diff --git a/poetry.lock b/poetry.lock index 73fc85db..c3905141 100644 --- a/poetry.lock +++ b/poetry.lock @@ -888,13 +888,13 @@ chunking = ["semchunk (>=2.2.0,<3.0.0)", "transformers (>=4.34.0,<5.0.0)"] [[package]] name = "docling-ibm-models" -version = "3.2.1" +version = "3.3.0" description = "This package contains the AI models used by the Docling PDF conversion package" optional = false python-versions = "<4.0,>=3.9" files = [ - {file = "docling_ibm_models-3.2.1-py3-none-any.whl", hash = "sha256:55bca5673381cc5862f4de584345020d071414c46bc1b9f6436d674e3610ec97"}, - {file = "docling_ibm_models-3.2.1.tar.gz", hash = "sha256:abd1bdc58f00600065eedbfbd34876704d5004cd20884a2c0a61ca2ee5a927dd"}, + {file = "docling_ibm_models-3.3.0-py3-none-any.whl", hash = "sha256:f1c99d345cb524239c7a2090969920e4311fd2fe22dad9bd609bc38039ec56eb"}, + {file = "docling_ibm_models-3.3.0.tar.gz", hash = "sha256:5a7497053871179d59870c830945aa8664a34aac48b7e68edf602720ee7f6c49"}, ] [package.dependencies] @@ -1046,13 +1046,13 @@ testing = ["hatch", "pre-commit", "pytest", "tox"] [[package]] name = "executing" -version = "2.1.0" +version = "2.2.0" description = "Get the currently executing AST node of a frame, and other information" optional = false python-versions = ">=3.8" files = [ - {file = "executing-2.1.0-py2.py3-none-any.whl", hash = "sha256:8d63781349375b5ebccc3142f4b30350c0cd9c79f921cde38be2be4637e98eaf"}, - {file = "executing-2.1.0.tar.gz", hash = "sha256:8ea27ddd260da8150fa5a708269c4a10e76161e2496ec3e587da9e3c0fe4b9ab"}, + {file = "executing-2.2.0-py2.py3-none-any.whl", hash = "sha256:11387150cad388d62750327a53d3339fad4888b39a6fe233c3afbb54ecffd3aa"}, + {file = "executing-2.2.0.tar.gz", hash = "sha256:5d108c028108fe2551d1a7b2e8b713341e2cb4fc0aa7dcf966fa4327a5226755"}, ] [package.extras] @@ -3674,14 +3674,14 @@ files = [ [[package]] name = "nvidia-nvjitlink-cu12" -version = "12.6.85" +version = "12.8.61" description = "Nvidia JIT LTO Library" optional = false python-versions = ">=3" files = [ - {file = "nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:eedc36df9e88b682efe4309aa16b5b4e78c2407eac59e8c10a6a47535164369a"}, - {file = "nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cf4eaa7d4b6b543ffd69d6abfb11efdeb2db48270d94dfd3a452c24150829e41"}, - {file = "nvidia_nvjitlink_cu12-12.6.85-py3-none-win_amd64.whl", hash = "sha256:e61120e52ed675747825cdd16febc6a0730537451d867ee58bee3853b1b13d1c"}, + {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:45fd79f2ae20bd67e8bc411055939049873bfd8fac70ff13bd4865e0b9bdab17"}, + {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9b80ecab31085dda3ce3b41d043be0ec739216c3fc633b8abe212d5a30026df0"}, + {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-win_amd64.whl", hash = "sha256:1166a964d25fdc0eae497574d38824305195a5283324a21ccb0ce0c802cbf41c"}, ] [[package]] @@ -4612,13 +4612,13 @@ files = [ [[package]] name = "pydantic" -version = "2.10.5" +version = "2.10.6" description = "Data validation using Python type hints" optional = false python-versions = ">=3.8" files = [ - {file = "pydantic-2.10.5-py3-none-any.whl", hash = "sha256:4dd4e322dbe55472cb7ca7e73f4b63574eecccf2835ffa2af9021ce113c83c53"}, - {file = "pydantic-2.10.5.tar.gz", hash = "sha256:278b38dbbaec562011d659ee05f63346951b3a248a6f3642e1bc68894ea2b4ff"}, + {file = "pydantic-2.10.6-py3-none-any.whl", hash = "sha256:427d664bf0b8a2b34ff5dd0f5a18df00591adcee7198fbd71981054cef37b584"}, + {file = "pydantic-2.10.6.tar.gz", hash = "sha256:ca5daa827cce33de7a42be142548b0096bf05a7e7b365aebfa5f8eeec7128236"}, ] [package.dependencies] @@ -6124,13 +6124,13 @@ files = [ [[package]] name = "sentence-transformers" -version = "3.3.1" +version = "3.4.0" description = "State-of-the-Art Text Embeddings" optional = false python-versions = ">=3.9" files = [ - {file = "sentence_transformers-3.3.1-py3-none-any.whl", hash = "sha256:abffcc79dab37b7d18d21a26d5914223dd42239cfe18cb5e111c66c54b658ae7"}, - {file = "sentence_transformers-3.3.1.tar.gz", hash = "sha256:9635dbfb11c6b01d036b9cfcee29f7716ab64cf2407ad9f403a2e607da2ac48b"}, + {file = "sentence_transformers-3.4.0-py3-none-any.whl", hash = "sha256:f7d4ad81260149172a98108a3481d8e82c11d31f40d41885f43d481149237743"}, + {file = "sentence_transformers-3.4.0.tar.gz", hash = "sha256:334288062d4b888cdd7b75913fead46b1e42bfe836f8343d23478d17f799e650"}, ] [package.dependencies] @@ -7487,13 +7487,13 @@ files = [ [[package]] name = "xlsxwriter" -version = "3.2.0" +version = "3.2.1" description = "A Python module for creating Excel XLSX files." optional = false python-versions = ">=3.6" files = [ - {file = "XlsxWriter-3.2.0-py3-none-any.whl", hash = "sha256:ecfd5405b3e0e228219bcaf24c2ca0915e012ca9464a14048021d21a995d490e"}, - {file = "XlsxWriter-3.2.0.tar.gz", hash = "sha256:9977d0c661a72866a61f9f7a809e25ebbb0fb7036baa3b9fe74afcfca6b3cb8c"}, + {file = "XlsxWriter-3.2.1-py3-none-any.whl", hash = "sha256:7e8f7c60b7a1660ef791d46ab5de78469cb978b991ca841af61f5832d2f9f4fe"}, + {file = "XlsxWriter-3.2.1.tar.gz", hash = "sha256:97618759cb264fb6a93397f660cca156ffa9561743b1823dafb60dc4474e1902"}, ] [[package]] @@ -7751,4 +7751,4 @@ tesserocr = ["tesserocr"] [metadata] lock-version = "2.0" python-versions = "^3.9" -content-hash = "8bb0b67294a50c0340c5cc02ce60d3608ef4d1968ae50f7e0b8b4c8a26c34734" +content-hash = "7fcfc061454f229745d6f305e1fa593468a684059717195c6ae4174bec13d362" diff --git a/pyproject.toml b/pyproject.toml index c3e1fa67..6945e5a7 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -27,7 +27,7 @@ packages = [{include = "docling"}] python = "^3.9" pydantic = "^2.0.0" docling-core = { version = "^2.15.1", extras = ["chunking"] } -docling-ibm-models = "^3.2.1" +docling-ibm-models = "^3.3.0" deepsearch-glm = "^1.0.0" docling-parse = "^3.1.0" filetype = "^1.2.0" diff --git a/tests/data/groundtruth/docling_v1/picture_classification.doctags.txt b/tests/data/groundtruth/docling_v1/picture_classification.doctags.txt new file mode 100644 index 00000000..cbcde73f --- /dev/null +++ b/tests/data/groundtruth/docling_v1/picture_classification.doctags.txt @@ -0,0 +1,17 @@ + +Figures Example +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +Figure 1: This is an example image. +
+ +Figure 1: This is an example image. +
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +Figure 2: This is an example image. +
+ +Figure 2: This is an example image. +
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. +
\ No newline at end of file diff --git a/tests/data/groundtruth/docling_v1/picture_classification.json b/tests/data/groundtruth/docling_v1/picture_classification.json new file mode 100644 index 00000000..ad1bc5c2 --- /dev/null +++ b/tests/data/groundtruth/docling_v1/picture_classification.json @@ -0,0 +1 @@ +{"_name": "", "type": "pdf-document", "description": {"title": null, "abstract": null, "authors": null, "affiliations": null, "subjects": null, "keywords": null, "publication_date": null, "languages": null, "license": null, "publishers": null, "url_refs": null, "references": null, "publication": null, "reference_count": null, "citation_count": null, "citation_date": null, "advanced": null, "analytics": null, "logs": [], "collection": null, "acquisition": null}, "file-info": {"filename": "picture_classification.pdf", "filename-prov": null, "document-hash": "959854dff729acaa22404d629a45cefcad8d942e595961185fc03a80d9fcc3a1", "#-pages": 2, "collection-name": null, "description": null, "page-hashes": [{"hash": "d9e3fc1226356b30c66012f05ad14089b00c59ea129195cd6ff8a0c68bda6f39", "model": "default", "page": 1}, {"hash": "9386884e13a97ce9662210a7e4258bbbb4f2e0e00663636160918e55b2806575", "model": "default", "page": 2}]}, "main-text": [{"prov": [{"bbox": [133.76800537109375, 654.4518432617188, 252.35513305664062, 667.1912231445312], "page": 1, "span": [0, 15], "__ref_s3_data": null}], "text": "Figures Example", "type": "subtitle-level-1", "payload": null, "name": "Section-header", "font": null}, {"prov": [{"bbox": [133.76800537109375, 501.97412109375, 477.4827575683594, 642.3280639648438], "page": 1, "span": [0, 887], "__ref_s3_data": null}], "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [226.89100646972656, 254.0182647705078, 384.35479736328125, 262.86505126953125], "page": 1, "span": [0, 35], "__ref_s3_data": null}], "text": "Figure 1: This is an example image.", "type": "caption", "payload": null, "name": "Caption", "font": null}, {"name": "Picture", "type": "figure", "$ref": "#/figures/0"}, {"prov": [{"bbox": [133.76800537109375, 122.51225280761719, 477.4817199707031, 238.95504760742188], "page": 1, "span": [0, 747], "__ref_s3_data": null}], "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [303.13299560546875, 87.43224334716797, 308.1142883300781, 96.27903747558594], "page": 1, "span": [0, 1], "__ref_s3_data": null}], "text": "1", "type": "page-footer", "payload": null, "name": "Page-footer", "font": null}, {"prov": [{"bbox": [133.76800537109375, 523.7951049804688, 477.4817199707031, 664.1490478515625], "page": 2, "span": [0, 887], "__ref_s3_data": null}], "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [226.89100646972656, 259.9422607421875, 384.35479736328125, 268.7890319824219], "page": 2, "span": [0, 35], "__ref_s3_data": null}], "text": "Figure 2: This is an example image.", "type": "caption", "payload": null, "name": "Caption", "font": null}, {"name": "Picture", "type": "figure", "$ref": "#/figures/1"}, {"prov": [{"bbox": [133.76800537109375, 117.32023620605469, 477.4817199707031, 245.71804809570312], "page": 2, "span": [0, 804], "__ref_s3_data": null}], "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.", "type": "paragraph", "payload": null, "name": "Text", "font": null}, {"prov": [{"bbox": [303.13299560546875, 87.43224334716797, 308.1142883300781, 96.27903747558594], "page": 2, "span": [0, 1], "__ref_s3_data": null}], "text": "2", "type": "page-footer", "payload": null, "name": "Page-footer", "font": null}], "figures": [{"prov": [{"bbox": [134.92005920410156, 281.78173828125, 475.66351318359375, 487.109375], "page": 1, "span": [0, 35], "__ref_s3_data": null}], "text": "Figure 1: This is an example image.", "type": "figure", "payload": null, "bounding-box": null}, {"prov": [{"bbox": [218.8155517578125, 283.10589599609375, 391.96246337890625, 513.984619140625], "page": 2, "span": [0, 35], "__ref_s3_data": null}], "text": "Figure 2: This is an example image.", "type": "figure", "payload": null, "bounding-box": null}], "tables": [], "bitmaps": null, "equations": [], "footnotes": [], "page-dimensions": [{"height": 