Make int8_hnsw our default index for new dense-vector fields#106836
Merged
elasticsearchmachine merged 12 commits intoelastic:mainfrom Apr 1, 2024
Merged
Conversation
Collaborator
|
Pinging @elastic/es-search (Team:Search) |
Collaborator
|
Hi @benwtrent, I've created a changelog YAML for you. |
Member
carlosdelest
left a comment
There was a problem hiding this comment.
The changes LGTM 💯
Are we planning to add doc changes explaining the new defaults?
…thub.com:benwtrent/elasticsearch into feature/update-default-vector-index-to-int8_hnsw
tteofili
approved these changes
Mar 28, 2024
Contributor
tteofili
left a comment
There was a problem hiding this comment.
thanks Ben, the changes look good
Member
Author
|
@elasticmachine update branch |
…ult-vector-index-to-int8_hnsw
…thub.com:benwtrent/elasticsearch into feature/update-default-vector-index-to-int8_hnsw
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
For float32, there is no compelling reason to use all the memory required by default for HNSW. Using
int8_hnswprovides a much saner default when it comes to cost vs relevancy.So, on all new indices that use
dense_vectorand want to index them for fast search, we will default toint8_hnsw.Users can still customize their parameters, or prefer
hnswover float32 if they so desire.