From 885cceccaeff4fca31fca3b29617775cd9361ff2 Mon Sep 17 00:00:00 2001 From: Gmer4Lfe Date: Sun, 2 Aug 2026 12:53:55 -0400 Subject: [PATCH] Restore the truncated intro of Notes_AI-Design.md A partial write at 11:41 left the status paragraphs cut off mid-line, and the previous commit swept it up. Content recovered from e02dc1b. --- Notes_AI-Design.md | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/Notes_AI-Design.md b/Notes_AI-Design.md index 9a4c701..e885238 100644 --- a/Notes_AI-Design.md +++ b/Notes_AI-Design.md @@ -1,6 +1,26 @@ # Varaverk AI Integration — Design Notes -**Status +**Status: retrieval is built; integration is not.** As of 2026-08-02 the `AI_*` and +`HOST*_OLLAMA_*` variables exist in both confs and both templates, and `AI/` holds a working +index and query path — see the RAG section at the end of this document and `AI/README-AI.md`. + +Everything else below remains design only. **No Varaverk script consults AI.** Every +`AI_ASSIST_*` toggle is false, `AI_CONF_WRITE_ENABLED` is false with an empty whitelist, and +host resolution across the mesh is specified but not implemented. Originally captured +2026-08-01 so the reasoning survives. + +Ollama itself *is* installed, tuned and verified on HOST1 — `qwen2.5-coder:14b` for +generation, `nomic-embed-text` for embeddings, 16k context, pinned to the RTX 3080. See +Hardware Budget for measured numbers. That is the substrate, not the integration. + +**Origin:** the RTX 3080 was freed when the Windows gaming VM was retired. It is bound to the +`nvidia` driver, not `vfio` — not reserved for passthrough, so there is no VM contention to +design around. Two goals at once: somewhere to learn local LLMs, and something Varaverk can +genuinely use. + +**Build order** — deliberately lowest-risk first. Each stage must be boring before the next +one starts: + 1. Chat assistant / settings helper / onboarding assistant — a wrong answer costs nothing 2. Watchdog and discovery context — a wrong answer costs a bad suggestion, still gated 3. Cleanup and sync decision aid — closest to destructive, last to be trusted