792.0, "page": 1, "width": 612.0}, {"height": 792.0, "page": 2, "width": 612.0}], "page-footers": [], "page-headers": [], "_s3_data": null, "identifiers": null} \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v1/picture_classification.md b/tests/data/groundtruth/docling_v1/picture_classification.md new file mode 100644 index 00000000..6b9d1faf --- /dev/null +++ b/tests/data/groundtruth/docling_v1/picture_classification.md @@ -0,0 +1,15 @@ +## Figures Example + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. + +Figure 1: This is an example image. + + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. + +Figure 2: This is an example image. + + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v1/picture_classification.pages.json b/tests/data/groundtruth/docling_v1/picture_classification.pages.json new file mode 100644 index 00000000..744f54fb --- /dev/null +++ b/tests/data/groundtruth/docling_v1/picture_classification.pages.json @@ -0,0 +1 @@ +[{"page_no": 0, "size": {"width": 612.0, "height": 792.0}, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}, {"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 3, "label": "section_header", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}, "confidence": 0.9627318382263184, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.48276, "b": 290.02588, "coord_origin": "TOPLEFT"}, "confidence": 0.9869933128356934, "cells": [{"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 4, "label": "caption", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}, "confidence": 0.9477447271347046, "cells": [{"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 553.04495, "r": 477.48172000000005, "b": 669.48775, "coord_origin": "TOPLEFT"}, "confidence": 0.9862836599349976, "cells": [{"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 5, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.8646790981292725, "cells": [{"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 2, "label": "picture", "bbox": {"l": 134.92005920410156, "t": 304.890625, "r": 475.66351318359375, "b": 510.21826171875, "coord_origin": "TOPLEFT"}, "confidence": 0.9803217053413391, "cells": [], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "section_header", "id": 3, "page_no": 0, "cluster": {"id": 3, "label": "section_header", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}, "confidence": 0.9627318382263184, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figures Example"}, {"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.48276, "b": 290.02588, "coord_origin": "TOPLEFT"}, "confidence": 0.9869933128356934, "cells": [{"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 4, "page_no": 0, "cluster": {"id": 4, "label": "caption", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}, "confidence": 0.9477447271347046, "cells": [{"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 1: This is an example image."}, {"label": "text", "id": 1, "page_no": 0, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 553.04495, "r": 477.48172000000005, "b": 669.48775, "coord_origin": "TOPLEFT"}, "confidence": 0.9862836599349976, "cells": [{"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua."}, {"label": "page_footer", "id": 5, "page_no": 0, "cluster": {"id": 5, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.8646790981292725, "cells": [{"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "1"}, {"label": "picture", "id": 2, "page_no": 0, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 134.92005920410156, "t": 304.890625, "r": 475.66351318359375, "b": 510.21826171875, "coord_origin": "TOPLEFT"}, "confidence": 0.9803217053413391, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "body": [{"label": "section_header", "id": 3, "page_no": 0, "cluster": {"id": 3, "label": "section_header", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}, "confidence": 0.9627318382263184, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figures Example"}, {"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.48276, "b": 290.02588, "coord_origin": "TOPLEFT"}, "confidence": 0.9869933128356934, "cells": [{"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 4, "page_no": 0, "cluster": {"id": 4, "label": "caption", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}, "confidence": 0.9477447271347046, "cells": [{"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 1: This is an example image."}, {"label": "text", "id": 1, "page_no": 0, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 553.04495, "r": 477.48172000000005, "b": 669.48775, "coord_origin": "TOPLEFT"}, "confidence": 0.9862836599349976, "cells": [{"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua."