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

Use new VectorScorer interface where applicable in Elasticsearch #109293

Open
benwtrent opened this issue Jun 3, 2024 · 2 comments
Open

Use new VectorScorer interface where applicable in Elasticsearch #109293

benwtrent opened this issue Jun 3, 2024 · 2 comments
Labels
>enhancement :Search Relevance/Vectors Vector search Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch

Comments

@benwtrent
Copy link
Member

Description

Lucene 9.11 provides a new interface for the vector values, VectorScorer, this is a flat scorer that gives a way to do optimized vector scoring for a flat vector encoding.

For example, int8_flat could use this interface instead of knn when calculating the nearest k vectors.

@elasticsearchmachine elasticsearchmachine added the Team:Search Meta label for search team label Jun 3, 2024
@elasticsearchmachine
Copy link
Collaborator

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

elasticsearchmachine pushed a commit that referenced this issue Jun 20, 2024
Lucene 9.11 introduced a new VectorScorer interface. We should utilize
this interface when scoring exact vectors. 

related to: #109293
@javanna javanna added Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch and removed Team:Search Meta label for search team labels Jul 12, 2024
@elasticsearchmachine
Copy link
Collaborator

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
>enhancement :Search Relevance/Vectors Vector search Team:Search Relevance Meta label for the Search Relevance team in Elasticsearch
Projects
None yet
Development

No branches or pull requests

3 participants