DiskBBQ - Always block encode doc vectors#141598
Merged
tteofili merged 16 commits intoelastic:mainfrom Feb 4, 2026
Merged
Conversation
…h into dbbq_bulkencode_dv
Contributor
Author
|
I've run some experiments yesterday with JinaV3 embeddings (FinancialQA, Trec-Covid), Cohere embeddings (Wikipedia) and E5-small (Quora). On average this gave a speedup of 50QPS across visit-percentage, filter-selectivity, quantize-bits etc. |
Contributor
Author
|
here're the visualized results for FinancialQA and Trec-Covid (JinaV3 embeddings), the other datasets and models show similar trends. |
elasticsearchmachine
added
the
Team:Search Relevance
Collaborator
|
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
Collaborator
|
Hi @tteofili, I've created a changelog YAML for you. |
kosabogi
pushed a commit
to kosabogi/elasticsearch
that referenced
this pull request
Feb 4, 2026
mamazzol
pushed a commit
to mamazzol/elasticsearch
that referenced
this pull request
Feb 5, 2026
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This always block encodes doc vectors in DiskBBQ.
this also adjusts bulk scoring when the tail size % 4 != 0.