My daily morning pep talk:
โI can do this!โ
โNo you canโt. Youโre dumb as hell.โ
โRight, but Iโm *this stupid* but Iโm *still alive*. Which means I must be a genius.โ
@leo_guinan Yeah it may be good enough for a general recommendations engine. But it was definitely too riddled with mistakes for my timestamp use case ๐ฉ
@leo_guinan Iโll give it another go this weekend. Getting back into the game and as Iโm making a search feature for a broadcaster with over a decade of hour-long episodes, I inherently have to scale pretty fast ๐ซจ.
Tfw when you have to spend as much time programming a fan to cool your old-ass rig while cycling through embeddings generation as you do programming the embeddings automation itself.
@xeraa Just saw you were with elastic! I love their stuff, but found implementing these to be a bit of a blocker. I wonder if I am just missing something? Wouldnโt be the first time.
@xeraa@trychroma makes it very easy to include granular timestamps with embeddings of audio transcripts. Great for enabling a user to pull up audio from a semantic search at the precise moment the relevant audio occurs.
@leo_guinan Honestly surprised that Elasticsearch removed the easy implementation of timestamps. Now seems like a great time to have them, since lots of ppl surely are thinking like us. Could be a great business case for Chroma to focus on.
@leo_guinan I knew that was coming, but didnโt realize how soon. Great timing ๐ธ. Too bad my next compute workload to generate the initial embeddings is two weeks at 24 hr/day ๐