sam/obsidian-vault
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sam-4screen-desktop 2026-8-3:12:59:15

Browse Source
This commit is contained in:
Sam Rolfe
2026-08-03 12:59:15 +10:00
parent 70492824ae
commit 4c05bb9657
2 changed files with 15 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
300 areas/350 AI/Pi Agent Extensions & Skills.md
View File

@@ -58,10 +58,22 @@ Open WebUI v0.11.0 runs on .13 as a native NixOS process (not Docker), managed v
|--------|--------|
| **URL** | `http://192.168.20.13:3000` |
| **Package** | `open-webui-0.11.0` (NixOS nixpkgs) |
| **How to connect OmniRoute** | Admin Panel ⚙️ → Settings → Connections → OpenAI API → URL: `http://192.168.20.13:20129/v1`, Key: OmniRoute API key |
| **How to connect OmniRoute** | Admin Panel ⚙️ → Settings → Connections → OpenAI API → URL: `http://192.168.20.13:20129/v1` (include `/v1`), Key: OmniRoute API key |
| **Also works with** | Any OpenAI-compatible API (TokenRouter, OpenRouter, DeepSeek) — add each as a separate connection |
| **Port note** | :3000 is taken by Open WebUI. Langfuse was bumped to :3001. |
---
## Ollama — Local LLM Inference
Runs on .13 with `qwen2.5-coder:7b` (Q4_K_M, 7.6B params). Sparse use — 15.5GB RAM on .13 limits local model viability. Open WebUI can connect to Ollama as a connection type directly.
| Aspect | Detail |
|--------|--------|
| **URL** | `http://192.168.20.13:11434` |
| **WebUI** | `http://192.168.20.13:3000` → Settings → Connections → Ollama → `http://127.0.0.1:11434` (localhost from .13's perspective) |
| **Model** | `qwen2.5-coder:7b` (last pulled Feb 2026) |
### Pi default model selection model
Machines route through `omni` provider with `defaultModel: "default-opencode-go-ds-flash"`: