[ibestvina]

Incredible work, and great explanation, thank you. Could you comment more on the cost of running this (e.g. per query or per hour, or however it's set up)? Where are you running the model from?

Also, could you provide more details on the cross encoder used for reranking?

Btw, if you already have all these song embeddings, it would be very interesting to be able to pick a song, and get all the similar ones in a playlist (sort of like "Song radio" on Spotify)!

[totony]

Having worked with the same tech, I'd assume this is pretty inexpensive both to train and run. Probably in the low 1000s (maybe even mid 100s?) to train. knn search on 35k entries is pretty simple. The most expensive is probably the cross encoder (both to train and to run). Would also be interested to know