github-starred/open-webui
2
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2026-07-16 14:39:31 -05:00
Code Issues 2.4k Packages Projects Releases 129 Wiki Activity

[GH-ISSUE #24321] issue: PDF in Knowledge garbled #58931

New Issue
Closed
opened 2026-05-06 00:29:28 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-06 00:29:28 -05:00
Owner
Copy Link

Originally created by @AIWintermuteAI on GitHub (May 2, 2026).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/24321

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!).
  • I am using the latest version of Open WebUI.

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

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

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

Image

Additional Information

No response

Originally created by @AIWintermuteAI on GitHub (May 2, 2026). Original GitHub issue: https://github.com/open-webui/open-webui/issues/24321 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I have also searched in the CLOSED issues AND CLOSED discussions and found no related items (your issue might already be addressed on the development branch!). - [x] I am using the latest version of Open WebUI. ### 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 - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### 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](https://github.com/user-attachments/files/27308212/Creatine.is.a.Conditionally.Essential.Nutrient.in.Chronic.Kidney.Disease_.A.Hypothesis.and.Narrative.Literature.Review.-.nutrients-11-01044.pdf) ### Logs & Screenshots <img width="1361" height="827" alt="Image" src="https://github.com/user-attachments/assets/97900e8e-f1fb-4537-9ec1-540e96b32998" /> ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-06 00:29:28 -05:00
GiteaMirror commented 2026-05-06 00:29:32 -05:00
Author
Owner
Copy Link

@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:

  1. #24149 issue: PDFViewer is rendering all PDF's as image - Search on PDF's gone
    by athoik · bug

  2. #22458 issue: PDF parsing with /filter error
    by MarceloMassarente · bug

  3. #21726 issue: RAG duplication when view_knowledge_file tool is used
    by susmitds · bug

  4. #21567 issue: Web retrieval cannot load PDF documents
    by erhhung · bug

  5. #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.

<!-- gh-comment-id:4364683505 --> @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: 1. [#24149](https://github.com/open-webui/open-webui/issues/24149) **issue: PDFViewer is rendering all PDF's as image - Search on PDF's gone** *by athoik · `bug`* 2. [#22458](https://github.com/open-webui/open-webui/issues/22458) **issue: PDF parsing with /filter error** *by MarceloMassarente · `bug`* 3. [#21726](https://github.com/open-webui/open-webui/issues/21726) **issue: RAG duplication when view_knowledge_file tool is used** *by susmitds · `bug`* 4. [#21567](https://github.com/open-webui/open-webui/issues/21567) **issue: Web retrieval cannot load PDF documents** *by erhhung · `bug`* 5. [#14715](https://github.com/open-webui/open-webui/issues/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.
GiteaMirror commented 2026-05-06 00:29:32 -05:00
Author
Owner
Copy Link

@AIWintermuteAI commented on GitHub (May 3, 2026):

Thanks bot, but no, none of these are similar.

<!-- gh-comment-id:4365819894 --> @AIWintermuteAI commented on GitHub (May 3, 2026): Thanks bot, but no, none of these are similar.
GiteaMirror commented 2026-05-06 00:29:33 -05:00
Author
Owner
Copy Link

@Classic298 commented on GitHub (May 3, 2026):

What is your document extraction engine

<!-- gh-comment-id:4365873983 --> @Classic298 commented on GitHub (May 3, 2026): What is your document extraction engine
GiteaMirror commented 2026-05-06 00:29:34 -05:00
Author
Owner
Copy Link

@AIWintermuteAI commented on GitHub (May 3, 2026):

Default
Image
It looks like it might depend on PDF file, since this particular one has issue, while another one does not.

<!-- gh-comment-id:4365886568 --> @AIWintermuteAI commented on GitHub (May 3, 2026): Default <img width="1464" height="917" alt="Image" src="https://github.com/user-attachments/assets/a3c2dcb8-f9b0-4e41-9e9f-5cf2701ef1d7" /> It looks like it might depend on PDF file, since this particular one has issue, while another one does not.
GiteaMirror commented 2026-05-06 00:29:35 -05:00
Author
Owner
Copy Link

@tjbck commented on GitHub (May 4, 2026):

Parser issue, we'd recommend swapping out to a different content extraction engine.

<!-- gh-comment-id:4373036294 --> @tjbck commented on GitHub (May 4, 2026): Parser issue, we'd recommend swapping out to a different content extraction engine.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
confirmed
confirmed issue
core
documentation
enhancement
good first issue
help wanted
non-core
pull-request
Mirrored from GitHub Pull Request
 python
question
testing wanted
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#58931
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?