mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 23:12:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: update all test cases

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-02-04 10:52:56 +01:00
parent 04f9963396
commit c9b0b5aff3
52 changed files with 52 additions and 52 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
poetry.lock generated
View File

@ -887,7 +887,7 @@ chunking = ["semchunk (>=2.2.0,<3.0.0)", "transformers (>=4.34.0,<5.0.0)"]
type = "git"
url = "ssh://git@github.com/DS4SD/docling-core.git"
reference = "cau/add-content-layer"
resolved_reference = "1609660791cbf83e7ffa3e5e1877f08c0ae986d7"
resolved_reference = "4c19ae7f7fb128a12173c50a9ab376114f70a689"
[[package]]
name = "docling-ibm-models"

2
tests/data/groundtruth/docling_v1/2203.01017v2.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2203.01017v2.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2206.01062.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2206.01062.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2305.03393v1-pg9.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2305.03393v1.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/2305.03393v1.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/amt_handbook_sample.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/code_and_formula.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/code_and_formula.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/picture_classification.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/picture_classification.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/redp5110_sampled.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v1/redp5110_sampled.pages.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2203.01017v2.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2206.01062.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2305.03393v1-pg9.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/2305.03393v1.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/amt_handbook_sample.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/code_and_formula.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/elife-56337.xml.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/example_01.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/example_02.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/example_03.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/example_04.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/example_05.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/ipa20180000016.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/ipa20200022300.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/lorem_ipsum.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/pa20010031492.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/pftaps057006474.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/pg06442728.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/picture_classification.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/pntd.0008301.xml.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/pone.0234687.xml.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/redp5110_sampled.json
View File

File diff suppressed because one or more lines are too long

2
tests/data/groundtruth/docling_v2/tablecell.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/test-01.xlsx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/test_emf_docx.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/unit_test_01.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/unit_test_headers.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/unit_test_lists.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/wiki_duck.html.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/word_sample.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data/groundtruth/docling_v2/word_tables.docx.json
View File

@ -10,7 +10,7 @@
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "body",
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},

2
tests/data_scanned/groundtruth/docling_v1/ocr_test.pages.json
View File

@ -1 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.json
View File

@ -1 +1 @@
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}
{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "ocr_test", "origin": {"mimetype": "application/pdf", "binary_hash": 14853448746796404529, "filename": "ocr_test.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "content_layer": "furniture", "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}], "content_layer": "body", "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "content_layer": "body", "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 69.6796646118164, "t": 764.9216918945312, "r": 504.87200927734375, "b": 689.012451171875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 94]}], "orig": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package", "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "pictures": [], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 595.201171875, "height": 841.9216918945312}, "image": null, "page_no": 1}}}

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.pages.json
View File

@ -1 +1 @@
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715732336044312, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]
[{"page_no": 0, "size": {"width": 595.201171875, "height": 841.9216918945312}, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "body": [{"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 69.6796630536824, "t": 76.99999977896756, "r": 504.8720051760782, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}, "confidence": 0.9715733528137207, "cells": [{"id": 0, "text": "Docling bundles PDF document conversion to", "bbox": {"l": 73.34702132031646, "t": 76.99999977896756, "r": 503.64955224479564, "b": 97.99999977896755, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "JSON and Markdown in an easy self contained", "bbox": {"l": 69.6796630536824, "t": 104.00000011573796, "r": 504.8720051760782, "b": 124.83139494707741, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "package", "bbox": {"l": 71.84193505100733, "t": 129.797125232046, "r": 153.088934155825, "b": 152.90926970226084, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"}], "headers": []}}]