8n: what's the difference?","Dify specializes in LLM applications (RAG, AI agents). n8n is a general-purpose automation tool that can also integrate LLMs. They are complementary.",{"q":60,"a":61},"Can Dify be used with local models?","Yes. Dify supports Ollama — you can connect local models (Llama, Mistral, Gemma) running on the same VPS or on a separate server.",{"q":63,"a":64},"Is Dify open source?","Yes. Dify Community Edition is open source (Apache 2.0). There is a Cloud version hosted by Dify.ai, but self-hosting on a VPS is free.",{"ram":66,"cpu":67,"stack":68,"port":74},"4 GB (8 GB recommended)","2 vCPU",[69,70,71,72,73],"Docker","Python","PostgreSQL","Redis","Weaviate","80",[76],"ubuntu-24.04",[78,87,96],{"name":79,"slug":80,"categorySlug":81,"categoryName":82,"categoryColor":83,"logo":84,"tagline":85,"description":86},"Open WebUI","open-webui","ia","Artificial Intelligence","text-purple-400 bg-purple-500\u002F10","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.",{"name":88,"slug":89,"categorySlug":90,"categoryName":91,"categoryColor":92,"logo":93,"tagline":94,"description":95},"Flowise","flowise","automatisation","Automation & Workflows","text-brand-action bg-brand-action\u002F10","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fflowise.svg","Build LLM pipelines and AI chatbots with drag-and-drop — visual LangChain.","Build LLM automation pipelines with drag-and-drop. Visual LangChain chains, connected to your existing tools.",{"name":97,"slug":98,"categorySlug":81,"categoryName":82,"categoryColor":83,"logo":99,"tagline":100,"description":101},"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.",[103,104],"deployer-dify-vps","heberger-application-ia",{"key":81,"slug":81,"name":82,"objective":106,"icon":107,"color":83},"Build, host and run AI solutions.","ai",1785628472785]