[GH-ISSUE #5623] [BUG]: Can not upload scanned PDF file #5200

Closed
opened 2026-06-05 14:52:35 -04:00 by yindo · 3 comments
Owner

Originally created by @kklldog on GitHub (May 13, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5623

How are you running AnythingLLM?

Docker (local)

What happened?

hi guys,
When I try to upload a scanned PDF file to space but I show error message:

No text content found in xxx.pdf

I saw the release note from 1.7.4 version that already support to OCR scanned pdf file.

Is there any special environment need be set or this is a bug?

Are there known steps to reproduce?

No response

LLM Provider & Model (if applicable)

Azure OpenAI gpt5.4

Embedder Provider & Model (if applicable)

embedding-3-large

Originally created by @kklldog on GitHub (May 13, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5623 ### How are you running AnythingLLM? Docker (local) ### What happened? hi guys, When I try to upload a scanned PDF file to space but I show error message: **No text content found in xxx.pdf** I saw the release note from 1.7.4 version that already support to OCR scanned pdf file. Is there any special environment need be set or this is a bug? ### Are there known steps to reproduce? _No response_ ### LLM Provider & Model (if applicable) Azure OpenAI gpt5.4 ### Embedder Provider & Model (if applicable) embedding-3-large
yindo added the possible bug label 2026-06-05 14:52:35 -04:00
yindo closed this issue 2026-06-05 14:52:35 -04:00
Author
Owner

@shatfield4 commented on GitHub (May 13, 2026):

Have you tried this with other PDFs? When you receive the "No text content found in xxx.pdf" log, this means our OCR system could not find any text to extract from the PDF you uploaded. Closing for now since this does not seem like a bug but please test with other PDF files to see if it is only that specific one or if it happens on all PDFs.

<!-- gh-comment-id:4445730730 --> @shatfield4 commented on GitHub (May 13, 2026): Have you tried this with other PDFs? When you receive the "No text content found in xxx.pdf" log, this means our OCR system could not find any text to extract from the PDF you uploaded. Closing for now since this does not seem like a bug but please test with other PDF files to see if it is only that specific one or if it happens on all PDFs.
Author
Owner

@kklldog commented on GitHub (May 19, 2026):

hi @shatfield4
Thanks your reply.
Not all pdf happen the error. If a structure PDF that works very well but all the scanned pdf totally can not work.
one strange point is that if I take a screenshot from scanned pdf then upload to space and it seems OCR can get the information from image.

<!-- gh-comment-id:4494217154 --> @kklldog commented on GitHub (May 19, 2026): hi @shatfield4 Thanks your reply. Not all pdf happen the error. If a structure PDF that works very well but all the scanned pdf totally can not work. one strange point is that if I take a screenshot from scanned pdf then upload to space and it seems OCR can get the information from image.
Author
Owner

@sanghyun8039 commented on GitHub (May 21, 2026):

I also had same issue.

VX2_외형도.pdf

<!-- gh-comment-id:4505494751 --> @sanghyun8039 commented on GitHub (May 21, 2026): I also had same issue. [VX2_외형도.pdf](https://github.com/user-attachments/files/28089002/VX2_.pdf)
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#5200