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
Utilizo a API embedding da OpenAI
Operating System: Ubuntu
Browser (if applicable): Chrome
Confirmation:
[x ] I have read and followed all the instructions provided in the README.md.
[x ] I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
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!
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
- **Utilizo a API embedding da OpenAI**
- **Operating System:** Ubuntu
- **Browser (if applicable):** Chrome
**Confirmation:**
- [x ] I have read and followed all the instructions provided in the README.md.
- [x ] I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
## 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!
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.
@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.
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
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.