Is there any resources of insight about memory cosumption of Voyager with around 100milions embeddings?

[Lorenzoncina]

No description provided.

[stephen29xie]

Hi @Lorenzoncina. The number of embeddings in the index is just one factor that affects the memory usage so it is difficult to know based on that alone. Other significant factors are the dimensionality of the vectors, the StorageDataType of the vector values, and M value used for index construction. You can use a reduced precision StorageDataType and smaller M value to reduce memory usage, but at the cost of lower precision and recall.