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.

Sign up for GitHub

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

Jump to bottom

[Feature Request] Smaller memory-consumption for JSON arrays of numbers. (To improve vector search) #3849

Open

javiabellan opened this issue Sep 11, 2023 · 1 comment

Assignees

Labels

javiabellan commented Sep 11, 2023 •

edited

Loading

Issue originally posted in RedisJSON: RedisJSON/RedisJSON#1087

Regarding this issue, i think the best the RediSearch can do for vector search is:

Allow having multiple vectors in the same byte array hash field. Because at indexing time we will know the vector dimension and its numeric representation (currently fp32 or fp64); therefore the number of vectors in the byte array can be calculated. This idea is inspired from indexing json array of N vectors
(less important): Allow fp16, or even uint8 vector represenations. (like FAISS and USearch do)

javiabellan assigned adrianoamaral

adrianoamaral added the feature label

github-actions bot commented Nov 13, 2023

This issue is stale because it has been open for 60 days with no activity.

github-actions bot added the stale label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment