Commit graph

  • 2394afd13c add license main Brent Schroeter 2026-01-20 22:31:04 -08:00
  • 35f750c28d clean up outdated files Brent Schroeter 2026-01-16 04:55:50 +00:00
  • b19b0bfb07 tune sharpness detection for sparse pages Brent Schroeter 2026-01-15 22:14:36 +00:00
  • df786f103f ignore spurious text in clipping detection Brent Schroeter 2026-01-15 22:14:01 +00:00
  • 24e59e0bfc properly cast null sql values Brent Schroeter 2026-01-15 21:44:45 +00:00
  • f0a4ef253b re-run ocr as needed to screen false positives Brent Schroeter 2026-01-15 21:33:57 +00:00
  • 9a94719dc1 replace sharpness edge detection with gradient Brent Schroeter 2026-01-15 21:31:24 +00:00
  • ce42ab58f1 fix sloppy llm code for pdf parsing Brent Schroeter 2026-01-15 21:27:04 +00:00
  • 1ca2238c5d switch from sqlite to phonograph Brent Schroeter 2026-01-14 23:26:46 +00:00
  • d48b672e1b improve contrast norm and sharpness measurement Brent Schroeter 2025-12-20 08:58:49 +00:00
  • 3da76d4537 reuse pdf ocr when available Brent Schroeter 2025-12-20 02:16:41 +00:00
  • ac7e93a75b add interchangeable ocr engines Brent Schroeter 2025-11-07 05:41:18 +00:00
  • d5757e3811 rewrite data fetching into archive_item.py Brent Schroeter 2025-10-04 18:03:03 -07:00
  • 4d9161b043 rewrite to engine.py Brent Schroeter 2025-10-04 15:09:16 -07:00
  • 815934ad23 store results to sqlite Brent Schroeter 2025-08-18 20:31:55 -07:00
  • d33a7dc515 crop detection tuning Brent Schroeter 2025-08-10 22:56:25 -07:00
  • a5e3a2a429 add ocr crop warnings Brent Schroeter 2025-08-10 22:10:16 -07:00
  • 8dbcb19b43 init Brent Schroeter 2025-08-10 12:27:39 -07:00