# Emmanuel Katto Dubai : Exploring Alternatives to Custom Vectorizer for Weaviate Cloud

**URL:** <https://forum.weaviate.io/t/emmanuel-katto-dubai-exploring-alternatives-to-custom-vectorizer-for-weaviate-cloud/7718>\
**Category:** General\
**Created:** [November 20, 2024, 5:19am UTC](https://forum.weaviate.io/t/emmanuel-katto-dubai-exploring-alternatives-to-custom-vectorizer-for-weaviate-cloud/7718 "2024-11-20T05:19:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![emmanuelkatto24](https://avatars.discourse-cdn.com/v4/letter/e/ea666f/32.png) [@emmanuelkatto24](https://forum.weaviate.io/u/emmanuelkatto24)\
**Post date:** [November 20, 2024, 5:19am UTC](https://forum.weaviate.io/t/emmanuel-katto-dubai-exploring-alternatives-to-custom-vectorizer-for-weaviate-cloud/7718/1 "2024-11-20T05:19:39Z")

</div>

HI Everyone, I’m Emmanuel Katto from Dubai, United Arab Emirates (UAE) We’re currently using PyTorch and the Transformers library in a custom Vectorizer class with the model `sentence-transformers/all-MiniLM-L6-v2` to vectorize SQL, Python, and YAML files before sending them to Weaviate Cloud. However, this setup relies on a resource-intensive PyTorch and Transformers stack.

Has anyone successfully set up a similar process directly within Weaviate Cloud, or found a more lightweight alternative for vectorization? Any suggestions for optimizing or simplifying this workflow would be greatly appreciated!

Regards  
**Emmanuel Katto**

---

<div class="post-metadata">

**Author:** ![DudaNogueira](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/dudanogueira/32/7846_2.png) [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)\
**Post date:** [November 20, 2024, 7:30pm UTC](https://forum.weaviate.io/t/emmanuel-katto-dubai-exploring-alternatives-to-custom-vectorizer-for-weaviate-cloud/7718/2 "2024-11-20T19:30:42Z")

</div>

hi @emmanuelkatto24 !!

We will soon allow running this kind of models from within Weaviate Cloud.

You can ask to be notified about the availability of this new feature here:

> **[Weaviate Cloud | Embedding](https://console.weaviate.cloud/apps/embedding)**
>
> Embedding service

Meanwhile, one thing you could do is running your inference model in your own cloud, provide an openai like api, and point your collection there.

For example, check this doc on Weaviate + KubeAi:

> **[KubeAI + Weaviate | Weaviate](https://weaviate.io/developers/weaviate/model-providers/kubeai)**
>
> KubeAI provides offers a wide range of models for natural language processing and generation through OpenAI-style API endpoints. Weaviate seamlessly integrates with KubeAI's APIs, allowing users to leverage any KubeAI models directly within the...

Let me know if that helps!