Experiments with (auto)scaling for the demo app on Raspberry Pi built for the vector-based retrieval system described in the post "Building Music Playlists Recommendation System."
Demo app built on Raspberry Pi for the sequence-to-sequence model described in the post "Building Music Playlists Recommendation System"
Documenting the lessons from integrating vector databases into our discovery system outlined in "Bit Of This, Bit Of That: Revisiting Search & Discovery"
Documenting the lessons from transitioning to a microservices architecture in our discovery system outlined in "Bit Of This, Bit Of That: Revisiting Search & Discovery"
Documenting the lessons from our initial monolithic approach in our discovery system outlined in "Bit Of This, Bit Of That: Revisiting Search & Discovery"
Genre-based categorization forms a vital part of music discovery. What started several decades ago as just a way to market and segment artists into well-defined categories today forms the core of the user experience in music apps in the form of …
With an aim towards playlist discovery and recommendation, we leverage sequence-to-sequence modeling to learn a fixed-length representation of playlists in an unsupervised manner.
Content taken from our paper titled “Representation, Exploration, and Recommendation Of Music Playlists”