mirror of
https://github.com/docling-project/docling-eval.git
synced 2026-05-17 13:10:47 +00:00
17e9fde84f
* Add README for Docling-DPBench Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * feat: Update OCREvaluator with additional metrics * fix: bug fix * add edit-distance lib * update pure ocr metrics * Establish SegmentedPage support in DatasetRecord and DatasetRecordWithPrediction Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add SegmentedPage usage to PixParse dataset provider Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * add pure ocr metrics * refactor: update dependencies * fix dependencies and build errors * feat: add optype and scipy-stubs packages * fix: fix type error * fix package name * fix bugs and add funsd ocr test * fix type error * finalize changes * fix build errors * fix: ignore edit_distance missing import * Add functionality to merge cells in Google OCR prediction (#103) * feat: add global_merge function in google prediction provider for word cell merging * address review comment * remove unused imports * address review comments and remove dictionary conversions --------- Co-authored-by: samiullahchattha <Sami.Ullah1@ibm.com> * refactor and address review comments * fix regression bug * refactor code and reduce metrics to three * make ocr classes private * fix type error * refactor: update geometry utils to use BoundingBox and TextCell Signed-off-by: samiullahchattha <Sami.Ullah1@ibm.com> * refactor: rename metrics variables for consistency and clarity Signed-off-by: samiullahchattha <Sami.Ullah1@ibm.com> * Update lock for docling-core Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: samiuc <sami.ullah.chat@gmail.com> Signed-off-by: samiullahchattha <Sami.Ullah1@ibm.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com> Co-authored-by: samiullahchattha <Sami.Ullah1@ibm.com>