Skip to content

captions embeddings #1

Description

@sujjeee

hey! just general curiosity. what if we create an image caption, convert it into vectors, and store it in a vector db? then, when someone uploads an image, we create a caption, convert it into a vector, and perform a similarity search to find similar images.

isn't that a good solution for image similarity search?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions