[KNN] Adding default value for oversampling in 9.1.0 #1290
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
Samiul-TheSoccerFan
added
the
documentation
jimczi
reviewed
Apr 29, 2025
|
@jimczi, can I get another review please? |
jimczi
approved these changes
May 6, 2025
Samiul-TheSoccerFan
requested review from
leemthompo
and removed request for
benwtrent and
leemthompo
|
@leemthompo Can I get another re-review please? |
leemthompo
approved these changes
May 6, 2025
| @@ -913,7 +913,7 @@ All forms of quantization will result in some accuracy loss and as the quantizat | |||
|
|
|||
| * `int8` requires minimal if any rescoring | |||
| * `int4` requires some rescoring for higher accuracy and larger recall scenarios. Generally, oversampling by 1.5x-2x recovers most of the accuracy loss. | |||
| * `bbq` requires rescoring except on exceptionally large indices or models specifically designed for quantization. We have found that between 3x-5x oversampling is generally sufficient. But for fewer dimensions or vectors that do not quantize well, higher oversampling may be required. | |||
| * `bbq` requires rescoring except on exceptionally large indices or models specifically designed for quantization. We have found that between 3x-5x oversampling is generally sufficient. But for fewer dimensions or vectors that do not quantize well, higher oversampling may be required. As noted above, we default to an oversampling factor of `3.0`. | |||
There was a problem hiding this comment.
Suggested change
| * `bbq` requires rescoring except on exceptionally large indices or models specifically designed for quantization. We have found that between 3x-5x oversampling is generally sufficient. But for fewer dimensions or vectors that do not quantize well, higher oversampling may be required. As noted above, we default to an oversampling factor of `3.0`. | |
| * `bbq` requires rescoring except on exceptionally large indices or models specifically designed for quantization. We have found that between 3x-5x oversampling is generally sufficient. But for fewer dimensions or vectors that do not quantize well, higher oversampling may be required. Starting in `9.1.0`, the default oversampling factor is 3. |
There was a problem hiding this comment.
Sure, that works. Thank you :)
leemthompo
changed the title
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.
Adding default value for
oversamplinginto the knn documentation. We have added this value from9.1.0.