Introduction
The kxi.ml.registry
class is intended to (via Python) provide a central component of any MLOps stack built upon KX technology, providing a location to which information required for model monitoring can be stored, retrained pipelines can be pushed and models for deployment can be retrieved.
The functionality aims to enhance our offering and provide users of the kdb Insights Enterprise and Microservices with:
- A method of introducing their own models generated prior to kdb Insights to kdb Insights Enterprise with wrapped functionality to allow these models to be integrated seamlessly within the limitations enforced by the kdb Insights Enterprise.
- A way to understand the models that the registry has knowledge of and are available to a user.
- A storage location for
Python
andq
models in one location that can wrap these models in a way that upon retrieval complies with the requirements of kdb Insights for deployment.
Sections
The API provided for utilising this functionality is provided in the following sections