github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12441] Updated to 0.12.3 and /v1/embedding API has odd error #8264

New Issue
Closed
opened 2026-04-12 20:48:04 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 20:48:04 -05:00
Owner
Copy Link

Originally created by @heapsoftware on GitHub (Sep 29, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12441

What is the issue?

Hi guys!

Thanks for this fantastic tool. Been using embeddings with https://github.com/Cinnamon/kotaemon and since the update maybe within the last two versions or so, all of a sudden all embedding calls stopped working. It was working without issue before but now comes up with the following error, can this be fixed on your side?

INFO:httpx:HTTP Request: POST http://IPADDRESS:11434/v1/embeddings "HTTP/1.1 400 Bad Request"
Error code: 400 - {'error': {'message': 'invalid input type', 'type': 'api_error', 'param': None, 'code': None}}

Relevant log output

OS

Docker

GPU

Nvidia

CPU

AMD

Ollama version

0.12.3

Originally created by @heapsoftware on GitHub (Sep 29, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12441 ### What is the issue? Hi guys! Thanks for this fantastic tool. Been using embeddings with https://github.com/Cinnamon/kotaemon and since the update maybe within the last two versions or so, all of a sudden all embedding calls stopped working. It was working without issue before but now comes up with the following error, can this be fixed on your side? INFO:httpx:HTTP Request: POST http://IPADDRESS:11434/v1/embeddings "HTTP/1.1 400 Bad Request" Error code: 400 - {'error': {'message': 'invalid input type', 'type': 'api_error', 'param': None, 'code': None}} ### Relevant log output ```shell ``` ### OS Docker ### GPU Nvidia ### CPU AMD ### Ollama version 0.12.3
GiteaMirror added the bug label 2026-04-12 20:48:04 -05:00
GiteaMirror commented 2026-04-12 20:48:07 -05:00
Author
Owner
Copy Link

@heapsoftware commented on GitHub (Sep 29, 2025):

I figured it out, it was due to the context_length param which is not supported per the ollama API doc.

<!-- gh-comment-id:3344520887 --> @heapsoftware commented on GitHub (Sep 29, 2025): I figured it out, it was due to the context_length param which is not supported per the ollama API doc.
GiteaMirror commented 2026-04-12 20:48:08 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 29, 2025):

@heapsoftware where were you passing the context_length parameter? I've been trying to duplicate the bug but haven't been able to so far.

<!-- gh-comment-id:3344530287 --> @pdevine commented on GitHub (Sep 29, 2025): @heapsoftware where were you passing the `context_length` parameter? I've been trying to duplicate the bug but haven't been able to so far.
GiteaMirror commented 2026-04-12 20:48:09 -05:00
Author
Owner
Copy Link

@heapsoftware commented on GitHub (Sep 29, 2025):

I get the error when I put the context_length parameter in kotaemon a like this below in Embedding settings, save and then click the Test button. I didnt do anything to get any of the traffic and/or post data it sending to the API endpoint, so not sure what its sending when I add that in, but I remove it and it works now.
Specification of the Embedding model in YAML format:
api_key: ollama
base_url: http://OLLAMAIP:11434/v1/
context_length: 512
model: mxbai-embed-large:latest

<!-- gh-comment-id:3344726131 --> @heapsoftware commented on GitHub (Sep 29, 2025): I get the error when I put the context_length parameter in kotaemon a like this below in Embedding settings, save and then click the Test button. I didnt do anything to get any of the traffic and/or post data it sending to the API endpoint, so not sure what its sending when I add that in, but I remove it and it works now. Specification of the Embedding model in YAML format: api_key: ollama base_url: http://OLLAMAIP:11434/v1/ context_length: 512 model: mxbai-embed-large:latest
GiteaMirror commented 2026-04-12 20:48:10 -05:00
Author
Owner
Copy Link

@yfxu-zz commented on GitHub (Sep 29, 2025):

unsubscribe

At 2025-09-29 11:33:01, "heapsoftware" @.***> wrote:

heapsoftware left a comment (ollama/ollama#12441)

I get the error when I put the context_length parameter in kotaemon a like this below in Embedding settings, save and then click the Test button. I didnt do anything to get any of the traffic and/or post data it sending to the API endpoint, so not sure what its sending when I add that in, but I remove it and it works now.
Specification of the Embedding model in YAML format:
api_key: ollama
base_url: http://OLLAMAIP:11434/v1/
context_length: 512
model: mxbai-embed-large:latest

—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you are subscribed to this thread.Message ID: @.***>

<!-- gh-comment-id:3345152970 --> @yfxu-zz commented on GitHub (Sep 29, 2025): unsubscribe At 2025-09-29 11:33:01, "heapsoftware" ***@***.***> wrote: heapsoftware left a comment (ollama/ollama#12441) I get the error when I put the context_length parameter in kotaemon a like this below in Embedding settings, save and then click the Test button. I didnt do anything to get any of the traffic and/or post data it sending to the API endpoint, so not sure what its sending when I add that in, but I remove it and it works now. Specification of the Embedding model in YAML format: api_key: ollama base_url: http://OLLAMAIP:11434/v1/ context_length: 512 model: mxbai-embed-large:latest — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>
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#8264
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?