fizzlepoof/truenas-stacks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Rebalance homelab AI routing around NOMAD-first inference

Browse Source
This commit is contained in:
Fizzlepoof
2026-06-13 23:54:56 +00:00
parent e19d4a5be3
commit 43b94813ca
7 changed files with 40 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/architecture/ARCHITECTURE_OVERVIEW.md
View File

@@ -40,7 +40,8 @@ Current live homelab stack plus the planned direction for the upgraded PD platfo
- **Dockhand** (3230) — Docker management UI
### AI Layer
- **LiteLLM** (4000) — unified LLM proxy; routes to Ollama on PD (light) and Rocinante (heavy)
- **LiteLLM** (4000) — unified LLM proxy; PD remains the shared light tier, while Rocinante is an opportunistic heavy tier when the PC is online
- **Honcho** — memory/deriver stack on N.O.M.A.D. using local Ollama first so PD outages do not cascade into MeshMonitor/database incidents
- **OpenWebUI** (8282) — chat UI with RAG, STT, and web search
- **Qdrant** (6333/6334) — vector database for RAG
- **Whisper** (8786 / 8787) — CPU speech-to-text on N.O.M.A.D. plus CUDA speech-to-text on Rocinante