# Can I use Weaviate with vLLM?

**URL:** <https://forum.weaviate.io/t/can-i-use-weaviate-with-vllm/22177>\
**Category:** General\
**Created:** [December 8, 2025, 2:08am UTC](https://forum.weaviate.io/t/can-i-use-weaviate-with-vllm/22177 "2025-12-08T02:08:49Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![KeroZhai](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/kerozhai/32/7797_2.png) [@KeroZhai](https://forum.weaviate.io/u/KeroZhai)\
**Post date:** [December 8, 2025, 2:08am UTC](https://forum.weaviate.io/t/can-i-use-weaviate-with-vllm/22177/1 "2025-12-08T02:08:49Z")

</div>

We use vLLM to deploy local LLMs, including embedding models.

Can I use Weaviate with them and how?

---

<div class="post-metadata">

**Author:** ![Shahin](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/shahin/32/7944_2.png) [@Shahin](https://forum.weaviate.io/u/Shahin)\
**Post date:** [December 8, 2025, 9:32am UTC](https://forum.weaviate.io/t/can-i-use-weaviate-with-vllm/22177/2 "2025-12-08T09:32:52Z")

</div>

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?

> **[weaviate/weaviate](https://github.com/weaviate/weaviate/issues)**
>
> Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of ...

Best regards,  
Mohamed Shahin  
Weaviate Support Engineer  
(Ireland, UTC±00:00/+01:00)