mirror of
https://github.com/open-webui/open-webui.git
synced 2026-05-06 19:08:59 -05:00
error when uploading files to chat #2956
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#2956
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 @mazierovictor on GitHub (Dec 8, 2024).
Installation Method = DOCKER
[Describe the method you used to install the project, e.g., git clone, Docker, pip, etc.]
Environment = Open WebUI Versão v0.4.8
Confirmation:
Expected Behavior:
The behavior I would like is to be able to attach any PDF and be able to interact with it without any problems. Plus, you can attach PDFs as a knowledge base without error.
Actual Behavior:
[Describe what actually happened.]
Description
Bug Summary:
[Provide a brief but clear summary of the bug]
Reproduction Details
Steps to Reproduce:
When attaching a PDF file with more than 20 pages to interact with, I get the following error:
"unable to reshape array of size 20101 to format (763,1493,newaxis)"
And, due to the error I can't interact with the PDF with more than 20 pages..
Still, if I try to use the file as a knowledge base it also gives the error.
Logs and Screenshots
Additional Information
[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]
Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
@mazierovictor commented on GitHub (Dec 8, 2024):
Discovering that the error is caused because the PDF has images and the Extract Images (OCR) option is active, when deactivating the option the PDF is processed without any error, however no images are considered, which is not the expected behavior.