Skip to content

Conversation

@Davidyz
Copy link
Owner

@Davidyz Davidyz commented Aug 2, 2025

A lot of embedding models support truncating the embedding output to accelerate the query. However, not all chromadb embedding function adapters (Ollama) support this. This PR adds the option for the users to set a customised embedding dimension where appropriate.

Note: If you changed the dimension for an existing collection, you'd need to drop it and re-vectorise. Otherwise, the queries won't work because the embedding dimensions must align.

@Davidyz Davidyz added enhancement New feature or request feature labels Aug 2, 2025
@codecov
Copy link

codecov bot commented Aug 2, 2025

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.77%. Comparing base (e6d3f6b) to head (733f6cf).

Additional details and impacted files
@@           Coverage Diff           @@
##             main     #265   +/-   ##
=======================================
  Coverage   99.77%   99.77%           
=======================================
  Files          24       24           
  Lines        1767     1775    +8     
=======================================
+ Hits         1763     1771    +8     
  Misses          4        4           

☔ 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.

@Davidyz Davidyz marked this pull request as ready for review August 3, 2025 07:18
@Davidyz Davidyz merged commit f997701 into main Aug 3, 2025
@Davidyz Davidyz deleted the feat/truncate_embedding branch August 3, 2025 07:34
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request feature

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants