rusackas commented on issue #32408:
URL: https://github.com/apache/superset/issues/32408#issuecomment-2718419571

   I think the main thing I'd look for from any AI/LLM proposal in Superset is 
how to _generalize_ the approach. I think we need to have a consistent way we 
add individual features (there could be _many_ of them) so they define 
consistent patterns in the UI/UX. I also think we should not be locked into any 
single Model/Service, and should use tools like LangChain/LangGraph to reply on 
the admin's configuration (so long as these packages are license-compatible). 
The more diverse we can make the offering, the better. This may also intersect 
with the Extensions architecture happening in parallel, so we should be asking 
ourselves "which of these features should be core to Superset, and which could 
be Extensions?"


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to