mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-11 06:08:09 +00:00
311 lines
9.0 KiB
JSON
Vendored
311 lines
9.0 KiB
JSON
Vendored
[
|
|
{
|
|
"page_no": 0,
|
|
"size": {
|
|
"width": 595.2,
|
|
"height": 841.92
|
|
},
|
|
"predictions": {
|
|
"layout": {
|
|
"clusters": [
|
|
{
|
|
"id": 0,
|
|
"label": "text",
|
|
"bbox": {
|
|
"l": 71.03,
|
|
"t": 75.97,
|
|
"r": 505.7,
|
|
"b": 154.06,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"confidence": 0.862,
|
|
"cells": [
|
|
{
|
|
"index": 0,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 72.73,
|
|
"r_y0": 96.34,
|
|
"r_x1": 505.27,
|
|
"r_y1": 96.34,
|
|
"r_x2": 505.27,
|
|
"r_y2": 75.97,
|
|
"r_x3": 72.73,
|
|
"r_y3": 75.97,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "Docling bundles PDF document conversion to",
|
|
"orig": "Docling bundles PDF document conversion to",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.998,
|
|
"from_ocr": true
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 71.03,
|
|
"r_y0": 123.92,
|
|
"r_x1": 505.7,
|
|
"r_y1": 123.92,
|
|
"r_x2": 505.7,
|
|
"r_y2": 102.7,
|
|
"r_x3": 71.03,
|
|
"r_y3": 102.7,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "JSON and Markdown in an easy self contained",
|
|
"orig": "JSON and Markdown in an easy self contained",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.995,
|
|
"from_ocr": true
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 71.03,
|
|
"r_y0": 154.06,
|
|
"r_x1": 152.64,
|
|
"r_y1": 154.06,
|
|
"r_x2": 152.64,
|
|
"r_y2": 130.29,
|
|
"r_x3": 71.03,
|
|
"r_y3": 130.29,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.998,
|
|
"from_ocr": true
|
|
}
|
|
],
|
|
"children": []
|
|
}
|
|
]
|
|
},
|
|
"tablestructure": {
|
|
"table_map": {}
|
|
},
|
|
"figures_classification": null,
|
|
"equations_prediction": null,
|
|
"vlm_response": null
|
|
},
|
|
"assembled": {
|
|
"elements": [
|
|
{
|
|
"label": "text",
|
|
"id": 0,
|
|
"page_no": 0,
|
|
"cluster": {
|
|
"id": 0,
|
|
"label": "text",
|
|
"bbox": {
|
|
"l": 71.03,
|
|
"t": 75.97,
|
|
"r": 505.7,
|
|
"b": 154.06,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"confidence": 0.862,
|
|
"cells": [
|
|
{
|
|
"index": 0,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 72.73,
|
|
"r_y0": 96.34,
|
|
"r_x1": 505.27,
|
|
"r_y1": 96.34,
|
|
"r_x2": 505.27,
|
|
"r_y2": 75.97,
|
|
"r_x3": 72.73,
|
|
"r_y3": 75.97,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "Docling bundles PDF document conversion to",
|
|
"orig": "Docling bundles PDF document conversion to",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.998,
|
|
"from_ocr": true
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 71.03,
|
|
"r_y0": 123.92,
|
|
"r_x1": 505.7,
|
|
"r_y1": 123.92,
|
|
"r_x2": 505.7,
|
|
"r_y2": 102.7,
|
|
"r_x3": 71.03,
|
|
"r_y3": 102.7,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "JSON and Markdown in an easy self contained",
|
|
"orig": "JSON and Markdown in an easy self contained",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.995,
|
|
"from_ocr": true
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 71.03,
|
|
"r_y0": 154.06,
|
|
"r_x1": 152.64,
|
|
"r_y1": 154.06,
|
|
"r_x2": 152.64,
|
|
"r_y2": 130.29,
|
|
"r_x3": 71.03,
|
|
"r_y3": 130.29,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.998,
|
|
"from_ocr": true
|
|
}
|
|
],
|
|
"children": []
|
|
},
|
|
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
|
|
}
|
|
],
|
|
"body": [
|
|
{
|
|
"label": "text",
|
|
"id": 0,
|
|
"page_no": 0,
|
|
"cluster": {
|
|
"id": 0,
|
|
"label": "text",
|
|
"bbox": {
|
|
"l": 71.03,
|
|
"t": 75.97,
|
|
"r": 505.7,
|
|
"b": 154.06,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"confidence": 0.862,
|
|
"cells": [
|
|
{
|
|
"index": 0,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 72.73,
|
|
"r_y0": 96.34,
|
|
"r_x1": 505.27,
|
|
"r_y1": 96.34,
|
|
"r_x2": 505.27,
|
|
"r_y2": 75.97,
|
|
"r_x3": 72.73,
|
|
"r_y3": 75.97,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "Docling bundles PDF document conversion to",
|
|
"orig": "Docling bundles PDF document conversion to",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.998,
|
|
"from_ocr": true
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 71.03,
|
|
"r_y0": 123.92,
|
|
"r_x1": 505.7,
|
|
"r_y1": 123.92,
|
|
"r_x2": 505.7,
|
|
"r_y2": 102.7,
|
|
"r_x3": 71.03,
|
|
"r_y3": 102.7,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "JSON and Markdown in an easy self contained",
|
|
"orig": "JSON and Markdown in an easy self contained",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.995,
|
|
"from_ocr": true
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 71.03,
|
|
"r_y0": 154.06,
|
|
"r_x1": 152.64,
|
|
"r_y1": 154.06,
|
|
"r_x2": 152.64,
|
|
"r_y2": 130.29,
|
|
"r_x3": 71.03,
|
|
"r_y3": 130.29,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 0.998,
|
|
"from_ocr": true
|
|
}
|
|
],
|
|
"children": []
|
|
},
|
|
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
|
|
}
|
|
],
|
|
"headers": []
|
|
},
|
|
"parsed_page": null
|
|
}
|
|
] |