}, {"label": "picture", "id": 2, "page_no": 0, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 134.92005920410156, "t": 304.890625, "r": 475.66351318359375, "b": 510.21826171875, "coord_origin": "TOPLEFT"}, "confidence": 0.9803217053413391, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "headers": [{"label": "page_footer", "id": 5, "page_no": 0, "cluster": {"id": 5, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.8646790981292725, "cells": [{"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "1"}]}}, {"page_no": 1, "size": {"width": 612.0, "height": 792.0}, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 127.85095000000013, "r": 477.48172000000005, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}, "confidence": 0.987092912197113, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 3, "label": "caption", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}, "confidence": 0.9494235515594482, "cells": [{"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 546.28195, "r": 477.48172000000005, "b": 674.67976, "coord_origin": "TOPLEFT"}, "confidence": 0.9874356985092163, "cells": [{"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 4, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.888852059841156, "cells": [{"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 2, "label": "picture", "bbox": {"l": 218.8155517578125, "t": 278.0154113769531, "r": 391.96246337890625, "b": 508.89410400390625, "coord_origin": "TOPLEFT"}, "confidence": 0.9837717413902283, "cells": [], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 1, "page_no": 1, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 127.85095000000013, "r": 477.48172000000005, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}, "confidence": 0.987092912197113, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 3, "page_no": 1, "cluster": {"id": 3, "label": "caption", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}, "confidence": 0.9494235515594482, "cells": [{"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 2: This is an example image."}, {"label": "text", "id": 0, "page_no": 1, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 546.28195, "r": 477.48172000000005, "b": 674.67976, "coord_origin": "TOPLEFT"}, "confidence": 0.9874356985092163, "cells": [{"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum."}, {"label": "page_footer", "id": 4, "page_no": 1, "cluster": {"id": 4, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.888852059841156, "cells": [{"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "2"}, {"label": "picture", "id": 2, "page_no": 1, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 218.8155517578125, "t": 278.0154113769531, "r": 391.96246337890625, "b": 508.89410400390625, "coord_origin": "TOPLEFT"}, "confidence": 0.9837717413902283, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "body": [{"label": "text", "id": 1, "page_no": 1, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 127.85095000000013, "r": 477.48172000000005, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}, "confidence": 0.987092912197113, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 3, "page_no": 1, "cluster": {"id": 3, "label": "caption", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}, "confidence": 0.9494235515594482, "cells": [{"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 2: This is an example image."}, {"label": "text", "id": 0, "page_no": 1, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 546.28195, "r": 477.48172000000005, "b": 674.67976, "coord_origin": "TOPLEFT"}, "confidence": 0.9874356985092163, "cells": [{"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum."}, {"label": "picture", "id": 2, "page_no": 1, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 218.8155517578125, "t": 278.0154113769531, "r": 391.96246337890625, "b": 508.89410400390625, "coord_origin": "TOPLEFT"}, "confidence": 0.9837717413902283, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "headers": [{"label": "page_footer", "id": 4, "page_no": 1, "cluster": {"id": 4, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.888852059841156, "cells": [{"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "2"}]}}] \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/picture_classification.doctags.txt b/tests/data/groundtruth/docling_v2/picture_classification.doctags.txt new file mode 100644 index 00000000..a86cbe7b --- /dev/null +++ b/tests/data/groundtruth/docling_v2/picture_classification.doctags.txt @@ -0,0 +1,15 @@ + +Figures Example +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +
+ +Figure 1: This is an example image. +
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. +
+ +Figure 2: This is an example image. +
+Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. +
\ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/picture_classification.json b/tests/data/groundtruth/docling_v2/picture_classification.json new file mode 100644 index 00000000..e80011b3 --- /dev/null +++ b/tests/data/groundtruth/docling_v2/picture_classification.json @@ -0,0 +1 @@ +{"schema_name": "DoclingDocument", "version": "1.0.0", "name": "picture_classification", "origin": {"mimetype": "application/pdf", "binary_hash": 6445357065749877499, "filename": "picture_classification.pdf", "uri": null}, "furniture": {"self_ref": "#/furniture", "parent": null, "children": [], "name": "_root_", "label": "unspecified"}, "body": {"self_ref": "#/body", "parent": null, "children": [{"cref": "#/texts/0"}, {"cref": "#/texts/1"}, {"cref": "#/texts/2"}, {"cref": "#/pictures/0"}, {"cref": "#/texts/3"}, {"cref": "#/texts/4"}, {"cref": "#/texts/5"}, {"cref": "#/texts/6"}, {"cref": "#/pictures/1"}, {"cref": "#/texts/7"}, {"cref": "#/texts/8"}], "name": "_root_", "label": "unspecified"}, "groups": [], "texts": [{"self_ref": "#/texts/0", "parent": {"cref": "#/body"}, "children": [], "label": "section_header", "prov": [{"page_no": 