project-nomad/admin/app/validators
jakeaturner 27be71b46e feat(AI): give chat a sampler instead of the backend's defaults
Chat sent num_ctx, num_predict and nothing else, so every turn decoded at
whatever the backend picked: temperature 0.8, top_p 0.9, no min_p. On a
heavily quantized 1-3B model that is the wandering, repetitive output people
read as "the local model is bad".

Adds `ai.responseStyle` with four profiles. min_p is the lever, not
temperature: it floors relative to the top token, so it truncates hard on a
confident distribution and barely at all on a flat one, which is where small
models start to wander. top_p stays at 1.0 rather than stacked on top of it.
repeat_penalty moves with the style, because a grounded answer legitimately
repeats a part number inside the 64-token window: `focused` relaxes it to
1.05, `creative` tightens it to 1.15.

`auto` is the only style that defers to the model. Plenty of library models
ship author-tuned samplers (qwen3 sets 0.6/0.95/20), so those win key by key
and NOMAD fills only the gap, which in practice is min_p. A style the user
picked by name overrides them, or it would silently do nothing on half
their models.

The compat transport drops min_p, so a profile carries a separate compatTopP.
Passing top_p 1.0 to a backend with no min_p behind it would sample the raw
distribution, which is worse than the 0.9 it replaced.

Resolved in the controller, so the grammar-constrained task calls keep their
temperature 0. An explicit temperature still outranks a profile's, which is
what keeps the eval harness deterministic.

`eval:generation --style` is new and load-bearing: temperature 0 makes min_p,
top_p and top_k inert, so a default run cannot see this change at all.
`--style=off` sends no samplers and no temperature, and is the control.

Verified against Ollama 0.32.9, min_p accepted. 22 unit tests.
2026-09-29 15:54:41 -07:00
..
responses feat: auto-generating OpenAPI docs with Scalar UI (#1128) 2026-08-04 03:38:33 +00:00
benchmark.ts feat: Add system benchmark feature with NOMAD Score 2026-01-22 21:48:12 -08:00
chat.ts feat: [wip] native AI chat interface 2026-01-31 20:39:49 -08:00
common.ts fix(security): harden assertNotPrivateUrl with ipaddr.js + host normalization 2026-06-23 04:46:55 +00:00
conditions.ts Add offline FDA drug reference (labels, interaction view, conditions, remedies) (#1040) 2026-08-04 03:38:33 +00:00
curated_collections.ts feat: support gated downloads for self-hosted curated content (#1172) 2026-08-04 03:39:55 +00:00
download.ts feat(Open WebUI): manage models via Command Center 2026-01-19 22:15:52 -08:00
drug_reference.ts Add offline FDA drug reference (labels, interaction view, conditions, remedies) (#1040) 2026-08-04 03:38:33 +00:00
nomad_md.ts feat(AI): nomad.md for custom instructions (#1127) 2026-08-04 03:38:33 +00:00
ollama.ts feat(AI): per-model thinking toggle with global default (off) (#1079) 2026-08-04 03:38:29 +00:00
rag.ts feat(KnowledgeBase): add document viewer, download, metadata, and sorting (#721) 2026-06-23 04:47:09 +00:00
settings.ts feat(AI): give chat a sampler instead of the backend's defaults 2026-09-29 15:54:41 -07:00
system.ts feat(dashboard): let a link tile carry a brand colour 2026-09-29 15:54:41 -07:00
zim.ts feat(zim): let users browse the Kiwix library in any language 2026-09-29 15:54:41 -07:00