Would love the community's thoughts on this take on pre-processing unstructured and multimodal data for LLM apps. The thesis is that the classical ETL pattern will come back to the fore in the case of multimodal data, given the steps to make such data valuable for AI app development.
Please let me know your thoughts and please let me know of any questions about Datavolo, powered by Apache NiFi!
2 comments
[ 3.3 ms ] story [ 14.2 ms ] threadPlease let me know your thoughts and please let me know of any questions about Datavolo, powered by Apache NiFi!
no reason to obfuscate the presence of a storage layer used by transformation. then it gets loaded into the final target.
old old is new old again.
several vendors are already doing this. big names. not names that make me think of delicious pasta.
maybe your take is novel enough to make it new new.