Skip to content

feat : Markdown OCR text inlining (force?) #390

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 3 commits into
base: main
Choose a base branch
from
+8 −0
Draft

feat : Markdown OCR text inlining (force?) #390

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
07b2703
Add INLINE option for image handling
ExtReMLapin Sep 23, 2025
af928d4
Allow markdown serializer to inline OCR text instead of images placeh…
ExtReMLapin Sep 23, 2025
61b0ae9
Merge pull request #1 from ExtReMLapin/patch-2
ExtReMLapin Sep 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions docling_core/transforms/serializer/markdown.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -421,6 +421,7 @@ def _serialize_image_part(
doc: DoclingDocument,
image_mode: ImageRefMode,
image_placeholder: str,
image_join_text: str = "\n",
**kwargs: Any,
) -> SerializationResult:
error_response = (
Expand Down Expand Up @@ -457,6 +458,12 @@ def _serialize_image_part(
text_res = image_placeholder
else:
text_res = f"![Image]({str(item.image.uri)})"
elif image_mode == ImageRefMode.INLINE:
total_text = []
for item, level in doc.iterate_items(root=item, traverse_pictures=True):
if isinstance(item, TextItem):
total_text.append(item.text)
text_res = image_join_text.join(total_text) if total_text else image_placeholder
else:
text_res = image_placeholder

Expand Down
1 change: 1 addition & 0 deletions docling_core/types/doc/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ class ImageRefMode(str, Enum):
PLACEHOLDER = "placeholder" # just a place-holder
EMBEDDED = "embedded" # embed the image as a base64
REFERENCED = "referenced" # reference the image via uri
INLINE = "inline" # inline the image OCR content directly in the document


class CoordOrigin(str, Enum):
Expand Down