scriptoriumadmin/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-10-11 03:38:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

fix: Docling citations show the wrong page number when a PDF has blank pages (#32203)

Browse source 
With the Docling engine, a blank page in a PDF threw off the page number of everything after it, so citations showed the wrong page and opened the file at the wrong place. Page numbers now come from the page Docling reports for each piece of text. Files that were already uploaded keep their old page numbers until they are reindexed or uploaded again.

Fixes #32201
This commit is contained in:
Classic298 2026-10-10 19:39:46 +02:00 • committed by GitHub
parent fde0a85369
commit 2526c8e603
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 15 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

16
backend/open_webui/retrieval/loaders/main.py
View file

@ -281,6 +281,7 @@ class DoclingLoader:
data={
'image_export_mode': 'placeholder',
'md_page_break_placeholder': page_break_marker,
'to_formats': ['md', 'json'],
# Keep Docling params as user-provided form values. Encoding nested
# values here would make Open WebUI responsible for Docling's API
# quirks and could break when Docling changes its form contract.
@ -306,9 +307,22 @@ class DoclingLoader:
metadata = {'Content-Type': self.mime_type} if self.mime_type else {}
if page_break_marker in md_content:
pages = md_content.split(page_break_marker)
json_content = document_data.get('json_content') or {}
# Docling only marks page changes, so blank pages leave no break; take page numbers from its JSON
page_indices = sorted(
{
item['prov'][0]['page_no'] - 1
for key in ('texts', 'tables', 'pictures', 'key_value_items', 'form_items')
for item in json_content.get(key, [])
if item.get('content_layer') == 'body' and item.get('prov')
}
)
if len(page_indices) != len(pages):
page_indices = range(len(pages))
documents = [
Document(page_content=page.strip(), metadata={**metadata, 'page': page_idx})
for page_idx, page in enumerate(md_content.split(page_break_marker))
for page_idx, page in zip(page_indices, pages)
if page.strip()
]
if documents: