mirror of
https://github.com/open-webui/open-webui.git
synced 2026-07-16 14:39:31 -05:00
[GH-ISSUE #24321] issue: PDF in Knowledge garbled #123574
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @AIWintermuteAI on GitHub (May 2, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/24321
Check Existing Issues
Installation Method
Docker
Open WebUI Version
0.9.2
Ollama Version (if applicable)
No response
Operating System
Ubuntu 24.04
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
See the text when pressing on uploaded pdf in Knowledge.
Actual Behavior
Nonsense on pdf preview
Steps to Reproduce
Upload this pdf to knowledge
Click on it to preview
Creatine is a Conditionally Essential Nutrient in Chronic Kidney Disease_ A Hypothesis and Narrative Literature Review - nutrients-11-01044.pdf
Logs & Screenshots
Additional Information
No response
@owui-terminator[bot] commented on GitHub (May 2, 2026):
🔍 Similar Issues Found
I found some existing issues that might be related. Please check if any of these are duplicates or contain helpful solutions:
#24149 issue: PDFViewer is rendering all PDF's as image - Search on PDF's gone
by athoik ·
bug#22458 issue: PDF parsing with /filter error
by MarceloMassarente ·
bug#21726 issue: RAG duplication when view_knowledge_file tool is used
by susmitds ·
bug#21567 issue: Web retrieval cannot load PDF documents
by erhhung ·
bug#14715 issue: Garbled text appears when exporting to PDF
by gongshaojie12 ·
bug💡 If this is a duplicate, consider closing it and adding details to the existing issue.
This comment was generated automatically. React with 👍 if helpful, 👎 if not.
@AIWintermuteAI commented on GitHub (May 3, 2026):
Thanks bot, but no, none of these are similar.
@Classic298 commented on GitHub (May 3, 2026):
What is your document extraction engine
@AIWintermuteAI commented on GitHub (May 3, 2026):
Default

It looks like it might depend on PDF file, since this particular one has issue, while another one does not.
@tjbck commented on GitHub (May 4, 2026):
Parser issue, we'd recommend swapping out to a different content extraction engine.