Mirrors/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-09 11:59:01 +02:00
Code Issues Packages Projects Releases Wiki Activity

refac

Browse Source 
Co-Authored-By: Jannik S. <jannik@streidl.dev>
This commit is contained in:
Timothy Jaeryang Baek
2026-06-29 13:47:39 -05:00
parent 9af700cc4f
commit caadfdec0b
1 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
backend/open_webui/retrieval/loaders/main.py
View File

@@ -188,6 +188,7 @@ class DoclingLoader:
self.params = params or {}
def load(self) -> list[Document]:
page_break_marker = '\f'
with open(self.file_path, 'rb') as f:
headers = {}
if self.api_key:
@@ -204,6 +205,7 @@ class DoclingLoader:
},
data={
'image_export_mode': 'placeholder',
'md_page_break_placeholder': page_break_marker,
**self.params,
},
headers=headers,
@@ -212,9 +214,19 @@ class DoclingLoader:
if r.ok:
result = r.json()
document_data = result.get('document', {})
text = document_data.get('md_content', '<No text content found>')
md_content = document_data.get('md_content', '')
text = md_content or '<No text content found>'
metadata = {'Content-Type': self.mime_type} if self.mime_type else {}
if page_break_marker in md_content:
documents = [
Document(page_content=page.strip(), metadata={**metadata, 'page': page_idx})
for page_idx, page in enumerate(md_content.split(page_break_marker))
if page.strip()
]
if documents:
log.debug('Docling extracted text: %s', text)
return documents
log.debug('Docling extracted text: %s', text)
return [Document(page_content=text, metadata=metadata)]