[{"data":1,"prerenderedAt":113},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-en-langflow":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"slugs":8,"categorySlugs":9,"name":13,"description":14,"phase":15,"unavailableReason":16,"docsUrl":17,"logo":16,"github":16,"tagline":18,"longDescription":19,"features":20,"useCases":27,"steps":37,"faq":53,"specs":69,"compatibleOs":75,"relatedApps":76,"relatedPosts":106,"category":110},"langflow",{"fr":7,"en":7,"ar":7},{"fr":10,"en":11,"ar":12},"ia","artificial-intelligence","الذكاء-الاصطناعي","LangFlow","Build AI agent and RAG pipelines with drag-and-drop. Open-source visual LLM workflow editor — Python-native, 100+ components, one-click REST API.",1,null,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fhow-to-host-langflow-on-a-vps","Visual LLM workflow builder — drag-and-drop AI agents and RAG pipelines, deploy as a REST API in one click.","LangFlow (153 000+ GitHub stars, MIT, v1.11.x) is the leading open-source visual editor for building LLM applications and AI agent workflows. You drag components onto a canvas — LLM providers (OpenAI, Anthropic, Ollama, Mistral, Groq), vector databases (Qdrant, Chroma), document loaders, text splitters, memory modules, custom Python code — and wire them together into a working pipeline without writing a framework from scratch.\n\nSelf-hosted on a ServOrbit VPS, LangFlow gives your team a private workspace for prototyping and deploying AI pipelines. Each flow is automatically exposed as a REST API endpoint, ready to call from any application. Authentication is built in: a generated admin password locks your instance from the first boot. Data persists in an SQLite database on a named Docker volume — no PostgreSQL required to get started.\n\nLangFlow complements the ServOrbit AI catalogue: pair it with Ollama for a fully local LLM backend, use Qdrant as the vector store for your RAG pipelines, or feed outputs through Langfuse for observability. MIT licence — no seat limits, no cloud dependency, no telemetry.",[21,22,23,24,25,26],"Drag-and-drop canvas to wire LLMs, vector databases, document loaders and custom Python components into a working AI pipeline — no framework boilerplate.","100+ built-in components covering major LLM providers (OpenAI, Anthropic, Ollama, Mistral, Groq, Azure), vector databases (Qdrant, Chroma, Pinecone) and tool integrations.","One-click REST API — every flow is instantly exposed as a documented HTTP endpoint, callable from any language or application.","Python-native: write custom components in pure Python, import any PyPI package, and unit-test your logic independently of the canvas.","Built-in auth: admin account is created with a generated password on first boot — no anonymous access possible with LANGFLOW_AUTO_LOGIN=false.","MIT licence — no seat limits, no telemetry, no vendor lock-in. All flow data stays on your VPS.",[28,31,34],{"title":29,"body":30},"Prototype AI pipelines before writing code","Wire an LLM provider, a document loader and a vector database together on the canvas in minutes, validate the output, then call the auto-generated API directly from your application.",{"title":32,"body":33},"Build RAG chatbots on private documents","Load internal PDFs or markdown files, split them into chunks, embed them in Qdrant, and chain a retrieval step with an Ollama or OpenAI call — all without writing a RAG framework.",{"title":35,"body":36},"Share and version team AI workflows","Export each flow as a JSON file, store it in Git, and import it on another LangFlow instance. Your pipelines are reproducible, reviewable and deployable anywhere.",[38,41,44,47,50],{"title":39,"body":40},"Open LangFlow","After installing from the Marketplace, open the URL in your ServOrbit client area. Without a domain, open an SSH tunnel — `ssh -L 7860:127.0.0.1:7860 root@your-vps-ip` — then browse to `http:\u002F\u002Flocalhost:7860`.",{"title":42,"body":43},"Log in for the first time","Enter `admin` as the username and the generated password shown under ADMIN_PASSWORD in your ServOrbit client area. This account has full access to all flows and settings.",{"title":45,"body":46},"Create your first flow","Click **New Flow** → **Blank Flow**. Drag a **Chat