Fix query embedding isn't normalized in Collection.QueryEmbedding() call #77
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Outdated suggestions cannot be applied.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.
For the
Collection.Query
call the embedding is created and normalized. ForCollection.QueryEmbedding()
the embedding is a parameter, and so far it was assumed/expected to be normalized by the user who calls the function, but that's not guaranteed, so now we check if the embedding is normalized and if it's not then we normalize it.There's virtually no impact on query performance if the query was normalized already, so no need to extend the function with a boolean parameter to allow users to explicitly skip the check.
Here's a run on
main
branch:Benchmark result
Here's a run on this branch with the normalization check:
Benchmark result
It looks even faster, which is just from regular fluctuation.