github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #3053] something broke /embeddings in last update ( 0.1.28 and .29) docker #63915

New Issue
Closed
opened 2026-05-03 15:25:39 -05:00 by GiteaMirror · 10 comments
GiteaMirror commented 2026-05-03 15:25:39 -05:00
Owner
Copy Link

Originally created by @Hansson0728 on GitHub (Mar 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3053

i dont even get a response when curl /embeddings.

curl -X POST http://localhost:11434/api/embeddings -d '{"model":"nomic-embed-text", "prompt": "hello"}'

nothin in the logs no answer no 404 no nothing. iam pretty sure i worked before 0.1.28..

Originally created by @Hansson0728 on GitHub (Mar 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3053 i dont even get a response when curl /embeddings. curl -X POST http://localhost:11434/api/embeddings -d '{"model":"nomic-embed-text", "prompt": "hello"}' nothin in the logs no answer no 404 no nothing. iam pretty sure i worked before 0.1.28..
GiteaMirror added the bug label 2026-05-03 15:25:39 -05:00
GiteaMirror commented 2026-05-03 15:25:41 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 11, 2024):

if i send an empty request i get a 400
curl -X POST http://localhost:11434/api/embeddings -d '{}'

then i send with a model
curl -X POST http://localhost:11434/api/embeddings -d '{"model":"nomic-embed-text"}'
i get an empty embedding:
{"embedding":[]}

then i try to embedd and i never get any response, the enpoint will never respont again.

<!-- gh-comment-id:1988625883 --> @Hansson0728 commented on GitHub (Mar 11, 2024): if i send an empty request i get a 400 curl -X POST http://localhost:11434/api/embeddings -d '{}' then i send with a model curl -X POST http://localhost:11434/api/embeddings -d '{"model":"nomic-embed-text"}' i get an empty embedding: {"embedding":[]} then i try to embedd and i never get any response, the enpoint will never respont again.
GiteaMirror commented 2026-05-03 15:25:42 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 11, 2024):

Hi @Hansson0728, is there anything in the ollama server logs?
https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md

<!-- gh-comment-id:1988632506 --> @BruceMacD commented on GitHub (Mar 11, 2024): Hi @Hansson0728, is there anything in the ollama server logs? https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md
GiteaMirror commented 2026-05-03 15:25:42 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 11, 2024):

nothing..... :/

i do know it worked before last update thóugh

<!-- gh-comment-id:1988637963 --> @Hansson0728 commented on GitHub (Mar 11, 2024): nothing..... :/ i do know it worked before last update thóugh
GiteaMirror commented 2026-05-03 15:25:43 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 11, 2024):

i tried 0.1.29 preview and its working as expected again.

<!-- gh-comment-id:1988712776 --> @Hansson0728 commented on GitHub (Mar 11, 2024): i tried 0.1.29 preview and its working as expected again.
GiteaMirror commented 2026-05-03 15:25:43 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 12, 2024):

iam sorry i have to reopen this, something is sttill wrong, its not at all stable...

i have notice if i set the Option Num_ctx to high. Ollama crashes instead of sending an error... there is not much to go on in the logs, nothing actually...

<!-- gh-comment-id:1991343886 --> @Hansson0728 commented on GitHub (Mar 12, 2024): iam sorry i have to reopen this, something is sttill wrong, its not at all stable... i have notice if i set the Option Num_ctx to high. Ollama crashes instead of sending an error... there is not much to go on in the logs, nothing actually...
GiteaMirror commented 2026-05-03 15:25:45 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 12, 2024):

