WeKnora/internal/application
po-et aea51ecb62 fix(wiki): batch taxonomy embeddings instead of one request per set
Taxonomy selection asked the embedding provider for every folder in one
request, and for every item in another, by calling BatchEmbed directly.
BatchEmbedWithPool is what reads BATCH_EMBED_SIZE and splits the inputs,
so these two calls sat outside the only control an operator has over
request width: a provider that caps inputs per request rejected them
however low that setting was, and the planner fell back to feeding all
folders (#3390).

Send both sets through the pool, the way every other embedding caller in
the service does. Nothing else changes: the pool reassembles the vectors
in input order, which is what the similarity ranking below depends on.

The regression test carries the real pooling implementation behind a
provider that records the width of every request it receives, so a call
that goes back to the provider directly shows up as one oversized
request rather than as a passing test.
2026-09-19 20:19:06 +08:00
..
access refactor(resource-access): unify scoped authorization and transfer recovery (#3097) 2026-09-08 15:36:33 +08:00
repository fix(security): close the low-severity shared-space findings (#3416) 2026-09-18 22:58:46 +08:00
service fix(wiki): batch taxonomy embeddings instead of one request per set 2026-09-19 20:19:06 +08:00