We use vLLM to deploy local LLMs, including embedding models.
Can I use Weaviate with them and how?
Hi @KeroZhai,
It’s lovely to have you with us.
We don’t can’t integrate vLLM directly into Weaviate via a built‑in integration. What I assume you’re doing is generating embeddings externally with vLLM and then passing them to Weaviate — that’s definitely possible.
However, having a direct integration could be a great feature. Could you please submit this as a feature request so the product team can review it?
Best regards,
Mohamed Shahin
Weaviate Support Engineer
(Ireland, UTC±00:00/+01:00)