ClassroomCopilot/api

Files

T

History

kcar 76e11b0b06

api-ci-deploy / test-build-deploy (push) Has been cancelled

Details

feat(docling): B1-2 AQA label normalization + missing-.1 inference + MCQ gap (salvaged)

(cherry picked from commit a707a5afd9)

2026-06-08 04:03:17 +00:00

..

feat(docling): B1 image-only OCR eval harness (overwatch-cleaned)

2026-06-08 03:10:10 +00:00

feat(docling): B1 image-only OCR eval harness (overwatch-cleaned)

2026-06-08 03:10:10 +00:00

__init__.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

.gitignore

feat(docling): B1 image-only OCR eval harness (overwatch-cleaned)

2026-06-08 03:10:10 +00:00

bands.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

dsync.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

extract.py

feat(docling): B1-2 AQA label normalization + missing-.1 inference + MCQ gap (salvaged)

2026-06-08 04:03:17 +00:00

finalize.py

[verified] generalize B1 response regions and marks gap fill

2026-06-08 04:49:21 +01:00

furniture.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

page_roles.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

README.md

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

regions.py

[verified] generalize B1 response regions and marks gap fill

2026-06-08 04:49:21 +01:00

tables.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

template.py

S5-5: centralized part-box synthesis (band-y x content-margins)

2026-06-07 20:38:25 +01:00

validate.py

[verified] add docling auto-map package wrapper

2026-06-07 20:03:06 +01:00

README.md

API Docling first-pass auto-map package

This package is the in-API home for the S5 exam-template/first-pass/v1 extraction pipeline copied from /home/kcar/dev/docling-exam-spike.

auto_map(pdf_bytes) returns the editable first-pass template.json shape consumed by downstream exam-marker mapping. The pipeline keeps margins as constraining inputs: document left/right and per-page top/bottom margins are derived before template assembly, then part/question bands and furniture/figure boxes are constrained through those margins.

dsync Redis env wiring

The OCR path uses dsync.py for docling-serve GPU locking, page cache, and retry. Configure with env-var names only:

DOCLING_SERVE
DOCLING_REDIS_URL
DOCLING_REDIS_HOST
DOCLING_REDIS_PORT
DOCLING_REDIS_PASSWORD
DOCLING_REDIS_DB

If Redis is unavailable, dsync falls back to no cache/lock and logs that state. Do not put secret values in this file.