shawn b80ed4b483 feat: Ollama vision OCR via Windows PC for label photo matching ...

- Add persistent SSH tunnel (systemd service) to Windows PC Ollama
- Add _HAS_OLLAMA check at server startup (qwen2.5vl:3b)
- Replace Tesseract-only OCR with Ollama-first strategy
- Ollama (qwen2.5vl:3b) handles dark/complex labels Tesseract can't read
- Keurig serial 2500.0100.0025534 now correctly matched as Asset #5144
- Add ocr_source field to /api/ocr response ('ollama' or 'tesseract')
- Fix match_label_photo.py argparse bug (image_paths -> images)
- Update match_label_photo.py CLI to read vision key from Hermes config

2026-05-29 08:59:53 -04:00

..

apply_gps_sources.py

feat: asset naming, location extraction, and location display

2026-05-28 23:58:56 -04:00

clean_asset_names.py

clean up asset names: strip addresses/floors/parks/building prefixes from names (353/1848 cleaned)

2026-05-23 20:24:51 -04:00

extract_asset_location_data.py

feat: extract floor/building/room/trailer from asset names

2026-05-23 19:41:55 -04:00

geocode_asset_addresses.py

feat: asset naming, location extraction, and location display

2026-05-28 23:58:56 -04:00

import_cantaloupe.py

Rename 'Add Asset' tab to 'Add / Find Asset' across nav + tabs

2026-05-25 23:14:52 -04:00

match_label_photo.py

feat: Ollama vision OCR via Windows PC for label photo matching

2026-05-29 08:59:53 -04:00

migrate_asset_names.py

fix: keep GUEST/CAST visible in asset names

2026-05-29 00:13:08 -04:00

populate_asset_company_place.py

feat: branch fallback for assets without account linkage

2026-05-29 07:51:02 -04:00

tag_disney_properties.py

feat: tag Disney assets with park/resort codes and display names

2026-05-23 19:50:16 -04:00