GitHub user gupta-sahil01 added a comment to the discussion: Ambient "operator 
recommender" — predictive next-operator suggestions on the canvas

Thanks for sharing this. My idea is to slot in as a complementary layer rather 
than a replacement: take your top-K candidates, add any UDFs in the user's 
workflow/scope as additional candidates, then re-rank with an LLM that has the 
schema, a small tuple sample, and (for UDFs) the source code as context.

GitHub link: 
https://github.com/apache/texera/discussions/5240#discussioncomment-17098690

----
This is an automatically sent email for [email protected].
To unsubscribe, please send an email to: [email protected]

Reply via email to