Yeah, I think basic workflows will be easier. It's nice to be able to "split" your LLM logic into multiple components though, rather than having to orchestrate these kinds of workflows with your own custom logic. I see some potential here, if they invest in improving its capabilities. They will also need to provide a mechanism to export / import workflows, so they can easily be shared. Maybe I missed this option, or they'll add it later?
Can’t we change the output of the prompts so that we can supply that output to the iterator? Currently it’s not allowing it to pipe with iterator as iterator is expecting array as the input type
I haven't been able to figure out how to use the iterator yet. Last I checked, the documentation was lacking. Any examples of how to use it. This feature is still in preview unfortunately.
Interesting one. I am curious how complicated the flow will be in real life scenarios and if it’s manageable with all those prompt and debug units
Yeah, I think basic workflows will be easier. It's nice to be able to "split" your LLM logic into multiple components though, rather than having to orchestrate these kinds of workflows with your own custom logic. I see some potential here, if they invest in improving its capabilities. They will also need to provide a mechanism to export / import workflows, so they can easily be shared. Maybe I missed this option, or they'll add it later?
Can’t we change the output of the prompts so that we can supply that output to the iterator? Currently it’s not allowing it to pipe with iterator as iterator is expecting array as the input type
I haven't been able to figure out how to use the iterator yet. Last I checked, the documentation was lacking. Any examples of how to use it. This feature is still in preview unfortunately.
Don't this have any memory concept
suppose i say my name is shubham and in next query i ask it what's my name