2 Commits

Author	SHA1	Message	Date
root	71adc51c00	fix(embed): chunk + mean-pool long text so large pages embed ... Split long page text into 1500-char chunks before calling Ollama, then mean-pool the per-chunk vectors into one page vector. Removes the hard 6000-char slice that still caused 500s on dense markdown/table pages. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-05 23:24:40 +10:00
root	37b7753360	feat(jobs): embed.text worker (Ollama → vector(1024)) ... Pads nomic-embed-text's 768 dims to 1024 zeros so a later 1024-dim model swap is a re-embed, not a migration (per master spec). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>	2026-06-01 03:43:57 +10:00