Cannes: How Dropbox ML saves $1.7M a year on document preview pre-warming

“Receive file id from Riviera pre-warm path. Riviera collects all file ids eligible for pre-warm. Riviera sends a prediction request with the file id we need a prediction for and the file type.”

“we use an internal service named the Suggest Backend. This service validates the prediction request, then queries for the appropriate signals relevant to that file. Signals are stored in either Edgestore (Dropbox's primary metadata stora…”

“The collected signals are sent to the Predict Service, which encodes the raw signals into a feature vector representing all relevant information for the file, then sends this vector to a model for evaluation. The model uses the feature v…”

“This prediction is then sent back to Riviera, which pre-warms files likely to be previewed up to 60 days in the future.”

“Suggest Backend logs the feature vector, prediction results, and request stats—critical information for troubleshooting performance degradation and latency issues.”