Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ApproximateNearestNeighbors] Add notebook and remove exactNearestNeighborsJoin API from the ann class #650

Merged
merged 1 commit into from
May 9, 2024

Conversation

lijinf2
Copy link
Collaborator

@lijinf2 lijinf2 commented May 9, 2024

No description provided.

"num_vecs = 100000\n",
"vec = np.random.randn(dim).reshape([1,dim])\n",
"arr = np.random.randn(num_vecs).reshape([num_vecs,1])\n",
"items = arr * vec\n",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We might want to have a 'better' selection of vectors. I see this is also in the exact knn notebook but didn't notice before. The vectors are all multiples of a single vectors. Perhaps we can find a better choice of vectors for the next release.

@@ -1323,4 +1331,4 @@ def approxSimilarityJoin(
where item_vector v1 is one of the k nearest neighbors of query_vector v2 and their distance is dist(v1, v2).
"""

return self.exactNearestNeighborsJoin(query_df, distCol)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

good catch

Copy link
Collaborator

@eordentlich eordentlich left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍

@lijinf2
Copy link
Collaborator Author

lijinf2 commented May 9, 2024

build

@lijinf2 lijinf2 merged commit c59795a into NVIDIA:branch-24.04 May 9, 2024
2 checks passed
@lijinf2 lijinf2 deleted the ann_nb branch June 26, 2024 21:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants