stumpylog fc5fc485de Performance: load a cached Hugging Face embedding model without contacting the Hub ...

Every chat question and AI suggestion request builds the embedding model, and sentence-transformers
checks the Hub for a newer revision each time. With the model already cached that check cost about
2 seconds per request (0.2 seconds without it), and it fails outright when the Hub is unreachable.

Load from the local cache first and only download when the model is missing. A full rebuild still
checks the Hub, so a new model release is picked up together with re-embedding every document
instead of silently mixing revisions.

2026-11-09 11:36:42 -08:00

..

assets

Documentation: tweak demo hosting attribution

2026-10-12 09:18:19 -07:00

administration.md

Performance: load a cached Hugging Face embedding model without contacting the Hub

2026-11-09 11:36:42 -08:00

advanced_usage.md

Feature: store barcode contents, list and search them (#14276)

2026-10-05 16:25:19 +00:00

api.md

Enhancement: relative date custom field queries (#14549)

2026-10-29 17:25:21 +00:00

changelog.md

Documentation: Add v3.4.2 changelog (#14681)

2026-11-03 14:05:46 -08:00

configuration.md

Enhancement: skip local 2FA for trusted OIDC AMR (#14403)

2026-10-24 21:11:10 +00:00

development.md

Chore: Randomize test order and seed Faker per run (#14173)

2026-09-21 10:57:13 -07:00

faq.md

Documentation: correct duplicates info (#14243)

2026-09-23 08:27:18 -07:00

index.md

Documentation: tweak demo hosting attribution

2026-10-12 09:18:19 -07:00

migration-v3.md

Merge branch 'main' into dev

2026-08-22 05:27:10 -07:00

setup.md

Chore: Drop ImageMagik as a dependency (#14440)

2026-10-20 11:22:43 -07:00

troubleshooting.md

Chore: silence gotenberg startup warning (#14405)

2026-10-12 16:54:47 +00:00

usage.md

Enhancement: support custom fields in workflow title templates (#14564)

2026-10-29 17:40:53 +00:00