48a5e49313
The LLM was bad at scoring its own conversion quality — rejecting good Pass 2 output (score 5/10 for a perfectly usable conversion). Instead: - Remove Pass 3 entirely (saves ~0.4s and one inference call) - Trust Pass 2 output and return it to the user - Build notification from Pass 1 classification info instead - User can always adjust mapping via dropdowns if they disagree |
||
|---|---|---|
| .. | ||
| datasets | ||
| hardware | ||
| inference | ||
| models | ||
| paths | ||
| .gitkeep | ||
| cache_cleanup.py | ||
| transformers_version.py | ||
| utils.py | ||