Support for inner product distance metric #167
Merged
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Outdated suggestions cannot be applied.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.
Description
This PR adds support for negative inner product as a distance metric, which rounds out the de-facto standard set for ANN vector search: L2, cosine, and inner product. (We use negative inner product for the same postgres reasons as pgvector does.) We continue to follow
pgvector
syntax: so,<#>
for the distance operator, andvector_ip_ops
for the operator class name.Some further details about the PR:
Testing
DistanceType
as a parameter to includeDistanceType::InnerProduct
References
Design doc: https://timescale.slab.com/posts/distance-metrics-for-pgvectorscale-atrovg6n?shr=NaR3yhZgvzEx6SixcBHwKsqV
Feature request: #96