[jeungsp]

Nothing fundamentally stops a postgres implementation being equally performant as something like Qdrant.

Fundamentally, an index’s performance is based on the hardware and the algorithm and the quality of implementation. Any optimizations Qdrant can make, we can also make.

We will be benchmarking ourselves against all of the other standalone database options as well and we’ll be working to try and outperform them. Excited to share those once we have them.

We are curious – what are you most concerned about? SELECT time? INDEX size? Latency? Throughput?

[swalsh]

I never spoke of performance, clearly postgres can match performance. It just seems more expensive in terms of dollars to do so.