+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Training & Customization (https://www.datasculpting.ai/inference/forumdisplay.php?fid=13)
+--- Forum: Model Merging (https://www.datasculpting.ai/inference/forumdisplay.php?fid=57)
+--- Thread: do you even need a vector DB here (/showthread.php?tid=956)
Pages:
1
2
Re: do you even need a vector DB here - sanevault - 10-16-2026
Thanks, that helps. The pattern around token cost has been pretty similar for me. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: do you even need a vector DB here - batchyard - 10-16-2026
My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.
Re: do you even need a vector DB here - cozykite - 10-17-2026
Maybe, but I had the opposite result. I get why that seems right, but on GB200 the bottleneck felt elsewhere. Worth testing the simpler explanation before adopting the more interesting one.