github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5539] can't embedding PDF file in Korean #3459

New Issue
Closed
opened 2026-04-12 14:08:24 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 14:08:24 -05:00
Owner
Copy Link

Originally created by @codeMonkey-shin on GitHub (Jul 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5539

What is the issue?

I'm trying to use rag by embedding a PDF file in Korean, but the encoding seems to be broken. When saved to vectordb, broken strings are stored.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.48

Originally created by @codeMonkey-shin on GitHub (Jul 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5539 ### What is the issue? I'm trying to use rag by embedding a PDF file in Korean, but the encoding seems to be broken. When saved to vectordb, broken strings are stored. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.48
GiteaMirror added the bug label 2026-04-12 14:08:24 -05:00
GiteaMirror commented 2026-04-12 14:08:26 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Jul 9, 2024):

@codeMonkey-shin sorry about this. May I ask which embedding model you are using? Is there a sample korean PDF in the public you could share for us to reproduce?

Thank you!

<!-- gh-comment-id:2216497786 --> @mchiang0610 commented on GitHub (Jul 9, 2024): @codeMonkey-shin sorry about this. May I ask which embedding model you are using? Is there a sample korean PDF in the public you could share for us to reproduce? Thank you!
GiteaMirror commented 2026-04-12 14:08:26 -05:00
Author
Owner
Copy Link

@codeMonkey-shin commented on GitHub (Jul 9, 2024):

@codeMonkey-shin sorry about this. May I ask which embedding model you are using? Is there a sample korean PDF in the public you could share for us to reproduce?

Thank you!

I used the chatfire/bge-m3:q8_0 model.

This model also supports Korean.

test.pdf

You can use the short Korean pdf file here.

<!-- gh-comment-id:2216639530 --> @codeMonkey-shin commented on GitHub (Jul 9, 2024): > @codeMonkey-shin sorry about this. May I ask which embedding model you are using? Is there a sample korean PDF in the public you could share for us to reproduce? > > Thank you! I used the chatfire/bge-m3:q8_0 model. This model also supports Korean. [test.pdf](https://github.com/user-attachments/files/16138640/test.pdf) You can use the short Korean pdf file here.
GiteaMirror commented 2026-04-12 14:08:27 -05:00
Author
Owner
Copy Link

@codeMonkey-shin commented on GitHub (Jul 9, 2024):

@codeMonkey-shin sorry about this. May I ask which embedding model you are using? Is there a sample korean PDF in the public you could share for us to reproduce?

Thank you!
Don't worry about it, it was my mistake. There seems to be an issue with the front-end.

<!-- gh-comment-id:2216986447 --> @codeMonkey-shin commented on GitHub (Jul 9, 2024): > @codeMonkey-shin sorry about this. May I ask which embedding model you are using? Is there a sample korean PDF in the public you could share for us to reproduce? > > Thank you! Don't worry about it, it was my mistake. There seems to be an issue with the front-end.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
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/ollama#3459
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?