ywmario·há 3 anos·discussJudging from the qps and cost columns, milvus/zilliz is much more efficient! It's probably a good choice for large scale data.It would be nice to have another column to compare the largest scales these DBs can support.
ywmario·há 3 anos·discussI have been under the impression that the embedded vector is the one actually matters. Token is just another format.
ywmario·há 3 anos·discussMilvus standalone is pretty neat. I made it successfully run on the first try.
ywmario·há 3 anos·discussI'm very sure milvus supports it. Milvus calls it hybrid search though: https://milvus.io/docs/hybridsearch.md#Conduct-a-hybrid-vect...
It would be nice to have another column to compare the largest scales these DBs can support.