Search / Retrieval / Reranking discussion

[vramport]

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.

[rasterhall]

Maybe, but I had the opposite result. The reported numbers can look compelling, but in ordinary usage I didn't see the same benefit. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[routecraft]

Spent some time on this today and wanted to compare notes.

I've gone back and forth between llama.cpp and Ollama for DeepSeek. The interesting difference for me has been router policy.

Interested in tradeoffs more than fan loyalty.

[turboarch95]

Thanks, that helps. 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.

[cachelab]

Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?

[routecrate]

Thanks, that helps. I don't think your conclusion is far off.

[mangovault67]

Interesting, I hadn't tried that. 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.