github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #6230] Add Generate Embedding for Sparse vector #50406

New Issue
Open
opened 2026-04-28 15:38:37 -05:00 by GiteaMirror · 27 comments
GiteaMirror commented 2026-04-28 15:38:37 -05:00
Owner
Copy Link

Originally created by @shashade2012 on GitHub (Aug 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6230

I find ollama already support bge-m3,
because bge-m3 can generate sparse vector. Is there any way for generate sparse embeddings?

Originally created by @shashade2012 on GitHub (Aug 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6230 I find ollama already support bge-m3, because bge-m3 can generate sparse vector. Is there any way for generate sparse embeddings?
GiteaMirror added the feature request label 2026-04-28 15:38:37 -05:00
GiteaMirror commented 2026-04-28 15:38:38 -05:00
Author
Owner
Copy Link

@dbc-2024 commented on GitHub (Aug 8, 2024):

+1

<!-- gh-comment-id:2275046617 --> @dbc-2024 commented on GitHub (Aug 8, 2024): +1
GiteaMirror commented 2026-04-28 15:38:39 -05:00
Author
Owner
Copy Link

@davide445 commented on GitHub (Aug 14, 2024):

+1

<!-- gh-comment-id:2289308989 --> @davide445 commented on GitHub (Aug 14, 2024): +1
GiteaMirror commented 2026-04-28 15:38:39 -05:00
Author
Owner
Copy Link

@roylknghv commented on GitHub (Aug 20, 2024):

+1

<!-- gh-comment-id:2298470040 --> @roylknghv commented on GitHub (Aug 20, 2024): +1
GiteaMirror commented 2026-04-28 15:38:40 -05:00
Author
Owner
Copy Link

@sondin commented on GitHub (Nov 14, 2024):

+1

<!-- gh-comment-id:2476696613 --> @sondin commented on GitHub (Nov 14, 2024): +1
GiteaMirror commented 2026-04-28 15:38:41 -05:00
Author
Owner
Copy Link

@Golden00885 commented on GitHub (Feb 10, 2025):

+1

<!-- gh-comment-id:2648552721 --> @Golden00885 commented on GitHub (Feb 10, 2025): +1
GiteaMirror commented 2026-04-28 15:38:41 -05:00
Author
Owner
Copy Link

@halogencookies commented on GitHub (Feb 18, 2025):

+1

<!-- gh-comment-id:2666988979 --> @halogencookies commented on GitHub (Feb 18, 2025): +1
GiteaMirror commented 2026-04-28 15:38:42 -05:00
Author
Owner
Copy Link

@zhengtingxue commented on GitHub (Mar 6, 2025):

+1

<!-- gh-comment-id:2703032484 --> @zhengtingxue commented on GitHub (Mar 6, 2025): +1
GiteaMirror commented 2026-04-28 15:38:45 -05:00
Author
Owner
Copy Link

@pawasthy commented on GitHub (Mar 18, 2025):

+1

<!-- gh-comment-id:2733677296 --> @pawasthy commented on GitHub (Mar 18, 2025): +1
GiteaMirror commented 2026-04-28 15:38:47 -05:00
Author
Owner
Copy Link

@AOShei commented on GitHub (Apr 4, 2025):

+1

<!-- gh-comment-id:2779095192 --> @AOShei commented on GitHub (Apr 4, 2025): +1
GiteaMirror commented 2026-04-28 15:38:48 -05:00
Author
Owner
Copy Link

@wangle201210 commented on GitHub (Apr 29, 2025):

+1

<!-- gh-comment-id:2837319157 --> @wangle201210 commented on GitHub (Apr 29, 2025): +1
GiteaMirror commented 2026-04-28 15:38:49 -05:00
Author
Owner
Copy Link

@FlorinCiobotea commented on GitHub (Jun 12, 2025):

+1

<!-- gh-comment-id:2965766123 --> @FlorinCiobotea commented on GitHub (Jun 12, 2025): +1
GiteaMirror commented 2026-04-28 15:38:50 -05:00
Author
Owner
Copy Link

@spencer-crook commented on GitHub (Jun 16, 2025):

+1

<!-- gh-comment-id:2977695598 --> @spencer-crook commented on GitHub (Jun 16, 2025): +1
GiteaMirror commented 2026-04-28 15:38:51 -05:00
Author
Owner
Copy Link

@MrDoe commented on GitHub (Jun 24, 2025):

+1

<!-- gh-comment-id:3000092549 --> @MrDoe commented on GitHub (Jun 24, 2025): +1
GiteaMirror commented 2026-04-28 15:38:52 -05:00
Author
Owner
Copy Link

@shanbady commented on GitHub (Jul 1, 2025):

+1

<!-- gh-comment-id:3021410632 --> @shanbady commented on GitHub (Jul 1, 2025): +1
GiteaMirror commented 2026-04-28 15:38:52 -05:00
Author
Owner
Copy Link

@appyhdu commented on GitHub (Aug 12, 2025):