2024-03-12 12:47:16 {"function":"initialize","level":"INFO","line":434,"msg":"initializing slots","n_slots":1,"tid":"139642842101312","timestamp":1710244036}
2024-03-12 12:47:16 {"function":"initialize","level":"INFO","line":443,"msg":"new slot","n_ctx_slot":256,"slot_id":0,"tid":"139642842101312","timestamp":1710244036}
2024-03-12 12:47:16 {"function":"update_slots","level":"INFO","line":1584,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"139641206572608","timestamp":1710244036}
2024-03-12 12:47:16 [GIN] 2024/03/12 - 11:47:16 | 200 | 15.638567581s |      172.18.0.2 | POST     "/api/embeddings" **< THIS IS JUST AN EMPTY POST TO LOAD THE MODEL**
2024-03-12 12:47:16 time=2024-03-12T11:47:16.892Z level=INFO source=dyn_ext_server.go:162 msg="Starting llama main loop"
2024-03-12 12:47:16 [1710244036] llama server main loop starting
2024-03-12 12:47:23 {"function":"launch_slot_with_data","level":"INFO","line":824,"msg":"slot is processing task","slot_id":0,"task_id":0,"tid":"139641206572608","timestamp":1710244043}
2024-03-12 12:47:23 [1710244043] caught exception in llama server main loop: locale::facet::_S_create_c_locale name not valid
2024-03-12 12:47:23 [1710244043] 
2024-03-12 12:47:23 llama server shutting down
<!-- gh-comment-id:1991470010 --> @Hansson0728 commented on GitHub (Mar 12, 2024): ``` 2024-03-12 12:47:16 {"function":"initialize","level":"INFO","line":434,"msg":"initializing slots","n_slots":1,"tid":"139642842101312","timestamp":1710244036} 2024-03-12 12:47:16 {"function":"initialize","level":"INFO","line":443,"msg":"new slot","n_ctx_slot":256,"slot_id":0,"tid":"139642842101312","timestamp":1710244036} 2024-03-12 12:47:16 {"function":"update_slots","level":"INFO","line":1584,"msg":"all slots are idle and system prompt is empty, clear the KV cache","tid":"139641206572608","timestamp":1710244036} 2024-03-12 12:47:16 [GIN] 2024/03/12 - 11:47:16 | 200 | 15.638567581s | 172.18.0.2 | POST "/api/embeddings" **< THIS IS JUST AN EMPTY POST TO LOAD THE MODEL** 2024-03-12 12:47:16 time=2024-03-12T11:47:16.892Z level=INFO source=dyn_ext_server.go:162 msg="Starting llama main loop" 2024-03-12 12:47:16 [1710244036] llama server main loop starting 2024-03-12 12:47:23 {"function":"launch_slot_with_data","level":"INFO","line":824,"msg":"slot is processing task","slot_id":0,"task_id":0,"tid":"139641206572608","timestamp":1710244043} 2024-03-12 12:47:23 [1710244043] caught exception in llama server main loop: locale::facet::_S_create_c_locale name not valid 2024-03-12 12:47:23 [1710244043] 2024-03-12 12:47:23 llama server shutting down ```
GiteaMirror commented 2026-05-03 15:25:47 -05:00
Author
Owner
Copy Link

@Hansson0728 commented on GitHub (Mar 12, 2024):

iam using the docker image:

running this:

$ apt-get install locales
$ locale-gen en_US.UTF-8
$ update-locale LANG=en_US.UTF-8

fixes the error

<!-- gh-comment-id:1991479571 --> @Hansson0728 commented on GitHub (Mar 12, 2024): iam using the docker image: running this: $ apt-get install locales $ locale-gen en_US.UTF-8 $ update-locale LANG=en_US.UTF-8 fixes the error
GiteaMirror commented 2026-05-03 15:25:49 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Mar 13, 2024):

Thanks for the report and workaround steps, this should be fixed in an upcoming release:
e72c567cfd

<!-- gh-comment-id:1994766140 --> @BruceMacD commented on GitHub (Mar 13, 2024): Thanks for the report and workaround steps, this should be fixed in an upcoming release: https://github.com/ollama/ollama/commit/e72c567cfd18a6e48de0acaeda60896af4bff3fd
GiteaMirror commented 2026-05-03 15:25:49 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jun 4, 2024):

Hi there, this should be fixed now. Let me know if you're still seeing it and sorry about the errors

<!-- gh-comment-id:2146737200 --> @jmorganca commented on GitHub (Jun 4, 2024): Hi there, this should be fixed now. Let me know if you're still seeing it and sorry about the errors
GiteaMirror commented 2026-05-03 15:25:49 -05:00
Author
Owner
Copy Link

@erikdubbelboer commented on GitHub (Jun 8, 2024):

@jmorganca the results I'm getting with v0.1.31 are still different from the results with v0.1.42. The results of v0.1.31 seem much more accurate.

Edit, I was wrong, this has been fixed in v0.1.42.

<!-- gh-comment-id:2156025966 --> @erikdubbelboer commented on GitHub (Jun 8, 2024): @jmorganca the results I'm getting with `v0.1.31` are still different from the results with `v0.1.42`. The results of `v0.1.31` seem much more accurate. **Edit, I was wrong, this has been fixed in `v0.1.42`.**
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#63915
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?