192 karma · joined February 16, 2023
I figured I'd sort it all out by the time I moved. However, I may have been a little too relaxed about the situation and stressed out about other stuff
all based on consulting calls and advisory work (i sell the implementation so sorry i don't post one click deploys)
I'd recommend taking a look at lancedb as they support text, vectors, and sql.
high relevancy scores are not percentages, they only make sense in 'ordering' but 0.7 does not mean relevant.
but .9 vs .7 means 'maybe more relevant.
1) are there filters we need to build 2) do we have inventory
this was a quick post that i wrote up after a 30 minute call with someone, mostly notes to take in preparation for a bigger talk im giving.
mostly training really interesting models, optimizing recommendation systems, designing frameworks. i was having a lot of fun.
closest thing people gave me was DQT but 10 months of PT didnt help and MRA / XRAY found nothing
exiting what? i have like some money saved up i took 2 years off work, i have about 6-7 years run way, but like turns out i like building things?
good liars deceive others great liars deceive themselves,
my goal was to call out that i do believe these are true, but i must acknowlege they are lies