Benjamin_Boenisch/breakpilot-lehrer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
e426de937c03257c13a6247d4d4b8647cc1ae4d9
breakpilot-lehrer/klausur-service/backend
History
Benjamin Admin e426de937c
Some checks failed
CI / go-lint (push) Has been skipped
Details
CI / python-lint (push) Has been skipped
Details
CI / nodejs-lint (push) Has been skipped
Details
CI / test-go-school (push) Successful in 27s
Details
CI / test-go-edu-search (push) Successful in 27s
Details
CI / test-python-klausur (push) Failing after 1m54s
Details
CI / test-python-agent-core (push) Successful in 18s
Details
CI / test-nodejs-website (push) Successful in 19s
Details
fix: expand narrow columns + lower dewarp thresholds for small angles 
Two fixes for edge case where residual shear pushes content out of
narrow columns (marker, page_ref):

1. Column expansion (Step 10): After detection, narrow columns (<10%
   content width) expand into adjacent whitespace gaps, claiming up to
   40% of the gap but never past the nearest word in the neighbor
   column. This gives marker/page_ref columns breathing room.

2. Dewarp sensitivity: Lower minimum angle from 0.15° to 0.08°, lower
   ensemble min confidence from 0.5 to 0.35, lower final threshold
   from 0.5 to 0.4, and skip quality gate for small corrections
   (<0.5°) where projection variance change is negligible.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-04 09:32:47 +01:00
..
data
feat(ocr-pipeline): British/American IPA pronunciation choice
2026-03-01 11:08:52 +01:00
mail
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
migrations
feat(ocr-pipeline): add Step 5 word recognition (grid from columns × rows)
2026-02-28 02:18:29 +01:00
models
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
policies
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
routes
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
services
feat: OCR pipeline v2.1 – narrow column OCR, dewarp automation, Fabric.js editor
2026-03-03 22:44:14 +01:00
tests
refactor(word-step): make table fully generic and fix marker-only row filter
2026-03-03 08:45:24 +01:00
admin_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
config.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
country_metadata.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
cv_vocab_pipeline.py
fix: expand narrow columns + lower dewarp thresholds for small angles
2026-03-04 09:32:47 +01:00
dsfa_corpus_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
dsfa_rag_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
eh_pipeline.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
eh_templates.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
embedding_client.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
full_compliance_pipeline.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
full_reingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
github_crawler.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
handwriting_htr_api.py
feat(klausur): Handschrift entfernen + Klausur-HTR implementiert
2026-03-03 12:04:26 +01:00
hybrid_search.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
hybrid_vocab_extractor.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
hyde.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_corpus_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_corpus_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_corpus_robust.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
legal_templates_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
main.py
feat(klausur): Handschrift entfernen + Klausur-HTR implementiert
2026-03-03 12:04:26 +01:00
metrics_db.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
migrate_rag_chunks.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
minio_storage.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
nibis_ingestion.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
nru_worksheet_generator.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
ocr_labeling_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
ocr_pipeline_api.py
feat: OCR pipeline v2.1 – narrow column OCR, dewarp automation, Fabric.js editor
2026-03-03 22:44:14 +01:00
ocr_pipeline_session_store.py
feat(klausur): Handschrift entfernen + Klausur-HTR implementiert
2026-03-03 12:04:26 +01:00
pdf_export.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
pdf_extraction.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
pipeline_checkpoints.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
pyproject.toml
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
qdrant_service.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
rag_evaluation.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
rbac.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
requirements.txt
feat: OCR pipeline v2.1 – narrow column OCR, dewarp automation, Fabric.js editor
2026-03-03 22:44:14 +01:00
reranker.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
self_rag.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
storage.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
template_sources.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
tesseract_vocab_extractor.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
training_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
training_export_service.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
trocr_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
upload_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
vocab_session_store.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
vocab_worksheet_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
worksheet_cleanup_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
worksheet_editor_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_api.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_crawler.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_models.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00
zeugnis_seed_data.py
Initial commit: breakpilot-lehrer - Lehrer KI Platform
2026-02-11 23:47:26 +01:00