feat: support transforming selected fragments in vector transform stage for ivf_pq index #2657
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
westonpace
reviewed
Jul 30, 2024
westonpace
approved these changes
Aug 1, 2024
|
I updated from main, let's merge if CI passes |
eddyxu
pushed a commit
that referenced
this pull request
Aug 1, 2024
…ge for ivf_pq index (#2657) The `transform_vectors()` api transforms the ivf-pq indices to get an output table with the row_id, pq_code, and partition_id. This PR modifies this API so that this transformation is done for selected fragments that the user specifies as a parameter. If `fragments=None`, the default will use all fragments of the dataset.
wjones127
added a commit
that referenced
this pull request
Aug 1, 2024
We are close to having green CI on Lance `main`. test_vector_transform is failing ever since we merged #2657 I think this is because we still have the file open but are re-using the same file uri. We need to close it to overwrite it.
raunaks13
added a commit
that referenced
this pull request
Aug 8, 2024
…#2681) Follow up of PRs #2566, #2657 and #2670 The whole pipeline can help users transform, shuffle, and load IVF-PQ indices in separate, standalone steps (can be useful when building indices for large datasets) First, the user runs `transform_vectors()` separately on selected fragments Then, they run `shuffle_transformed_vectors()` on each transformed result Finally, they load all the shuffled vectors and commit the index into the dataset using `load_shuffled_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Outdated suggestions cannot be applied.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.
The
transform_vectors()api transforms the ivf-pq indices to get an output table with the row_id, pq_code, and partition_id. This PR modifies this API so that this transformation is done for selected fragments that the user specifies as a parameter. Iffragments=None, the default will use all fragments of the dataset.