VectorDB and Judge Parallelism #65
Merged
Conversation
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
Closed
5 tasks
AlexCuadron
reviewed
Jun 14, 2025
Collaborator
AlexCuadron
left a comment
AlexCuadron
left a comment
There was a problem hiding this comment.
Very nice, only some nits and questions. Fix those and its ready :)
vcache-project
approved these changes
Jun 14, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The LLMSimilarityEvaluator requires async execution to ensure performant e2e latency.
To achieve that, I multi-threaded the exploration logic. The multi-threaded logic is decoupled from the core logic.
Every LLM-based label generation gets processed with its own thread (I/O bounded). The logic maintains one global and thread-safe queue to handle the vector db and metadata objects.
The logic is tested and verified by running the actual benchmarks.