github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1114] Reduce Embedding size #560

New Issue
Closed
opened 2026-04-12 10:15:15 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 10:15:15 -05:00
Owner
Copy Link

Originally created by @Mohit0928 on GitHub (Nov 13, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1114

I'm trying to replicate this example of langchain. I'm using ElasticSearch as the database to store the embedding. In the given example I have replaced embeddings = OpenAIEmbeddings() with oembed = OllamaEmbeddings(model="llama2") which one can import from langchain.embeddings import OllamaEmbeddings. I'm running Ollama locally. But, I'm running into below error:

raise HTTP_EXCEPTIONS.get(status_code, TransportError)(
elasticsearch.exceptions.RequestError: RequestError(400, 'mapper_parsing_exception', 'The number of dimensions for field [vector] should be in the range [1, 2048] but was [4096]')

The Ollama model always create the embedding of size 4096 even when I sat the chunk size of 500. Is there any way to reduce the size of embedding?

Originally created by @Mohit0928 on GitHub (Nov 13, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1114 I'm trying to replicate [this example](https://python.langchain.com/docs/integrations/vectorstores/elasticsearch#basic-example) of langchain. I'm using ElasticSearch as the database to store the embedding. In the given example I have replaced `embeddings = OpenAIEmbeddings()` with `oembed = OllamaEmbeddings(model="llama2")` which one can import `from langchain.embeddings import OllamaEmbeddings`. I'm running `Ollama` locally. But, I'm running into below error: ``` raise HTTP_EXCEPTIONS.get(status_code, TransportError)( elasticsearch.exceptions.RequestError: RequestError(400, 'mapper_parsing_exception', 'The number of dimensions for field [vector] should be in the range [1, 2048] but was [4096]') ``` The Ollama model always create the embedding of size `4096` even when I sat the chunk size of `500`. Is there any way to reduce the size of embedding?
GiteaMirror commented 2026-04-12 10:15:16 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Nov 13, 2023):

Hi @Mohit0928 the output size of the embedding is determined based on how the model was trained rather than the size of the input, it is a constant. The way to deal with this normally is to use a different model. Ollama doesn't have any embedding specific models in its library at the moment though, so I can't make a great recommendation on a good one to use.

<!-- gh-comment-id:1809158510 --> @BruceMacD commented on GitHub (Nov 13, 2023): Hi @Mohit0928 the output size of the embedding is determined based on how the model was trained rather than the size of the input, it is a constant. The way to deal with this normally is to use a different model. Ollama doesn't have any embedding specific models in its library at the moment though, so I can't make a great recommendation on a good one to use.
GiteaMirror commented 2026-04-12 10:15:17 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Dec 4, 2023):

It looks like this question was answered by Bruce so I will go ahead and close it now. If you think there is anything we left out, reopen and we can address. Thanks for being part of this great community.

<!-- gh-comment-id:1839440089 --> @technovangelist commented on GitHub (Dec 4, 2023): It looks like this question was answered by Bruce so I will go ahead and close it now. If you think there is anything we left out, reopen and we can address. Thanks for being part of this great community.
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
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#560
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?