Distance metrics integration #422
Merged
Conversation
This file contains 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
|
Please add a bit more context for this change in the PR description and link to the respective shortcut issue. |
…arch into vlad/distancemetrics
Fixed inner product ordering
jparismorgan
reviewed
Jul 4, 2024
generalize metric handling logic to index.py
There was a problem hiding this comment.
Could we also add C++ unit tests for this? Specifically that we can set and get the metadata correctly, both during index creation and after writing to a URI. Note that you can just add checks to existing tests, you probably don't need totally new test cases here.
NikolaosPapailiou
approved these changes
Jul 22, 2024
cainamisir
force-pushed
the
vlad/distancemetrics
branch
2 times, most recently
from
0032183 to
53410b6
Compare
jparismorgan
approved these changes
Jul 25, 2024
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Outdated suggestions cannot be applied.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.
Added two new distance metrics to the FLAT index.
Usage: in create() or ingest(), distance_metric can be specified like this:
distance_metric=vspy.DistanceMetric.COSINEor
distance_metric=vspy.DistanceMetric.INNER_PRODUCTDefault distance metric is L2.
Note: the Inner Product distance metric returns -dot(a,b) as to provide the vectors in the order indicating highest similarity, without changing the paradigm that "distances" are returned in increasing order.