Files

T

Frank e3eb5334cb feat: initialize serverAppConfigs with podman stacks for Dankserver and Dankclaw

- Dankserver stack: RomM, Copyparty, Calibre-Web, node-exporter
- Dankclaw stack: Gluetun VPN (SearXNG tunnel), SearXNG+Valkey, ComfyUI
  (CPU backend), OpenWebUI, Hermes, Gitea+Postgres (migrated), Caddy
  reverse proxy, Grafana+Prometheus+Loki+Alloy observability
- Caddyfiles with .local hostname convention and basicauth homepage
- bind-mount storage policy, no named volumes
- deploy.sh mirroring vllmScripts git workflow (push -> pull -> restart -> health)
- docs/ Obsidian vault: per-service docs from frank-default-small research
  subagents (promtail EOL -> Alloy; gitea SECRET_KEY preservation; ComfyUI --cpu)
- bats test suite at 6 seams — 22 tests green

2026-08-13 20:19:41 -07:00

1.8 KiB

Raw Blame History

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://localhost:7770/v1` (llama.cpp)

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 local llama.cpp server through its OpenAI-compatible API. Configure a new connection in the UI or set the base URL:

environment:
  OPENAI_API_BASE_URL: "http://host.containers.internal:7770/v1"
  OPENAI_API_KEY: "none"

The hostname host.containers.internal reaches the podman host where llama.cpp listens on 7770.

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.

1.8 KiB Raw Blame History Unescape Escape