{"id":4146,"library":"open-webui","title":"Open WebUI","description":"Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various Large Language Model (LLM) runners, including Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG. It provides a ChatGPT-style interface for interacting with local or cloud-based models. The project is actively developed with continuous updates.","status":"active","version":"0.8.12","language":"python","source_language":"en","source_url":"https://github.com/open-webui/open-webui","tags":["AI","LLM","UI","Chatbot","Self-hosted","Ollama","OpenAI API","RAG","Frontend"],"install":[{"cmd":"pip install open-webui","lang":"bash","label":"Install via pip"}],"dependencies":[{"reason":"Requires Python 3.11 or newer (up to <3.13.0a1) for compatibility.","package":"Python","optional":false}],"imports":[],"quickstart":{"code":"pip install open-webui\nopen-webui serve","lang":"bash","description":"Install Open WebUI via pip and then start the web server. The UI will typically be accessible at http://localhost:8080 (or http://localhost:3000 if using Docker without --network=host)."},"warnings":[{"fix":"Use a specific version tag (e.g., `ghcr.io/open-webui/open-webui:v0.8.12`) instead of `:main` in Docker commands.","message":"When using Docker, the `:main` tag always points to the latest build and can include breaking changes without warning. For production or stability, it is recommended to pin a specific version tag (e.g., `:v0.8.6`).","severity":"breaking","affected_versions":"All versions using `:main` Docker tag"},{"fix":"Set a persistent `WEBUI_SECRET_KEY` environment variable in your deployment environment.","message":"A persistent `WEBUI_SECRET_KEY` environment variable is crucial. Without it, Open WebUI generates a random key on each restart, leading to user logouts and 'Error decrypting tokens' for essential secrets like OAuth tokens or API keys.","severity":"gotcha","affected_versions":"All versions"},{"fix":"Use `python=3.11` when creating virtual environments (e.g., `conda create -n open-webui python=3.11`) or ensure your system default is 3.11.","message":"Ensure you are using Python 3.11 for installation to avoid compatibility issues. The library requires Python <3.13.0a1,>=3.11.","severity":"gotcha","affected_versions":"<0.8.12"},{"fix":"Add `--network=host` and `-e OLLAMA_BASE_URL=http://127.0.0.1:11434` to your `docker run` command.","message":"For Docker deployments with Ollama, connection issues often arise if the WebUI container cannot reach the Ollama server. Using `--network=host` and setting `OLLAMA_BASE_URL` (e.g., `http://127.0.0.1:11434`) in your Docker run command can resolve this.","severity":"gotcha","affected_versions":"All versions"},{"fix":"Ensure `ENABLE_REALTIME_CHAT_SAVE` is set to `False` (or not set, as `False` is the default) in production environments.","message":"Enabling `ENABLE_REALTIME_CHAT_SAVE` in production is strongly discouraged. It causes massive database write pressure and severe performance degradation under concurrent load.","severity":"gotcha","affected_versions":"All versions"},{"fix":"Clear your browser cache (Ctrl+F5 or Cmd+Shift+R) after updating.","message":"After updating Open WebUI, it's a common issue that the UI might appear broken due to stale frontend assets.","severity":"gotcha","affected_versions":"All versions"},{"fix":"Review and restrict user permissions for 'Workspace → Tools' to trusted administrators.","message":"Workspace Tools and Functions execute arbitrary Python code on your server. Restrict Workspace access to trusted administrators only, as granting tool creation/import access is equivalent to giving shell access.","severity":"gotcha","affected_versions":"All versions with Workspace Tools/Functions"}],"env_vars":null,"search_vec":"'activ':67 'ai':18,72 'api':39,81 'base':62 'built':42 'built-in':41 'chatbot':75 'chatgpt':52 'chatgpt-styl':51 'cloud':61 'cloud-bas':60 'compat':38 'continu':70 'design':20 'develop':68 'engin':45 'entir':23 'extens':7 'featur':9 'feature-rich':8 'friend':14 'frontend':83 'host':17,78 'includ':33 'infer':44 'interact':56 'interfac':54 'languag':29 'larg':28 'llm':31,73 'local':58 'model':30,63 'offlin':24 'ollama':34,79 'open':1,3 'openai':37,80 'openai-compat':36 'oper':22 'platform':19 'project':65 'provid':49 'rag':47,82 'rich':10 'runner':32 'self':16,77 'self-host':15,76 'style':53 'support':26 'ui':74 'updat':71 'user':13 'user-friend':12 'various':27 'webui':2,4","created_at":"2026-04-12T03:42:55.795159+00:00","updated_at":"2026-04-16T17:33:10.230621+00:00","problems":[{"fix":"Ensure Ollama is configured to listen on all network interfaces by setting `OLLAMA_HOST=0.0.0.0` in its environment variables and restarting it. When running Open WebUI in Docker, use the `--network=host` flag to allow the container to access the host's network, or configure `OLLAMA_BASE_URL` to `http://host.docker.internal:11434` and ensure `host.docker.internal` is resolvable within the Docker container (e.g., by adding `--add-host=host.docker.internal:host-gateway` to the `docker run` command).","cause":"This error commonly occurs when Open WebUI, especially when running in a Docker container, cannot reach the Ollama server. This is often due to Ollama only listening on `127.0.0.1` (localhost) on the host machine, which is not directly accessible from within the Docker container, or incorrect network configuration.","error":"Open WebUI: Server Connection Error / Connection refused / Cannot connect to host host.docker.internal:11434"},{"fix":"First, ensure Ollama is running and has models pulled (run `ollama list` in your terminal). Verify that the `OLLAMA_BASE_URL` environment variable for Open WebUI is correctly set to the address where Ollama is accessible (e.g., `http://127.0.0.1:11434` or `http://host.docker.internal:11434` if in Docker). If running in Docker, ensure proper network configuration as described in the 'Connection refused' fix. Also, check Open WebUI's Admin Settings > Connections to confirm the Ollama Server URL is correct, and for non-admin users, ensure model access control is configured appropriately or temporarily set `BYPASS_MODEL_ACCESS_CONTROL` environment variable.","cause":"This typically happens when Open WebUI cannot successfully communicate with the Ollama server to retrieve the list of available models, or when the `OLLAMA_BASE_URL` is incorrectly configured within Open WebUI's settings or environment variables. It can also be due to non-admin users lacking permissions to see models, or Ollama itself not having any models pulled.","error":"No models available / models not showing in the UI"},{"fix":"Reduce the size of the model being used, or free up system RAM. To determine the memory requirements of a model, you can run `ollama run <model_name>` in your terminal. If continuously encountering this, consider upgrading your system's RAM or using a machine with more memory. You can also adjust the `AIOHTTP_CLIENT_TIMEOUT` environment variable in Open WebUI to increase the timeout for slow responses, though this does not fix the underlying memory issue.","cause":"This error often indicates that the loaded model requires more RAM than is currently available on the system running Ollama. When a model attempts to load or process a request, and there isn't enough memory, Ollama can return an internal server error.","error":"500 Internal Server Error (Ollama: 500, message='Internal Server Error') when generating responses"}],"ecosystem":"pypi","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":null,"cli_name":"","cli_version":null,"type":"library","homepage":"https://openwebui.com","github":null,"docs":null,"changelog":null,"pypi":"https://pypi.org/project/open-webui/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["llm-agents","web-framework","ai-ml"],"base_url":null,"auth_type":null,"provenance":{"verified_status":null,"verified_at":null,"last_verified":"2026-04-11","next_check":"2026-07-10","install_tag":null}}