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

Introduce a new data type VECTOR (alias of ARRAY<Float32>) #10769

Open
Tracked by #10689
BohuTANG opened this issue Mar 25, 2023 · 2 comments
Open
Tracked by #10689

Introduce a new data type VECTOR (alias of ARRAY<Float32>) #10769

BohuTANG opened this issue Mar 25, 2023 · 2 comments
Assignees
Labels
C-feature Category: feature

Comments

@BohuTANG
Copy link
Member

BohuTANG commented Mar 25, 2023

Summary

We propose adding a new data type, VECTOR, as an alias for ARRAY<FLOAT32>.

When a column type is set to VECTOR, an IVF_PQ index will be automatically created in the underlying storage.

This index significantly improves the speed and efficiency of cosine distance calculations, optimizing vector data retrieval and analysis.

@BohuTANG BohuTANG changed the title Introduce a new data type VECTOR (alias of ARRAY<Float32>) (@b41sh ) Introduce a new data type VECTOR (alias of ARRAY<Float32>) Mar 25, 2023
@BohuTANG BohuTANG added the C-feature Category: feature label Mar 25, 2023
@flaneur2020
Copy link
Member

I guess the vector type may have a size hint? likewise VECTOR(1536)

On checking similiarities, the vectors' length should be same

@b41sh
Copy link
Member

b41sh commented Mar 28, 2023

I guess the vector type may have a size hint? likewise VECTOR(1536)

On checking similiarities, the vectors' length should be same

Currently, there is no size_hint, we can add it later if needed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
C-feature Category: feature
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants