Add normalized_cosine vector search similarity #798
Merged
+2,221
−1,906
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Outdated suggestions cannot be applied.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.
Adds the
normalized_cosine
similarity as an option for vector search. The usage is the same ascosine
similarity, but the vectors are normalized to unit length before indexing. The query vectors are also automatically normalized, allowing use of fasterDOT_PRODUCT
similarity internally.The original magnitudes of the indexed vectors are available in the
<field_name>._magitude
field. This allows for reconstruction of the original vector, if needed.