{"slug": "open-webui-your-local-chatgpt", "title": "Open WebUI: Your Local ChatGPT", "summary": "Open WebUI is a self-hosted web interface for Ollama that transforms local large language models into a ChatGPT-like experience, running entirely on the user's machine with no data leaving it. It supports features such as model switching during conversations, file uploads for document analysis, voice input, web search integration, and local image generation. The tool can be installed via Docker or pip, offers multi-user support, and ensures data privacy by connecting to a local Ollama instance.", "body_md": "Transform your local LLM into a beautiful, full-featured web interface — like ChatGPT, but running entirely on your machine.\nOpen WebUI is a self-hosted web interface for Ollama. It gives you:\nBest of all: It connects to your local Ollama instance — no data ever leaves your machine.\nqwen2.5:7b\n)Docker is the easiest way. One command and you're done:\ndocker run -d \\\n-p 3000:8080 \\\n-v open-webui:/app/backend/data \\\n-e OLLAMA_BASE_URL=http://host.docker.internal:11434 \\\n--name open-webui \\\n--restart always \\\nghcr.io/open-webui/open-webui:main\nWhat this does:\n-p 3000:8080\n— makes it available at http://localhost:3000\n-v open-webui:/app/backend/data\n— keeps your chats saved even if you restart-e OLLAMA_BASE_URL\n— tells it where your Ollama is running--restart always\n— auto-starts when your computer boots# Check logs — you should see \"Application startup complete\"\ndocker logs open-webui --tail 20\nThen open http://localhost:3000 in your browser.\nFirst time? Create an account. Don't worry — it's local only. Your data stays on your machine.\nIf you don't have Docker:\n# Install\npip install open-webui\n# Run\nopen-webui serve\nThen open http://localhost:8080.\nAfter logging in, Open WebUI looks and feels like ChatGPT:\nKey areas:\nIn the top dropdown, you can switch models during a conversation. Each model sees the same chat history.\nqwen2.5:7b\nfor general chatdeepseek-r1:14b\nwhen you need hard reasoningcodellama\nfor code tasksClick the paperclip icon and upload a PDF, Word doc, or text file. The model can then answer questions about it.\nUse cases:\nClick the microphone icon to speak instead of type. This works in Chrome and Edge.\nIn Settings → Model, you can adjust:\nOpen WebUI can integrate with local image generators:\n# Add Automatic1111 (Stable Diffusion)\ndocker run -d \\\n-p 7860:7860 \\\n-v sd-models:/models \\\n--gpus all \\\nasd/stable-diffusion-webui:latest\nThen configure in Open WebUI Settings → Image Generation.\nEnable web search in Settings → Web Search. Open WebUI will search the internet when answering questions.\nFor secure remote access (behind a VPN or tunnel):\n# Using Caddy as a reverse proxy\ndocker run -d \\\n-p 443:443 \\\n-v open-webui:/app/backend/data \\\n-e OLLAMA_BASE_URL=http://ollama:11434 \\\n-e WEBUI_SECRET_KEY=your-secret-here \\\n--name open-webui \\\nghcr.io/open-webui/open-webui:main\nOpen WebUI supports multiple users out of the box. Each user:\nTo add users: Go to Settings → Admin Panel → Users → Create User.\nNext step: Now that you have a GUI, try setting up Local RAG — let your LLM answer questions about your own documents.\nPart of the Local LLM Guide — the definitive resource for running AI on your own hardware.", "url": "https://wpnews.pro/news/open-webui-your-local-chatgpt", "canonical_source": "https://dev.to/lingdas1/open-webui-your-local-chatgpt-29d8", "published_at": "2026-05-23 18:55:33+00:00", "updated_at": "2026-05-23 19:01:40.165738+00:00", "lang": "en", "topics": ["large-language-models", "open-source", "developer-tools"], "entities": ["Open WebUI", "Ollama", "ChatGPT", "Docker", "qwen2.5", "deepseek-r1", "codellama"], "alternates": {"html": "https://wpnews.pro/news/open-webui-your-local-chatgpt", "markdown": "https://wpnews.pro/news/open-webui-your-local-chatgpt.md", "text": "https://wpnews.pro/news/open-webui-your-local-chatgpt.txt", "jsonld": "https://wpnews.pro/news/open-webui-your-local-chatgpt.jsonld"}}