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

[FEATURE] Is possible to add new KNNs using microservices? That broadens the KNNs that can be used as backends #1328

Open
ksrinivs64 opened this issue Nov 28, 2023 · 2 comments
Labels
enhancement Features Introduces a new unit of functionality that satisfies a requirement

Comments

@ksrinivs64
Copy link

Is your feature request related to a problem?
I'd like to be able to call out to a KNN written in Python not C (PyNNDescent). It has support for computing Hamming distances over integer vectors, something that most other KNNs do not support. However, trying to POST from the library following code for NMS and FAISS seems to run into security problems even when URL permissions are given to the plugin to POST. The POST never happens, nothing happens in the logs, and the system behaves like it has no results.

What solution would you like?
A way to call out to a vector database using HTTP.

What alternatives have you considered?
We tried launching a Python interpreter through Jep but that failed due to threading issues.

Do you have any additional context?
Add any other context or screenshots about the feature request here.

@navneet1v
Copy link
Collaborator

navneet1v commented Dec 5, 2023

Hi @ksrinivs64,
Thanks for creating the feature request. We have been thinking about separating the core K-NN engines via pluggable interfaces. Using those interfaces users can integrate their custom code to call any library or endpoint as per their use case.

But right now we don't have a github issue around this. But I will try to create one and link the issue here. But having said that, it will take some time to develop that feature, as this will be a massive undertaking.

cc: @vamshin , @jmazanec15 , @heemin32

@navneet1v navneet1v added the Features Introduces a new unit of functionality that satisfies a requirement label Dec 5, 2023
@ksrinivs64
Copy link
Author

ksrinivs64 commented Dec 5, 2023 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement Features Introduces a new unit of functionality that satisfies a requirement
Projects
Status: Backlog
Development

No branches or pull requests

2 participants