Files

T

Claude 12ed4426e0 Refine capacity numbers from LXC 104 summary; flag iGPU passthrough fix

- LXC 104 (docker) confirmed: 16 CPU, 31.25 GiB RAM (7.86 used / 25%),
  200 GiB boot disk at 47.7% — disk is the real near-term constraint,
  not RAM. Numbers propagated into Q11 (docs/11), docs/03 architecture
  table, and CLAUDE.md infra block.
- New optimization #26 in docs/12: fix the Intel Arc iGPU passthrough
  flagged as broken in the LXC notes. Concrete /etc/pve/lxc/104.conf
  snippet provided. Once working, TEI / infinity / Immich CLIP can run
  GPU-accelerated for ~5–10x throughput.
- New optimization #27: disk-pressure mitigation playbook (move Qdrant
  to unas if it grows, prune docker layers monthly, cap n8n executions).
- New optimization #28: shrink the LXC's 8 GiB swap to 2 GiB.

2026-05-04 22:10:51 +00:00

4.1 KiB

Raw Blame History

03 — Architecture Overview

A one-page mental model. For details follow the cross-links.

Topology

                         ┌────────────────┐
   voice / typing ──────▶│     Memos      │◀──── Nexa replies as comments
                         │  (interface)   │
                         └───────┬────────┘
                                 │ webhook (- [ ] / #nexa:*)
                                 ▼
                         ┌────────────────┐
   IMAP / RSS / NC  ────▶│      n8n       │◀──── workflows live in
   Karakeep / Bluesky    │  (logic)       │      ./nexa-core/n8n-workflows
                         └───┬────────┬───┘
                  classify ▲ │        │ ▲ retrieve
                           │ ▼        ▼ │
                       ┌──────────┐  ┌──────────┐
                       │  SAIA    │  │  Qdrant  │
                       │ LiteLLM  │  │  vector  │
                       └──────────┘  └────┬─────┘
                                          │
                                          ▼
                                     ┌──────────┐
                                     │ GraphDB  │  Ontotext, SPARQL
                                     │  (RDF)   │  Phase 3.4
                                     └──────────┘
                                 │
                                 ▼ writes
                  ┌──────────────────────────────┐
                  │  Nextcloud (Tasks, Calendar, │
                  │  Mail, Files / Obsidian)     │
                  └──────────────────────────────┘

Components

Component	Role	Where it runs (today)
Memos	Interface, voice input, webhook source	docker host LXC 104 (unprivileged, 16 CPU / 31 GiB / 200 GiB) → `memos.nuclide.systems`
n8n	Workflow / logic engine	docker host LXC 104 → `n8n.nuclide.systems`
SAIA / LiteLLM	Model gateway, embeddings, classification	docker host LXC 104 → `ai.nuclide.systems` (LiteLLM internal :4000)
Qdrant	Vector memory (semantic recall)	docker host LXC 104 — reuse `qdrant_scientific`. Collections: `nexa_knowledge_text` (Phase 3.1, 1024-dim) and `nexa_knowledge_visual` (Phase 3.2, 768-dim)
Ontotext GraphDB	Structural memory via SPARQL (Phase 3.4)	not yet deployed; see 09-deployment
TEI (HF text-embeddings-inference)	Self-hosted text embeddings, `BAAI/bge-m3`, Phase 3.1	docker host LXC 104, CPU only — swapped for `infinity` in Phase 3.2 to add `jina-clip-v2`
Nextcloud	Tasks, calendar, mail, files	dedicated LXC 105 → `nc.nuclide.systems`
ntfy	Push channel for system alerts	docker host → `ntfy.nuclide.systems`
Backrest	Backup orchestration	LXC 103
Zoraxy	Reverse proxy + TLS	LXC 108 (`192.168.1.4:8000`)
AdGuard DNS	Internal name resolution	LXC 102
Home Assistant	Voice + house automation	VM 100 (HAOS)

Two-pillar memory

Qdrant answers "what is similar / relevant?" (cosine search over embeddings).
Ontotext GraphDB answers "who, what depends on what, how is it structured?" (SPARQL over RDF).

Both pillars are queried in parallel for #nexa:ask and merged before SAIA generates the final answer. See 08 — GraphRAG architecture.

Dual-context routing

Every input is classified work or personal before any side effect (task creation, calendar write). See 04 — Integration matrix and 06 — Classification logic.

4.1 KiB Raw Blame History