mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Removed special html code wrapping when exporting to docling document, cleaned up comments

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-02-13 10:29:37 +01:00
parent b12f5ba80f
commit b0935daec4
1 changed files with 1 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docling/pipeline/vlm_pipeline.py
View File

@ -89,14 +89,7 @@ class VlmPipeline(PaginatedPipeline):
"code": "lightblue", "code": "lightblue",
} }
""" self.keep_images = (
if pipeline_options.artifacts_path is None:
self.artifacts_path = self.download_models_hf()
else:
self.artifacts_path = Path(pipeline_options.artifacts_path)
"""
keep_images = (
self.pipeline_options.generate_page_images self.pipeline_options.generate_page_images
or self.pipeline_options.generate_picture_images or self.pipeline_options.generate_picture_images
or self.pipeline_options.generate_table_images or self.pipeline_options.generate_table_images
@ -429,9 +422,6 @@ class VlmPipeline(PaginatedPipeline):
text_content = extract_text_from_backend(page, bbox) text_content = extract_text_from_backend(page, bbox)
else: else:
text_content = extract_inner_text(full_chunk) text_content = extract_inner_text(full_chunk)
# If it's code, wrap it with <pre><code> tags
if doc_label == DocItemLabel.CODE:
text_content = f"<pre><code>{text_content}</code></pre>"
doc.add_text( doc.add_text(
label=doc_label, label=doc_label,
text=text_content, text=text_content,
@ -454,6 +444,3 @@ class VlmPipeline(PaginatedPipeline):
@classmethod @classmethod
def is_backend_supported(cls, backend: AbstractDocumentBackend): def is_backend_supported(cls, backend: AbstractDocumentBackend):
return isinstance(backend, PdfDocumentBackend) return isinstance(backend, PdfDocumentBackend)
# def _turn_tags_into_doc(self, document_tags):
# return DoclingDocument()