Mala Mahadevan wraps up a three-parter on how DiskANN works:
In Part 1, we saw how ‘Vamana’ represents vectors as nodes, connects them with edges, and uses greedy graph traversal to avoid comparing a query against every vector in the dataset. In Part 2, we investigated how PQ gave us compact representations for inexpensive distance calculations, caching kept useful graph nodes close, how SSDs provided capacity, and beam search allowed multiple promising nodes to be expanded together.
In this last part, we will be exploring how we use the parameters to tune DiskANN.
Click through to learn more about these parameters and what they do.