Files
didar 9bf367abf4
deploy / deploy (push) Successful in 30s
fix: filter RU/KZ stopwords from KB search so filler words can't false-match
search_kb_rows had no relevance floor: any exact-token hit, however
generic, scored above zero and could win as the top/only result. A
caller utterance as thin as a bare "да" (confirming the language) could
exact-match that same common word inside an unrelated FAQ article's
body and get returned as "the" answer, which then got read back
almost verbatim — this is what surfaced live as the AI unprompted
launching into a voucher-activation explanation right after the
customer confirmed Russian, having said nothing else.

tokenize_kb_text now drops a curated set of RU/KZ greetings,
confirmations, pronouns, and particles. A stopword-only query naturally
falls through to the existing "no query tokens -> no results" path
instead of returning a coincidental match; genuine single-content-word
queries (e.g. "ваучер") are unaffected. Applies to every channel that
calls _kb_search (voice, Telegram, WhatsApp), not just voice.
2026-08-31 01:08:11 +05:00
..
2026-05-09 09:16:06 +05:00
.
2026-05-04 23:00:34 +05:00