What algorithms are these databases using for fast similarity search?
Are they guaranteed to return the most optimal similar neighbors or will they be sloppy in return for efficiency?
Are they guaranteed to return the most optimal similar neighbors or will they be sloppy in return for efficiency?
The most commonly used one I've seen is HNSW, which greatly speeds up search at the expensive of some extra memory consumption. Recall is also strong - for many large-scale use cases you can get 95%+ with properly tuned parameters.