superduper
superduper copied to clipboard
Superduper: Integrate AI models and machine learning workflows with your database to implement custom AI applications, without moving your data. Including streaming inference, scalable model hosting,...
Implement a skeleton `streamlit` application with sidebar dropdown to choose from all available and installed applications.
Users should be able to serve multiple demos for a range of applications in their deployment/ `db`. These demos should not need to be prespecified at a set path, but...
Implement all functionality-specific functions for SuperDuperDB in the base MetadataStore. - delete_parent_child - create_component - create_job - create_parent_child - get_job - update_job - show_components .... For all subclasses, unless customized...
Now we have two different vectors for different types of data backends, and we need to merge them into one.
### What's wrong? We have to update all of the place by hand. Do not use auto replace :D ### How could it be better? _No response_
## Description ## Related Issues ## Checklist - [ ] Is this code covered by new or existing unit tests or integration tests? - [ ] Did you run `make...
This will allow us to force LLMs to emit `Component` instances. ```python from pydantic import BaseModel @property def pydantic(self) -> BaseModel: ... ```
Use `db.apply(self, jobs=False, queue=False)`.
If a user is on 0.5, we should be able to assist them to transition to 0.5+.
### Contact Details [email protected] ### Feature Description As superduper directly operate on db, I would like to see text 2 sql functionality supported. ### Use Case Description Creating dashboards/reports directly...