Skip to content

Add muvera config#1635

Merged
robbespo00 merged 29 commits into
mainfrom
rob/muvera
May 8, 2025
Merged

Add muvera config#1635
robbespo00 merged 29 commits into
mainfrom
rob/muvera

Conversation

@robbespo00
Copy link
Copy Markdown
Contributor

@robbespo00 robbespo00 commented Apr 11, 2025

This PR introduces new configuration parameters for multi-vector indexes (aka ColBERT type).

The need for this new set of params come from the MUVERA algorithm which allows to save memory when creating multi-vector indexes.

The user can configure three values:

  • ksim: number of gaussian vectors for space partitioning, the number of cluster will be 2^ksim
  • dprojections: projection dimensionality of each cluster vectors
  • repetitions: number of times we repeat the space partitioning + dim projections for better approximation

Copy link
Copy Markdown

@orca-security-eu orca-security-eu Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Orca Security Scan Summary

Status Check Issues by priority
Passed Passed Infrastructure as Code high 0   medium 0   low 0   info 0 View in Orca
Passed Passed SAST high 0   medium 0   low 0   info 0 View in Orca
Passed Passed Secrets high 0   medium 0   low 0   info 0 View in Orca
Passed Passed Vulnerabilities high 0   medium 0   low 0   info 0 View in Orca

@codecov-commenter
Copy link
Copy Markdown

codecov-commenter commented Apr 11, 2025

Codecov Report

❌ Patch coverage is 72.54902% with 14 lines in your changes missing coverage. Please review.
✅ Project coverage is 88.17%. Comparing base (3ab1e58) to head (176def6).
⚠️ Report is 851 commits behind head on main.

Files with missing lines Patch % Lines
integration/test_collection_config.py 58.33% 10 Missing ⚠️
...eaviate/collections/classes/config_vector_index.py 83.33% 2 Missing ⚠️
weaviate/collections/classes/config.py 92.30% 1 Missing ⚠️
weaviate/collections/classes/config_methods.py 50.00% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1635      +/-   ##
==========================================
+ Coverage   88.09%   88.17%   +0.08%     
==========================================
  Files         254      256       +2     
  Lines       17630    17693      +63     
==========================================
+ Hits        15531    15601      +70     
+ Misses       2099     2092       -7     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@weaviate-git-bot
Copy link
Copy Markdown

To avoid any confusion in the future about your contribution to Weaviate, we work with a Contributor License Agreement. If you agree, you can simply add a comment to this PR that you agree with the CLA so that we can merge.

beep boop - the Weaviate bot 👋🤖

PS:
Are you already a member of the Weaviate Slack channel?

Comment thread weaviate/collections/classes/config.py Outdated
Comment thread integration/test_collection_config.py Outdated
@robbespo00 robbespo00 changed the title [WIP] Add muvera config Add muvera config May 8, 2025
@robbespo00 robbespo00 merged commit 7b588c5 into main May 8, 2025
56 checks passed
@robbespo00 robbespo00 deleted the rob/muvera branch May 8, 2025 08:52
@tsmith023 tsmith023 restored the rob/muvera branch May 12, 2025 09:40
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants