Embeddings discussion

[ggufwire22]

Interesting, I hadn't tried that. I ended up in about the same place using Ollama. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[edgecoast]

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher. The surprise was that memory pressure showed up before throughput collapsed.

[vramscope]

A couple questions before I guess too hard. Is this local-only or are you routing anything externally?