feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905)
* Add DoclingParseV3 backend implementation Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use docling-core with docling-parse types Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes and test updates Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset tests Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test units Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add back DoclingParse v1 backend, pipeline options Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update locks Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update docling-core to 2.22.0 Update dependency library docling-core to latest release 2.22.0 Fix regression tests and ground truth files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * Ground-truth files updated Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update tests, use TextCell.from_ocr property Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Text fixes, new test data Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Rename docling backend to v4 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Test all backends, fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset all tests to use docling-parse v1 for now Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for DPv4 backend init, better test coverage Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * test_input_doc use default backend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
@@ -5,6 +5,7 @@ from typing import Iterable, Optional, Union
|
||||
|
||||
import numpy
|
||||
from docling_core.types.doc import BoundingBox, DocItemLabel, TableCell
|
||||
from docling_core.types.doc.page import BoundingRectangle
|
||||
from docling_ibm_models.tableformer.data_management.tf_predictor import TFPredictor
|
||||
from PIL import ImageDraw
|
||||
|
||||
@@ -129,7 +130,7 @@ class TableStructureModel(BasePageModel):
|
||||
draw.rectangle([(x0, y0), (x1, y1)], outline="red")
|
||||
|
||||
for cell in table_element.cluster.cells:
|
||||
x0, y0, x1, y1 = cell.bbox.as_tuple()
|
||||
x0, y0, x1, y1 = cell.rect.to_bounding_box().as_tuple()
|
||||
x0 *= scale_x
|
||||
x1 *= scale_x
|
||||
y0 *= scale_x
|
||||
@@ -223,11 +224,19 @@ class TableStructureModel(BasePageModel):
|
||||
# Only allow non empty stings (spaces) into the cells of a table
|
||||
if len(c.text.strip()) > 0:
|
||||
new_cell = copy.deepcopy(c)
|
||||
new_cell.bbox = new_cell.bbox.scaled(
|
||||
scale=self.scale
|
||||
new_cell.rect = BoundingRectangle.from_bounding_box(
|
||||
new_cell.rect.to_bounding_box().scaled(
|
||||
scale=self.scale
|
||||
)
|
||||
)
|
||||
|
||||
tokens.append(new_cell.model_dump())
|
||||
tokens.append(
|
||||
{
|
||||
"id": new_cell.index,
|
||||
"text": new_cell.text,
|
||||
"bbox": new_cell.rect.to_bounding_box().model_dump(),
|
||||
}
|
||||
)
|
||||
page_input["tokens"] = tokens
|
||||
|
||||
tf_output = self.tf_predictor.multi_table_predict(
|
||||
|
||||
Reference in New Issue
Block a user