Abhinav Raut 000d789ed8 shortlist tags with embeddings before asking the LLM to suggest them ...

Tag suggestion used to send the first 300 tags to the model, so anything past
that was invisible. Tags are now embedded into the same index as the knowledge
base, and only the tags most similar to the conversation get sent. The reconcile
loop embeds new and renamed tags and drops vectors for deleted ones, and a
provider change purges them so they are rebuilt with the new model.

2026-07-30 23:09:23 +05:30

..

models

fix: Use SyncedEnforcer in casbin, fixes panics.

2025-01-22 03:40:32 +05:30

queries.sql

shortlist tags with embeddings before asking the LLM to suggest them

2026-07-30 23:09:23 +05:30

tag.go

i18n: fix localization issues (#231)

2026-02-22 15:12:00 +05:30