+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: RAG & Knowledge Systems (https://www.datasculpting.ai/inference/forumdisplay.php?fid=14)
+--- Forum: Embeddings (https://www.datasculpting.ai/inference/forumdisplay.php?fid=59)
+--- Thread: Help with Embeddings: early impressions (/showthread.php?tid=234)
Help with Embeddings: early impressions - vectorshed43 - 09-12-2026
Thought I'd post a small recipe because a lot of threads ask similar things.
This isn't revolutionary, but the combination of Ollama and 7900 XTX felt surprisingly usable once I tuned around structured output.
If someone wants the exact settings I can clean them up and post them.
Re: Help with Embeddings: early impressions - vectorshed43 - 09-13-2026
That matches what I was seeing. I ended up in about the same place using vLLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.
Re: Help with Embeddings: early impressions - edgecoast - 09-13-2026
Quote:That matches what I was seeing. I ended up in about the same place using vLLM. I got better results once I stopped chasing one metric and just looked
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.
Re: Help with Embeddings: early impressions - quantnest - 09-14-2026
I'd approach it in a boring order. Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at MoE serving. Not glamorous advice, but repeatable baselines save a lot of time.
Re: Help with Embeddings: early impressions - paperport64 - 09-14-2026
Can you fill in a bit more context? Is this local-only or are you routing anything externally?
Re: Help with Embeddings: early impressions - vectorshed43 - 09-14-2026
Did a small comparison this afternoon. 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 Embeddings: early impressions - vramscope - 09-14-2026
What worked for me was pretty simple. If you're on LM Studio, I'd confirm the version first and then reduce variables until the behavior is obvious.
Re: Help with Embeddings: early impressions - quantnest - 09-14-2026
Appreciate the detail. I ended up in about the same place using Ollama. Worth rechecking your defaults though, because one bad assumption can make the rest of the thread look confusing.
Re: Help with Embeddings: early impressions - ggufwire22 - 09-14-2026
that fixed it for me too.
Re: Help with Embeddings: early impressions - vramscope - 09-14-2026
Quote:that fixed it for me too.
Interesting, I hadn't tried that. I don't think your conclusion is far off.