Oliver/ai_qc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
ai_qc/backend/visual_qc_apps/element_alignment
History
Exact
nickviljoen 9eed569587 Tone down OCR from authoritative to supplementary to reduce false positives 
OCR measurements were causing the LLM to over-rely on bounding box numbers
and fail correct assets on minor measurement inaccuracies. Changes:
- All prompts now say "supplementary data" not "authoritative/primary source"
- LLM instructed to prioritise visual assessment, use OCR to confirm/question
- Alignment tolerance widened from 1.5% to 3% of width
- OCR context footer softened with accuracy caveat (~5-10px margin of error)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 13:54:00 +02:00
..
__init__.py Create frontend and backend folder structure for deployment 2025-11-06 11:55:53 +02:00
app.py Tone down OCR from authoritative to supplementary to reduce false positives 2026-04-02 13:54:00 +02:00