GitHub user gupta-sahil01 added a comment to the discussion: Ambient "operator recommender" — predictive next-operator suggestions on the canvas
So this was just an idea. I don't have the specifics yet on how I'm gonna use the information. I was thinking that first I would filter the operator catalog to those whose input schema is satisfiable with the current output schema. Ranking could be done using a frequency model and then for the top few candidates, use an LLM to read data, infer intent and generate the rationale. I don't know if this makes sense or not. GitHub link: https://github.com/apache/texera/discussions/5240#discussioncomment-17094621 ---- This is an automatically sent email for [email protected]. To unsubscribe, please send an email to: [email protected]
