fix: cache ONNXMiniLM_L6_V2 instance in DefaultEmbeddingFunction#6960
Open
Jah-yee wants to merge 1 commit intochroma-core:mainfrom
Open
fix: cache ONNXMiniLM_L6_V2 instance in DefaultEmbeddingFunction#6960Jah-yee wants to merge 1 commit intochroma-core:mainfrom
Jah-yee wants to merge 1 commit intochroma-core:mainfrom
Conversation
DefaultEmbeddingFunction.__call__ was constructing a fresh ONNXMiniLM_L6_V2 on every call, triggering cold lazy-init of the tokenizer (~5ms) and ONNX session each time. This caused a ~10x slowdown on repeated embed calls. Fix: create the ONNXMiniLM_L6_V2 instance once in __call__ and cache it on self._ef for subsequent calls. Fixes chroma-core#6941 Signed-off-by: Jah-yee <[email protected]>
Reviewer ChecklistPlease leverage this checklist to ensure your code review is thorough before approving Testing, Bugs, Errors, Logs, Documentation
System Compatibility
Quality
|
Contributor
|
Cache This PR fixes a performance issue in The change is limited to This summary was automatically generated by @propel-code-bot |
![propel-code-bot[bot]](https://avatars.githubusercontent.com/in/1179004?s=60&v=4){kind=small}
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
DefaultEmbeddingFunction.call was constructing a fresh ONNXMiniLM_L6_V2 on every call, triggering cold lazy-init of the tokenizer (~5ms) and ONNX session each time. This caused a ~10x slowdown on repeated embed calls.
Fix: create the ONNXMiniLM_L6_V2 instance once in call and cache it on self._ef for subsequent calls.
Fixes #6941
Signed-off-by: Jah-yee [email protected]
Thank you for your work on this project. I hope this small fix is helpful. Please let me know if there's anything to adjust.
Warmly, RoomWithOutRoof