1, "bbox": {"l": 133.76800537109375, "t": 667.1912231445312, "r": 252.35513305664062, "b": 654.4518432617188, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 15]}], "orig": "Figures Example", "text": "Figures Example", "level": 1}, {"self_ref": "#/texts/1", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 133.76800537109375, "t": 642.3280639648438, "r": 477.4827575683594, "b": 501.97412109375, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 887]}], "orig": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.", "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"self_ref": "#/texts/2", "parent": {"cref": "#/body"}, "children": [], "label": "caption", "prov": [{"page_no": 1, "bbox": {"l": 226.89100646972656, "t": 262.86505126953125, "r": 384.35479736328125, "b": 254.0182647705078, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 35]}], "orig": "Figure 1: This is an example image.", "text": "Figure 1: This is an example image."}, {"self_ref": "#/texts/3", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 1, "bbox": {"l": 133.76800537109375, "t": 238.95504760742188, "r": 477.4817199707031, "b": 122.51225280761719, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 747]}], "orig": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua.", "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua."}, {"self_ref": "#/texts/4", "parent": {"cref": "#/body"}, "children": [], "label": "page_footer", "prov": [{"page_no": 1, "bbox": {"l": 303.13299560546875, "t": 96.27903747558594, "r": 308.1142883300781, "b": 87.43224334716797, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 1]}], "orig": "1", "text": "1"}, {"self_ref": "#/texts/5", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 2, "bbox": {"l": 133.76800537109375, "t": 664.1490478515625, "r": 477.4817199707031, "b": 523.7951049804688, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 887]}], "orig": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.", "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"self_ref": "#/texts/6", "parent": {"cref": "#/body"}, "children": [], "label": "caption", "prov": [{"page_no": 2, "bbox": {"l": 226.89100646972656, "t": 268.7890319824219, "r": 384.35479736328125, "b": 259.9422607421875, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 35]}], "orig": "Figure 2: This is an example image.", "text": "Figure 2: This is an example image."}, {"self_ref": "#/texts/7", "parent": {"cref": "#/body"}, "children": [], "label": "text", "prov": [{"page_no": 2, "bbox": {"l": 133.76800537109375, "t": 245.71804809570312, "r": 477.4817199707031, "b": 117.32023620605469, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 804]}], "orig": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum.", "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum."}, {"self_ref": "#/texts/8", "parent": {"cref": "#/body"}, "children": [], "label": "page_footer", "prov": [{"page_no": 2, "bbox": {"l": 303.13299560546875, "t": 96.27903747558594, "r": 308.1142883300781, "b": 87.43224334716797, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 1]}], "orig": "2", "text": "2"}], "pictures": [{"self_ref": "#/pictures/0", "parent": {"cref": "#/body"}, "children": [], "label": "picture", "prov": [{"page_no": 1, "bbox": {"l": 134.92005920410156, "t": 487.109375, "r": 475.66351318359375, "b": 281.78173828125, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 35]}], "captions": [{"cref": "#/texts/2"}], "references": [], "footnotes": [], "image": null, "annotations": []}, {"self_ref": "#/pictures/1", "parent": {"cref": "#/body"}, "children": [], "label": "picture", "prov": [{"page_no": 2, "bbox": {"l": 218.8155517578125, "t": 513.984619140625, "r": 391.96246337890625, "b": 283.10589599609375, "coord_origin": "BOTTOMLEFT"}, "charspan": [0, 35]}], "captions": [{"cref": "#/texts/6"}], "references": [], "footnotes": [], "image": null, "annotations": []}], "tables": [], "key_value_items": [], "pages": {"1": {"size": {"width": 612.0, "height": 792.0}, "image": null, "page_no": 1}, "2": {"size": {"width": 612.0, "height": 792.0}, "image": null, "page_no": 2}}} \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/picture_classification.md b/tests/data/groundtruth/docling_v2/picture_classification.md new file mode 100644 index 00000000..8e233a96 --- /dev/null +++ b/tests/data/groundtruth/docling_v2/picture_classification.md @@ -0,0 +1,17 @@ +## Figures Example + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. + +Figure 1: This is an example image. + + + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. + +Figure 2: This is an example image. + + + +Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/picture_classification.pages.json b/tests/data/groundtruth/docling_v2/picture_classification.pages.json new file mode 100644 index 00000000..744f54fb --- /dev/null +++ b/tests/data/groundtruth/docling_v2/picture_classification.pages.json @@ -0,0 +1 @@ +[{"page_no": 0, "size": {"width": 612.0, "height": 792.0}, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}, {"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 3, "label": "section_header", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}, "confidence": 0.9627318382263184, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.48276, "b": 290.02588, "coord_origin": "TOPLEFT"}, "confidence": 0.9869933128356934, "cells": [{"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 4, "label": "caption", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}, "confidence": 0.9477447271347046, "cells": [{"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 553.04495, "r": 477.48172000000005, "b": 669.48775, "coord_origin": "TOPLEFT"}, "confidence": 0.9862836599349976, "cells": [{"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 5, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.8646790981292725, "cells": [{"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 2, "label": "picture", "bbox": {"l": 134.92005920410156, "t": 304.890625, "r": 475.66351318359375, "b": 510.21826171875, "coord_origin": "TOPLEFT"}, "confidence": 0.9803217053413391, "cells": [], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "section_header", "id": 3, "page_no": 0, "cluster": {"id": 3, "label": "section_header", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}, "confidence": 0.9627318382263184, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figures Example"}, {"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.48276, "b": 290.02588, "coord_origin": "TOPLEFT"}, "confidence": 0.9869933128356934, "cells": [{"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 4, "page_no": 0, "cluster": {"id": 4, "label": "caption", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}, "confidence": 0.9477447271347046, "cells": [{"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 1: This is an example image."}, {"label": "text", "id": 1, "page_no": 0, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 553.04495, "r": 477.48172000000005, "b": 669.48775, "coord_origin": "TOPLEFT"}, "confidence": 0.9862836599349976, "cells": [{"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua."}, {"label": "page_footer", "id": 5, "page_no": 0, "cluster": {"id": 5, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.8646790981292725, "cells": [{"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "1"}, {"label": "picture", "id": 2, "page_no": 0, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 134.92005920410156, "t": 304.890625, "r": 475.66351318359375, "b": 510.21826171875, "coord_origin": "TOPLEFT"}, "confidence": 0.9803217053413391, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "body": [{"label": "section_header", "id": 3, "page_no": 0, "cluster": {"id": 3, "label": "section_header", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}, "confidence": 0.9627318382263184, "cells": [{"id": 0, "text": "Figures Example", "bbox": {"l": 133.76801, "t": 124.80877999999996, "r": 252.35513, "b": 137.54816000000005, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figures Example"}, {"label": "text", "id": 0, "page_no": 0, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.48276, "b": 290.02588, "coord_origin": "TOPLEFT"}, "confidence": 0.9869933128356934, "cells": [{"id": 1, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eir-", "bbox": {"l": 133.76801, "t": 149.67193999999995, "r": 477.47971, "b": 158.51873999999998, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "mod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam volup-", "bbox": {"l": 133.76801, "t": 161.62694999999997, "r": 477.4806500000001, "b": 170.47375, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "tua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd", "bbox": {"l": 133.76801, "t": 173.58196999999996, "r": 477.47571000000005, "b": 182.42877, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ip-", "bbox": {"l": 133.76801, "t": 185.53698999999995, "r": 477.47466999999995, "b": 194.38378999999998, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "sum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor", "bbox": {"l": 133.76801, "t": 197.49199999999996, "r": 477.47668, "b": 206.33880999999997, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero", "bbox": {"l": 133.76801, "t": 209.44701999999995, "r": 477.48068000000006, "b": 218.29381999999998, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "eos et accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 221.40301999999997, "r": 355.20874, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "Stet clita kasd gubergren,", "bbox": {"l": 362.60098, "t": 221.40301999999997, "r": 477.48276, "b": 230.24982, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 233.35802999999999, "r": 477.47772, "b": 242.20483000000002, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 245.31304999999998, "r": 477.47971, "b": 254.15985, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 257.26806999999997, "r": 477.47473, "b": 266.11487, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 269.22308, "r": 477.47571000000005, "b": 278.06989, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 281.17911, "r": 351.48471, "b": 290.02588, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 4, "page_no": 0, "cluster": {"id": 4, "label": "caption", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}, "confidence": 0.9477447271347046, "cells": [{"id": 14, "text": "Figure 1: This is an example image.", "bbox": {"l": 226.89101, "t": 529.13495, "r": 384.3548, "b": 537.98174, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 1: This is an example image."}, {"label": "text", "id": 1, "page_no": 0, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 553.04495, "r": 477.48172000000005, "b": 669.48775, "coord_origin": "TOPLEFT"}, "confidence": 0.9862836599349976, "cells": [{"id": 15, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 553.04495, "r": 477.47786999999994, "b": 561.89174, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 564.99995, "r": 477.47860999999995, "b": 573.84674, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 576.95496, "r": 477.47571000000005, "b": 585.80174, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 588.90996, "r": 477.47559, "b": 597.75674, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 600.86595, "r": 477.48169000000007, "b": 609.7127399999999, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 612.82095, "r": 477.48062, "b": 621.66774, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 624.7759599999999, "r": 477.48172000000005, "b": 633.62274, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 636.73096, "r": 477.47772, "b": 645.57774, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 648.68596, "r": 477.47971, "b": 657.53275, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua.", "bbox": {"l": 133.76801, "t": 660.64096, "r": 399.57816, "b": 669.48775, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua."}, {"label": "picture", "id": 2, "page_no": 0, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 134.92005920410156, "t": 304.890625, "r": 475.66351318359375, "b": 510.21826171875, "coord_origin": "TOPLEFT"}, "confidence": 0.9803217053413391, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "headers": [{"label": "page_footer", "id": 5, "page_no": 0, "cluster": {"id": 5, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.8646790981292725, "cells": [{"id": 25, "text": "1", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "1"}]}}, {"page_no": 1, "size": {"width": 612.0, "height": 792.0}, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}, {"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}, {"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}, {"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "predictions": {"layout": {"clusters": [{"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 127.85095000000013, "r": 477.48172000000005, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}, "confidence": 0.987092912197113, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 3, "label": "caption", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}, "confidence": 0.9494235515594482, "cells": [{"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 546.28195, "r": 477.48172000000005, "b": 674.67976, "coord_origin": "TOPLEFT"}, "confidence": 0.9874356985092163, "cells": [{"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 4, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.888852059841156, "cells": [{"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, {"id": 2, "label": "picture", "bbox": {"l": 218.8155517578125, "t": 278.0154113769531, "r": 391.96246337890625, "b": 508.89410400390625, "coord_origin": "TOPLEFT"}, "confidence": 0.9837717413902283, "cells": [], "children": []}]}, "tablestructure": {"table_map": {}}, "figures_classification": null, "equations_prediction": null}, "assembled": {"elements": [{"label": "text", "id": 1, "page_no": 1, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 127.85095000000013, "r": 477.48172000000005, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}, "confidence": 0.987092912197113, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 3, "page_no": 1, "cluster": {"id": 3, "label": "caption", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}, "confidence": 0.9494235515594482, "cells": [{"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 2: This is an example image."}, {"label": "text", "id": 0, "page_no": 1, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 546.28195, "r": 477.48172000000005, "b": 674.67976, "coord_origin": "TOPLEFT"}, "confidence": 0.9874356985092163, "cells": [{"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum."}, {"label": "page_footer", "id": 4, "page_no": 1, "cluster": {"id": 4, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.888852059841156, "cells": [{"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "2"}, {"label": "picture", "id": 2, "page_no": 1, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 218.8155517578125, "t": 278.0154113769531, "r": 391.96246337890625, "b": 508.89410400390625, "coord_origin": "TOPLEFT"}, "confidence": 0.9837717413902283, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "body": [{"label": "text", "id": 1, "page_no": 1, "cluster": {"id": 1, "label": "text", "bbox": {"l": 133.76801, "t": 127.85095000000013, "r": 477.48172000000005, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}, "confidence": 0.987092912197113, "cells": [{"id": 0, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 127.85095000000013, "r": 477.47786999999994, "b": 136.69775000000004, "coord_origin": "TOPLEFT"}}, {"id": 1, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 139.80597, "r": 477.47860999999995, "b": 148.65277000000003, "coord_origin": "TOPLEFT"}}, {"id": 2, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 151.76099, "r": 477.47571000000005, "b": 160.60779000000002, "coord_origin": "TOPLEFT"}}, {"id": 3, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 163.716, "r": 477.47559, "b": 172.56281, "coord_origin": "TOPLEFT"}}, {"id": 4, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 175.67102, "r": 477.48169000000007, "b": 184.51782000000003, "coord_origin": "TOPLEFT"}}, {"id": 5, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 187.62701000000004, "r": 477.48062, "b": 196.47382000000005, "coord_origin": "TOPLEFT"}}, {"id": 6, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 199.58203000000003, "r": 477.48172000000005, "b": 208.42882999999995, "coord_origin": "TOPLEFT"}}, {"id": 7, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 211.53705000000002, "r": 477.47772, "b": 220.38385000000005, "coord_origin": "TOPLEFT"}}, {"id": 8, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 223.49207, "r": 477.47971, "b": 232.33887000000004, "coord_origin": "TOPLEFT"}}, {"id": 9, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 235.44708000000003, "r": 477.47473, "b": 244.29387999999994, "coord_origin": "TOPLEFT"}}, {"id": 10, "text": "accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea", "bbox": {"l": 133.76801, "t": 247.40210000000002, "r": 477.47571000000005, "b": 256.24890000000005, "coord_origin": "TOPLEFT"}}, {"id": 11, "text": "takimata sanctus est Lorem ipsum dolor sit amet.", "bbox": {"l": 133.76801, "t": 259.35808999999995, "r": 351.48471, "b": 268.20489999999995, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet."}, {"label": "caption", "id": 3, "page_no": 1, "cluster": {"id": 3, "label": "caption", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}, "confidence": 0.9494235515594482, "cells": [{"id": 12, "text": "Figure 2: This is an example image.", "bbox": {"l": 226.89101, "t": 523.21097, "r": 384.3548, "b": 532.05774, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Figure 2: This is an example image."}, {"label": "text", "id": 0, "page_no": 1, "cluster": {"id": 0, "label": "text", "bbox": {"l": 133.76801, "t": 546.28195, "r": 477.48172000000005, "b": 674.67976, "coord_origin": "TOPLEFT"}, "confidence": 0.9874356985092163, "cells": [{"id": 13, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy", "bbox": {"l": 148.71201, "t": 546.28195, "r": 477.47786999999994, "b": 555.12874, "coord_origin": "TOPLEFT"}}, {"id": 14, "text": "eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam", "bbox": {"l": 133.76801, "t": 558.23695, "r": 477.47860999999995, "b": 567.08374, "coord_origin": "TOPLEFT"}}, {"id": 15, "text": "voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita", "bbox": {"l": 133.76801, "t": 570.19196, "r": 477.47571000000005, "b": 579.03874, "coord_origin": "TOPLEFT"}}, {"id": 16, "text": "kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem", "bbox": {"l": 133.76801, "t": 582.14696, "r": 477.47559, "b": 590.99374, "coord_origin": "TOPLEFT"}}, {"id": 17, "text": "ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod", "bbox": {"l": 133.76801, "t": 594.10196, "r": 477.48169000000007, "b": 602.94875, "coord_origin": "TOPLEFT"}}, {"id": 18, "text": "tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At", "bbox": {"l": 133.76801, "t": 606.05696, "r": 477.48062, "b": 614.90375, "coord_origin": "TOPLEFT"}}, {"id": 19, "text": "vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren,", "bbox": {"l": 133.76801, "t": 618.01295, "r": 477.48172000000005, "b": 626.85974, "coord_origin": "TOPLEFT"}}, {"id": 20, "text": "no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor", "bbox": {"l": 133.76801, "t": 629.96796, "r": 477.47772, "b": 638.81474, "coord_origin": "TOPLEFT"}}, {"id": 21, "text": "sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt", "bbox": {"l": 133.76801, "t": 641.92296, "r": 477.47971, "b": 650.76974, "coord_origin": "TOPLEFT"}}, {"id": 22, "text": "ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et", "bbox": {"l": 133.76801, "t": 653.87796, "r": 477.47473, "b": 662.72475, "coord_origin": "TOPLEFT"}}, {"id": 23, "text": "accusam et justo duo dolores et ea rebum.", "bbox": {"l": 133.76801, "t": 665.83296, "r": 318.01736, "b": 674.67976, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum."}, {"label": "picture", "id": 2, "page_no": 1, "cluster": {"id": 2, "label": "picture", "bbox": {"l": 218.8155517578125, "t": 278.0154113769531, "r": 391.96246337890625, "b": 508.89410400390625, "coord_origin": "TOPLEFT"}, "confidence": 0.9837717413902283, "cells": [], "children": []}, "text": "", "annotations": [], "provenance": null, "predicted_class": null, "confidence": null}], "headers": [{"label": "page_footer", "id": 4, "page_no": 1, "cluster": {"id": 4, "label": "page_footer", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}, "confidence": 0.888852059841156, "cells": [{"id": 24, "text": "2", "bbox": {"l": 303.133, "t": 695.720963, "r": 308.11429, "b": 704.567757, "coord_origin": "TOPLEFT"}}], "children": []}, "text": "2"}]}}] \ No newline at end of file