Input** component and an **OpenAI** (or **Ollama**) LLM component onto the canvas. Connect them and click **Run** to send a test message.",{"title":48,"body":49},"Call the flow as a REST API","Click the **API** button (top-right). LangFlow shows the flow's unique endpoint URL and a ready-to-copy `curl` command. Call it from Node.js, Python or any HTTP client — no extra setup.",{"title":51,"body":52},"Export and version your flows","Go to **Settings → Export** to download the flow as a JSON file. Commit it to your Git repository and restore it on any LangFlow instance by importing the JSON file.",[54,57,60,63,66],{"q":55,"a":56},"How do I log in to LangFlow for the first time?","Enter `admin` as the username and the generated password (ADMIN_PASSWORD in your ServOrbit client area). Authentication is enforced from the first boot — the instance is never open without credentials.",{"q":58,"a":59},"Does LangFlow require a domain name?","No. Access it via an SSH tunnel (`ssh -L 7860:127.0.0.1:7860 root@your-ip`, then `http:\u002F\u002Flocalhost:7860`). Attaching a domain enables direct HTTPS access — ServOrbit configures nginx and TLS automatically.",{"q":61,"a":62},"Can LangFlow connect to Ollama or a local LLM?","Yes. Use the Ollama component on the canvas and set its base URL. If Ollama is installed on the same VPS via the Marketplace, reach it at `http:\u002F\u002Fhost.docker.internal:11434` from inside the LangFlow container.",{"q":64,"a":65},"What is the difference between LangFlow and Flowise?","Both are visual LLM workflow builders. LangFlow is Python-native and targets developers who want to write custom components or export clean Python code from their flows. Flowise is more no-code oriented, with a simpler canvas. The two share the LangChain lineage but have diverged in developer profile and ecosystem.",{"q":67,"a":68},"How do I back up my LangFlow flows?","Export each flow individually from the canvas menu (JSON export). For a full backup, copy the SQLite database: `docker cp langflow-langflow-1:\u002Fapp\u002Fdata\u002Flangflow.db .\u002Flangflow-backup.db`. Restore by copying it back and restarting the container.",{"version":70,"license":71,"ram":72,"cpu":73,"disk":74},"1.11.3","MIT","2 GB minimum, 4 GB recommended","2 vCPU minimum","10 GB",[],[77,86,94,100],{"name":78,"slug":79,"categorySlug":80,"categoryName":81,"categoryColor":82,"logo":83,"tagline":84,"description":85},"Flowise","flowise","automation-workflows","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":87,"slug":88,"categorySlug":11,"categoryName":89,"categoryColor":90,"logo":91,"tagline":92,"description":93},"Ollama","ollama","Artificial Intelligence","text-purple-400 bg-purple-500\u002F10","https:\u002F\u002Fcdn.simpleicons.org\u002Follama","Run open-source LLMs on your VPS — OpenAI-compatible API, zero per-token cost.","Run open-source LLMs locally via a dead-simple API. Pull Llama 3, Mistral, Qwen or DeepSeek in one command — OpenAI-compatible, zero per-token cost.",{"name":95,"slug":96,"categorySlug":11,"categoryName":89,"categoryColor":90,"logo":97,"tagline":98,"description":99},"Qdrant","qdrant","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Fqdrant.svg","Self-hosted vector database for semantic search and RAG — the missing infrastructure layer for your LLM stack.","Self-hosted vector database for semantic search and RAG. Store, index and query high-dimensional embeddings with HNSW indexing — the missing infrastructure layer for your LLM stack.",{"name":101,"slug":102,"categorySlug":11,"categoryName":89,"categoryColor":90,"logo":103,"tagline":104,"description":105},"Langfuse","langfuse","https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Fselfhst\u002Ficons\u002Fsvg\u002Flangfuse.svg","Trace, evaluate and manage your LLM applications — self-hosted, production-ready.","Open-source LLM observability: trace every AI request, run evaluations, manage prompt versions and compare model costs — self-hosted, compatible with OpenAI, LiteLLM, LangChain and Ollama.",[107,108,109],"deployer-dify-vps","heberger-open-webui","heberger-flowise-vps",{"key":10,"slug":11,"name":89,"objective":111,"icon":112,"color":90},"Build, host and run AI solutions.","ai",1787661757676]