+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Vector Databases (https://www.datasculpting.ai/inference/forumdisplay.php?fid=60)
+--- Thread: Help with Vector Databases: worth it? (/showthread.php?tid=132)
Pages:
1
2
Re: Help with Vector Databases: worth it? - rocmstack25 - 09-07-2026
My first guess would be this: On dual 3090, the easiest win is often to back off the aggressive settings and see whether the problem survives. At this point the real bottleneck is my patience.
Re: Help with Vector Databases: worth it? - southspark - 09-07-2026
I tested this tonight. The issue went away once I changed one setting and restarted the stack cleanly.
Re: Help with Vector Databases: worth it? - orbitbench6 - 09-07-2026
Good point. That matches what I saw on dual 3090. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Help with Vector Databases: worth it? - southspark - 09-07-2026
Thanks, that helps. The pattern around structured output has been pretty similar for me.
Re: Help with Vector Databases: worth it? - relayforge - 09-08-2026
Quote:Thanks, that helps. The pattern around structured output has been pretty similar for me.
Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit.
Re: Help with Vector Databases: worth it? - rocmstack25 - 09-08-2026
Not sure I agree there. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. I keep promising myself this is the last rebuild.