ti.sil/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-18 15:25:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #13085 from ayan4m1/fix/tika-image-ocr

Browse source 
fix: pass extractInlineImages header to Tika if PDF_EXTRACT_IMAGES is true
This commit is contained in:
Tim Jaeryang Baek 2025-05-02 03:47:51 -07:00 committed by GitHub
commit 7d184c3a14
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
backend/open_webui/retrieval/loaders/main.py
View file

@ -99,6 +99,9 @@ class TikaLoader:
else: else:
headers = {} headers = {}
if self.kwargs.get("PDF_EXTRACT_IMAGES") == True:
headers['X-Tika-PDFextractInlineImages'] = 'true'
endpoint = self.url endpoint = self.url
if not endpoint.endswith("/"): if not endpoint.endswith("/"):
endpoint += "/" endpoint += "/"