Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Allow more than 1024 dimensions for indexed dense_vector fields #92593

Closed
phillipb opened this issue Dec 28, 2022 · 2 comments
Closed

Allow more than 1024 dimensions for indexed dense_vector fields #92593

phillipb opened this issue Dec 28, 2022 · 2 comments
Labels
>enhancement :Search/Search Search-related issues that do not fall into other categories Team:Search Meta label for search team

Comments

@phillipb
Copy link

Description

I'd like to be able to configure the max number of dimensions that are allowed for indexed dense_vectors. I'm using OpenAi's embeddings (which I'm assuming will be a popular use case) and they have 1536 dimensions, but dense_vectors only support 1024. Ideally, I'd like to not lose any semantic meaning by truncating my vectors.

@phillipb phillipb added >enhancement needs:triage Requires assignment of a team area label labels Dec 28, 2022
@original-brownbear original-brownbear added the :Search/Search Search-related issues that do not fall into other categories label Dec 29, 2022
@elasticsearchmachine elasticsearchmachine added Team:Search Meta label for search team and removed needs:triage Requires assignment of a team area label labels Dec 29, 2022
@elasticsearchmachine
Copy link
Collaborator

Pinging @elastic/es-search (Team:Search)

@benwtrent
Copy link
Member

Closing as duplicate of: #92458

We don't want to accidentally spread the conversation around to multiple places.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
>enhancement :Search/Search Search-related issues that do not fall into other categories Team:Search Meta label for search team
Projects
None yet
Development

No branches or pull requests

4 participants