project-nomad/admin
Chris Sherwood b0be0dec43 fix(ai): don't probe the native embed endpoint on a non-Ollama backend
_embedWithFallback() always tried Ollama's native /api/embed first and only
reached /v1/embeddings from the catch block. Against a backend that only
speaks the OpenAI embeddings API, every batch therefore paid a
guaranteed-failing round trip plus a warn line before doing the real work.

Invisible on a handful of documents. Expensive on a bulk file-embeddings
job: the reporter is indexing several million chunks through an
OpenAI-compatible proxy, which doubles request volume and log noise against
their embedding host for the entire lifetime of the ingest.

Gates the native attempt on _isNativeBackend(), matching how _doDownloadModel
already skips /api/pull. Used the probe rather than reading isOllamaNative
directly: the field is null until something populates it, and an embed job
can easily be the first thing to touch the service after a restart, which is
exactly when a long ingest is starting and the saving matters most. The probe
memoizes for the process lifetime, so this costs one request overall rather
than one per batch.

Behaviour is otherwise unchanged. A native backend still tries /api/embed
first and still falls back if it fails for a non-context reason, and
context-length errors still bubble to embed() for the truncated retry. The
response-shape validation stays: the probe establishes that /api/tags
answered like Ollama, not that /api/embed will.

Reported by @horsleyb.

Closes #1279

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-29 15:54:41 -07:00
..
app fix(ai): don't probe the native embed endpoint on a non-Ollama backend 2026-09-29 15:54:41 -07:00
bin feat: curated content system overhaul 2026-02-11 15:44:46 -08:00
commands fix(queue): stop stalled-job recovery forking the embedding chain 2026-09-29 15:54:41 -07:00
config fix: lazy-connect + retry for ioredis to avoid blocked startup 2026-06-23 17:40:10 +00:00
constants feat(AI): let retrieval decline instead of making the prompt paper over it 2026-09-29 15:54:41 -07:00
database feat(benchmark): official multi-arch sysbench, resolved digest, platform metadata (#1158) 2026-08-04 03:39:53 +00:00
docs docs: answer the RAM question alongside disk 2026-09-29 15:54:41 -07:00
inertia fix(benchmark): show the v2 score in Benchmark History 2026-09-29 15:54:41 -07:00
providers fix(kiwix): self-heal a missing or corrupt library XML on startup 2026-06-23 04:46:56 +00:00
public feat(creator-packs): add missing Modern Rogue banner asset (#1147) 2026-08-04 03:39:52 +00:00
resources chore: standardize brand name to Project NOMAD, retire backronym 2026-08-04 03:37:32 +00:00
scripts refactor(drug-reference): make collections JSON the single source for curated data (#1130) 2026-08-04 03:38:35 +00:00
start feat: auto-generating OpenAPI docs with Scalar UI (#1128) 2026-08-04 03:38:33 +00:00
tests fix(queue): stop stalled-job recovery forking the embedding chain 2026-09-29 15:54:41 -07:00
types feat(AI): let retrieval decline instead of making the prompt paper over it 2026-09-29 15:54:41 -07:00
util Add offline FDA drug reference (labels, interaction view, conditions, remedies) (#1040) 2026-08-04 03:38:33 +00:00
views chore: standardize brand name to Project NOMAD, retire backronym 2026-08-04 03:37:32 +00:00
.editorconfig feat: initial commit 2025-06-29 15:51:08 -07:00
.env.example feat(creator-packs): gated per-creator video packs, offline via Kiwix (#1106) 2026-08-04 03:38:27 +00:00
ace.js feat: initial commit 2025-06-29 15:51:08 -07:00
adonisrc.ts feat(GPU): auto-remediate nomad_ollama passthrough loss on admin boot (#755) 2026-05-20 10:16:00 -07:00
eslint.config.js feat: openwebui+ollama and zim management 2025-07-09 09:08:21 -07:00
package-lock.json chore(deps): bump axios and systeminformation in /admin 2026-08-04 03:38:40 +00:00
package.json feat(eval): standardized RAG quality evaluation harness (#1233) 2026-09-29 15:54:41 -07:00
tailwind.config.ts feat: initial commit 2025-06-29 15:51:08 -07:00
tsconfig.json Add offline FDA drug reference (labels, interaction view, conditions, remedies) (#1040) 2026-08-04 03:38:33 +00:00
vite.config.ts fix(Maps): ensure proper parsing of hostnames (#640) 2026-04-03 14:26:50 -07:00