+1

<!-- gh-comment-id:3179666233 --> @appyhdu commented on GitHub (Aug 12, 2025): +1
GiteaMirror commented 2026-04-28 15:38:53 -05:00
Author
Owner
Copy Link

@Haruno19 commented on GitHub (Aug 14, 2025):

+1

<!-- gh-comment-id:3187285154 --> @Haruno19 commented on GitHub (Aug 14, 2025): +1
GiteaMirror commented 2026-04-28 15:38:54 -05:00
Author
Owner
Copy Link

@jaredmcqueen commented on GitHub (Aug 17, 2025):

+1

<!-- gh-comment-id:3194589523 --> @jaredmcqueen commented on GitHub (Aug 17, 2025): +1
GiteaMirror commented 2026-04-28 15:38:54 -05:00
Author
Owner
Copy Link

@roytmana commented on GitHub (Sep 30, 2025):

any update on sparse embeddings support? it would have been an extremely useful feature!

<!-- gh-comment-id:3354073374 --> @roytmana commented on GitHub (Sep 30, 2025): any update on sparse embeddings support? it would have been an extremely useful feature!
GiteaMirror commented 2026-04-28 15:38:55 -05:00
Author
Owner
Copy Link

@afrianluthfan commented on GitHub (Oct 31, 2025):

+1

<!-- gh-comment-id:3471689965 --> @afrianluthfan commented on GitHub (Oct 31, 2025): +1
GiteaMirror commented 2026-04-28 15:38:56 -05:00
Author
Owner
Copy Link

@qu-en commented on GitHub (Nov 5, 2025):

+1

<!-- gh-comment-id:3490691925 --> @qu-en commented on GitHub (Nov 5, 2025): +1
GiteaMirror commented 2026-04-28 15:38:56 -05:00
Author
Owner
Copy Link

@Lords08 commented on GitHub (Dec 24, 2025):

Any update on sparse embeddings support?
I have read the BGE-M3 documentation, this model support Colbert Multi Vector Embeddings too.
It is very convenient if one api call to Ollama, can generate 3 type vectors at once (Dense, Sparse, and Colbert)!

<!-- gh-comment-id:3688591247 --> @Lords08 commented on GitHub (Dec 24, 2025): Any update on sparse embeddings support? I have read the BGE-M3 documentation, this model support Colbert Multi Vector Embeddings too. It is very convenient if one api call to Ollama, can generate 3 type vectors at once (Dense, Sparse, and Colbert)!
GiteaMirror commented 2026-04-28 15:38:57 -05:00
Author
Owner
Copy Link

@JakobStadlhuber commented on GitHub (Jan 2, 2026):

+1

<!-- gh-comment-id:3706407363 --> @JakobStadlhuber commented on GitHub (Jan 2, 2026): +1
GiteaMirror commented 2026-04-28 15:38:58 -05:00
Author
Owner
Copy Link

@thohemp commented on GitHub (Jan 9, 2026):

+1

<!-- gh-comment-id:3728255974 --> @thohemp commented on GitHub (Jan 9, 2026): +1
GiteaMirror commented 2026-04-28 15:39:01 -05:00
Author
Owner
Copy Link

@JayceJoyce commented on GitHub (Feb 19, 2026):

+1

<!-- gh-comment-id:3929523563 --> @JayceJoyce commented on GitHub (Feb 19, 2026): +1
GiteaMirror commented 2026-04-28 15:39:04 -05:00
Author
Owner
Copy Link

@byeoryjeong commented on GitHub (Feb 26, 2026):

+1

<!-- gh-comment-id:3964326101 --> @byeoryjeong commented on GitHub (Feb 26, 2026): +1
GiteaMirror commented 2026-04-28 15:39:06 -05:00
Author
Owner
Copy Link

@deroivano commented on GitHub (Mar 16, 2026):

+1

<!-- gh-comment-id:4064555833 --> @deroivano commented on GitHub (Mar 16, 2026): +1
GiteaMirror commented 2026-04-28 15:39:07 -05:00
Author
Owner
Copy Link

@21digitalweb commented on GitHub (Apr 18, 2026):

I have run into an issue with using Dense vectors only. In a test I vectorised data of groceries. When type in "Buy Yogurt" as a query and vectorize it, the results returned are things like; Yogurt (Expected) and then Butter and Honey.

Both are used in cooking, but does not satisfy the query. There are many other Yogurt results that didn't feature and should have given the key word comparison when using SparseVector.

Now I end up either using vLLM instead of Ollama OR I need to sidecar some code. Dissapointing since the LLM can produce the vector and does.

<!-- gh-comment-id:4273531963 --> @21digitalweb commented on GitHub (Apr 18, 2026): I have run into an issue with using Dense vectors only. In a test I vectorised data of groceries. When type in "Buy Yogurt" as a query and vectorize it, the results returned are things like; Yogurt (Expected) and then Butter and Honey. Both are used in cooking, but does not satisfy the query. There are many other Yogurt results that didn't feature and should have given the key word comparison when using SparseVector. Now I end up either using vLLM instead of Ollama OR I need to sidecar some code. Dissapointing since the LLM can produce the vector and does.
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 feature request
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#50406
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?