Help with Search / Retrieval / Reranking

[thetarunner]

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.

[phasetrack]

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.

[amberpatch25]

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.