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

Persist model definition for k-NN indices #1342

Closed
jmazanec15 opened this issue Dec 11, 2023 · 1 comment
Closed

Persist model definition for k-NN indices #1342

jmazanec15 opened this issue Dec 11, 2023 · 1 comment
Labels
Enhancements Increases software capabilities beyond original client specifications v2.13.0

Comments

@jmazanec15
Copy link
Member

Description

For training, we create a template index in order to initialize components for each segment. Currently, we do not persist the parameters around the model anywhere other than the serialized model component.

This provides a poor user experience because users may forget what parameters a particular model has. Also, from a developers perspective, it makes it difficult to look up information about particular models for optimizations.

Proposed solution

Instead, we should serialize the model information with the model-metadata and in the model system index. This needs to be done in a backwards compatible way. This way, we can look up the model parameters for a particular model easily.

@jmazanec15 jmazanec15 added the Enhancements Increases software capabilities beyond original client specifications label Dec 11, 2023
@ryanbogan ryanbogan added v2.13.0 and removed v2.12.0 labels Feb 21, 2024
@jmazanec15
Copy link
Member Author

Addressed in #1527

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Enhancements Increases software capabilities beyond original client specifications v2.13.0
Projects
None yet
Development

No branches or pull requests

2 participants