mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-30 14:04:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added support for force_backend_text parameter

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-03-18 10:14:16 +01:00
parent 5c62f88175
commit 5dffd10eae
1 changed files with 35 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
docling/pipeline/vlm_pipeline.py
View File

@ -12,6 +12,7 @@ from docling_core.types.doc import ( # DocItemLabel,; DoclingDocument,; GroupLa
DocItem,
ImageRef,
PictureItem,
TextItem,
)
from docling_core.types.doc.document import DocTagsDocument
from docling_core.types.doc.tokens import DocumentToken, TableToken
@ -87,6 +88,19 @@ class VlmPipeline(PaginatedPipeline):
return page
def extract_text_from_backend(self, page: Page, bbox: BoundingBox | None) -> str:
# Convert bounding box normalized to 0-100 into page coordinates for cropping
text = ""
if bbox:
if page.size:
# bbox.l = bbox.l * page.size.width
# bbox.t = bbox.t * page.size.height
# bbox.r = bbox.r * page.size.width
# bbox.b = bbox.b * page.size.height
if page._backend:
text = page._backend.get_text_in_rect(bbox)
return text
def _assemble_document(self, conv_res: ConversionResult) -> ConversionResult:
with TimeRecorder(conv_res, "doc_assemble", scope=ProfilingScope.DOCUMENT):
@ -112,9 +126,27 @@ class VlmPipeline(PaginatedPipeline):
doctags_list_c, image_list_c
)
conv_res.document.load_from_doctags(doctags_doc)
# USE THIS TO FORCE BACKEND TEXT
# if self.force_backend_text:
# text_content = extract_text_from_backend(page, bbox)
# If forced backend text, replace model predicted text with backend one
if page.size:
if self.force_backend_text:
scale = self.pipeline_options.images_scale
for element, _level in conv_res.document.iterate_items():
if (
not isinstance(element, TextItem)
or len(element.prov) == 0
):
continue
crop_bbox = (
element.prov[0]
.bbox.scaled(scale=scale)
.to_top_left_origin(
page_height=page.size.height * scale
)
)
txt = self.extract_text_from_backend(page, crop_bbox)
element.text = txt
element.orig = txt
elif (
self.pipeline_options.vlm_options.response_format
== ResponseFormat.MARKDOWN