+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Search / Retrieval / Reranking (https://www.datasculpting.ai/inference/forumdisplay.php?fid=61)
+--- Thread: Help with Search / Retrieval / Reranking (/showthread.php?tid=697)
Help with Search / Retrieval / Reranking - thetarunner - 10-03-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
Just sharing a setup that ended up working reasonably well: Gemma, TensorRT-LLM, M3 Max, with a lot of attention on consumer GPUs.
Maybe useful as a starting point for newer folks.
If I had to summarize the lesson so far, it would be that clean setup and observability beat clever guesses.
Re: Help with Search / Retrieval / Reranking - phasetrack - 10-05-2026
Tried to reproduce it just now. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: Help with Search / Retrieval / Reranking - amberpatch25 - 10-06-2026
Good point. I don't think your conclusion is far off. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing. I keep promising myself this is the last rebuild.