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

preparing to migrate to new doctags deserializer

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-03-17 13:29:07 +01:00
parent 46dc2e621f
commit 8e54299eac
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docling/pipeline/vlm_pipeline.py
View File

@ -9,6 +9,7 @@ from pathlib import Path
from typing import Optional from typing import Optional
from docling_core.types import DoclingDocument from docling_core.types import DoclingDocument
from docling_core.types.doc.document import DocTagsDocument
from docling_core.types.doc import ( from docling_core.types.doc import (
BoundingBox, BoundingBox,
DocItem, DocItem,
@ -108,6 +109,11 @@ class VlmPipeline(PaginatedPipeline):
== ResponseFormat.DOCTAGS == ResponseFormat.DOCTAGS
): ):
conv_res.document = self._turn_tags_into_doc(conv_res.pages) conv_res.document = self._turn_tags_into_doc(conv_res.pages)
# doctags_doc = DocTagsDocument.from_doctags_and_image_pairs([doctags], [image])
# 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)
elif ( elif (
self.pipeline_options.vlm_options.response_format self.pipeline_options.vlm_options.response_format
== ResponseFormat.MARKDOWN == ResponseFormat.MARKDOWN