OpenWebUI

OpenWebUI is a self-hosted chat interface for LLMs. It connects to OpenAI-compatible endpoints, Ollama, llama.cpp, and vLLM, and adds RAG, plugins, tool calling, and multi-user support.

Host: Dankclaw — Hostname: chat.dankclaw.local — Port: 3000 — Docs: https://github.com/open-webui/open-webui

Facts (from research, primary source)

Item	Value
Image	`ghcr.io/open-webui/open-webui:main` (CPU build for non-NVIDIA hosts)
Port	3000 (host) → 8080 (container)
Data volume	config, sessions, RAG indexes
Backend	OpenAI-compatible endpoint at `http://192.168.0.235:7770/v1` — llama.cpp FastMTP on Dankserver (`frank-default-large`, Qwen3.8-27B IQ4_XS, 128K ctx)

Note: the :cuda image tag was previously used on Dankserver. Dankclaw is AMD; use the default (CPU) image, NOT the cuda tag.

Connecting to llama.cpp

OpenWebUI talks to the llama.cpp server on Dankserver through its OpenAI-compatible API. Configure a new connection in the UI or set the base URL:

environment:
  OPENAI_API_BASE_URL: "http://192.168.0.235:7770/v1"
  OPENAI_API_KEY: "none"

The endpoint moved from Dankclaw to Dankserver in the 2026-08-17 redo; use the LAN address, not host.containers.internal (which only reaches the podman host).

The :7770 endpoint is the frank-default-large service on Dankserver, managed by the sibling vllmScripts repository (not this repo). Model swaps, context sizing, and spec tuning happen there. See the vllmScripts knowledge base.

Alternative backend: frank-default-small on port 52625 (vLLM on Dankclaw, nameistoken Qwen3.6-35B-A3B Quark W8A8 INT8, 262K ctx, tool calling). Same OpenAI-compatible API shape. Point OPENAI_API_BASE_URL at http://192.168.0.143:52625/v1.

Volumes

Container path	Host path (convention)
`/app/backend/data`	`/opt/openwebui/data`

Healthcheck

OpenWebUI responds on /health with 200.

Gotchas

Use the non-CUDA image on AMD hosts.
The default admin account is created on first login; secure it immediately.
If the backend (llama.cpp) is slow to load, OpenWebUI may show connection errors until the model is ready — that matches the known 3–8 minute model load time.

2.5 KiB Raw Blame History Unescape Escape