Marcel 7f78bc9cf4 fix(ocr): increase memory limit to 10GB, reduce render DPI to 200 ...

Surya 0.17 models use ~5GB idle. At 300 DPI on a multi-page PDF,
page images + inference tensors push past the 6GB limit, causing
OOM kills during 'Detecting bboxes'. Increased to 10GB and reduced
render DPI to 200 (still sufficient for OCR, uses ~44% less memory).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-12 22:20:36 +02:00

..

engines

feat(ocr): auto-insert [unleserlich] markers for low-confidence words

2026-04-12 19:16:17 +02:00

confidence.py

feat(ocr): per-script-type confidence thresholds

2026-04-12 20:50:59 +02:00

Dockerfile

fix(ocr): add pyvips for kraken PDF input support

2026-04-12 20:11:14 +02:00

main.py

fix(ocr): increase memory limit to 10GB, reduce render DPI to 200

2026-04-12 22:20:36 +02:00

models.py

feat(ocr): add Python OCR microservice, RestClientOcrClient, Docker Compose

2026-04-12 15:26:40 +02:00

requirements.txt

fix(ocr): add pyvips for kraken PDF input support

2026-04-12 20:11:14 +02:00

test_confidence.py

feat(ocr): per-script-type confidence thresholds

2026-04-12 20:50:59 +02:00