langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-22 12:36:14 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Using the online version of Dify, uploading a PDF file, and using a custom cutting method resulted in failure during embedding. #757

New Issue
Closed
opened 2026-02-21 17:28:18 -05:00 by yindo · 7 comments
yindo commented 2026-02-21 17:28:18 -05:00
Owner
Copy Link
Copy Source

Originally created by @mozeqiu123 on GitHub (Nov 30, 2023).

Originally assigned to: @JohnJyong on GitHub.

Dify version

0.3.32

Cloud or Self Hosted

Cloud

Steps to reproduce

When I used the online version of Dify, uploaded my PDF file, and then customized the cutting method, an error occurred when embedding.
image

✔️ Expected Behavior

Embedded successfully

❌ Actual Behavior

Embedding failed

Originally created by @mozeqiu123 on GitHub (Nov 30, 2023). Originally assigned to: @JohnJyong on GitHub. ### Dify version 0.3.32 ### Cloud or Self Hosted Cloud ### Steps to reproduce When I used the online version of Dify, uploaded my PDF file, and then customized the cutting method, an error occurred when embedding. ![image](https://github.com/langgenius/dify/assets/139750690/26ada004-f2cc-4a43-8275-662f4584c830) ### ✔️ Expected Behavior Embedded successfully ### ❌ Actual Behavior Embedding failed
yindo added the 🐞 bug🤔 cant-reproduce labels 2026-02-21 17:28:18 -05:00
yindo closed this issue 2026-02-21 17:28:18 -05:00
yindo commented 2026-02-21 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Nov 30, 2023):

Can you hover on the error and get the detailed message?

@crazywoola commented on GitHub (Nov 30, 2023): Can you hover on the error and get the detailed message?
yindo commented 2026-02-21 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@mozeqiu123 commented on GitHub (Nov 30, 2023):

Can you hover on the error and get the detailed message?

I placed the mouse on the error and there was no response
image

@mozeqiu123 commented on GitHub (Nov 30, 2023): > Can you hover on the error and get the detailed message? I placed the mouse on the error and there was no response ![image](https://github.com/langgenius/dify/assets/139750690/e377dade-e051-48ca-ba26-793be504d79d)
yindo commented 2026-02-21 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Dec 1, 2023):

Can you attach the original file if that's ok? We need to something to test if possible.

@crazywoola commented on GitHub (Dec 1, 2023): Can you attach the original file if that's ok? We need to something to test if possible.
yindo commented 2026-02-21 17:28:18 -05:00
Author
Owner
Copy Link
Copy Source

@mozeqiu123 commented on GitHub (Dec 1, 2023):

Can you attach the original file if that's ok? We need to something to test if possible.

yes,sure.
2307.16789.pdf
Uploading bcgdeeplink.pdf…

@mozeqiu123 commented on GitHub (Dec 1, 2023): > Can you attach the original file if that's ok? We need to something to test if possible. yes,sure. [2307.16789.pdf](https://github.com/langgenius/dify/files/13521459/2307.16789.pdf) [Uploading bcgdeeplink.pdf…]()
yindo commented 2026-02-21 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Dec 5, 2023):

image I have tested this file, seems ok to me, because I have run out of the tokens, can not finish the whole process, as you can see, there is an error message in the top left in this image. You can paste the error message here.

And I change the embedding model back to openai and it's works for me
image

@crazywoola commented on GitHub (Dec 5, 2023): <img width="1856" alt="image" src="https://github.com/langgenius/dify/assets/100913391/0819581b-65dc-41bd-bde4-e135fb230e65"> I have tested this file, seems ok to me, because I have run out of the tokens, can not finish the whole process, as you can see, there is an error message in the top left in this image. You can paste the error message here. And I change the embedding model back to openai and it's works for me <img width="1847" alt="image" src="https://github.com/langgenius/dify/assets/100913391/f8f80be9-1bfc-45d8-8a1e-5c3a1334f0d0">
yindo commented 2026-02-21 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@mozeqiu123 commented on GitHub (Dec 5, 2023):

image I have tested this file, seems ok to me, because I have run out of the tokens, can not finish the whole process, as you can see, there is an error message in the top left in this image. You can paste the error message here.
And I change the embedding model back to openai and it's works for me image

Okay, I will try again

@mozeqiu123 commented on GitHub (Dec 5, 2023): > <img alt="image" width="1856" src="https://private-user-images.githubusercontent.com/100913391/288028807-0819581b-65dc-41bd-bde4-e135fb230e65.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTEiLCJleHAiOjE3MDE4MzQ3ODQsIm5iZiI6MTcwMTgzNDQ4NCwicGF0aCI6Ii8xMDA5MTMzOTEvMjg4MDI4ODA3LTA4MTk1ODFiLTY1ZGMtNDFiZC1iZGU0LWUxMzVmYjIzMGU2NS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBSVdOSllBWDRDU1ZFSDUzQSUyRjIwMjMxMjA2JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDIzMTIwNlQwMzQ4MDRaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT05NzZjYTc3YWI3OWQwMjQ3ZWY1MDI0N2Y2MDYxMzFjZGY4MGJhMThiOGYxNzI1OGQyZjM3MDE4YTRkYzM0YmQwJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.OFNRUL5aycMEtvFrf0G9zAdrsnL1rCETnU_HvbZJmFA"> I have tested this file, seems ok to me, because I have run out of the tokens, can not finish the whole process, as you can see, there is an error message in the top left in this image. You can paste the error message here. > And I change the embedding model back to openai and it's works for me <img alt="image" width="1847" src="https://private-user-images.githubusercontent.com/100913391/288029610-f8f80be9-1bfc-45d8-8a1e-5c3a1334f0d0.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTEiLCJleHAiOjE3MDE4MzQ3ODQsIm5iZiI6MTcwMTgzNDQ4NCwicGF0aCI6Ii8xMDA5MTMzOTEvMjg4MDI5NjEwLWY4ZjgwYmU5LTFiZmMtNDVkOC04YTFlLTVjM2ExMzM0ZjBkMC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBSVdOSllBWDRDU1ZFSDUzQSUyRjIwMjMxMjA2JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDIzMTIwNlQwMzQ4MDRaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT00M2ZlNTNjYTFkNDdiMDI5MDM0M2JkMDE3NTQzZDlhMTU1MzAxMDk3ZDY0MWJjMWU0MjRlY2U0NzI1OGIzN2EzJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.-YnCN3OVFFdWI_G418sJYdVxznfmRDFkCDUC0RArJis"> Okay, I will try again
yindo commented 2026-02-21 17:28:19 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Dec 19, 2023):

We are using unstructure.io to process pdf data now, you could try this again in v0.3.34.

@crazywoola commented on GitHub (Dec 19, 2023): We are using unstructure.io to process pdf data now, you could try this again in v0.3.34.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug 🤔 cant-reproduce
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#757
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?