Skip to content

[Feature Request]: Implement MUVERA function for Tensor data #2799

@yingfeng

Description

@yingfeng

Is there an existing issue for the same feature request?

  • I have checked the existing issues.

Is your feature request related to a problem?

Describe the feature you'd like

MUVERA Fixed Dimensional Encoding , "Fixed Dimensional Encoding" , this function take a tensor as input and output a single vector (the FDE), such that the dot product between a query FDE and a document FDE approximates the
similarity between the original query Tensor and document Tensor. See https://arxiv.org/abs/2405.19504 for further details.

Describe implementation you've considered

  • FDE algorithm implementation
  • FDE function for select
  • FDE function can be applied for insert
  • FDE function can be used within MATCH
  • Python SDK

Documentation, adoption, use case

Additional information

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions