Support cosine similarity in kNN search #79500
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
jtibshirani
added
:Search/Search
|
I ran benchmarks and confirmed the new validation for |
|
Pinging @elastic/es-search (Team:Search) |
mayya-sharipova
approved these changes
Oct 20, 2021
lockewritesdocs
pushed a commit
to lockewritesdocs/elasticsearch
that referenced
this pull request
Oct 28, 2021
This PR adds support for `cosine` similarity:
```
"mappings": {
"properties": {
"my_vector": {
"type": "dense_vector",
"dims": 128,
"index": true,
"similarity": "cosine"
}
}
}
```
Unlike `dot_product`, which requires vectors to be of unit length, this
similarity can handle vectors with any magnitude.
This PR also adds validation around `dot_product` to help catch mistakes. When
indexing vectors, we double-check that each vector has unit length. We also
check that kNN query vectors have unit length.
jtibshirani
added
:Search Relevance/Vectors
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Outdated suggestions cannot be applied.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.
This PR adds support for
cosinesimilarity:Unlike
dot_product, which requires vectors to be of unit length, thissimilarity can handle vectors with any magnitude.
This PR also adds validation around
dot_productto help catch mistakes. Whenindexing vectors, we double-check that each vector has unit length. We also
check that kNN query vectors have unit length.