# Verba: Changing OpenAI Embeddings & Chunk Size

**URL:** <https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419>\
**Category:** Support\
**Created:** [February 7, 2024, 6:46pm UTC](https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419 "2024-02-07T18:46:41Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![Mike\_Hudson](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/mike_hudson/32/355_2.png) [@Mike\_Hudson](https://forum.weaviate.io/u/Mike_Hudson)\
**Post date:** [February 7, 2024, 6:46pm UTC](https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419/1 "2024-02-07T18:46:41Z")

</div>

Is it possible to easily change the Verba code so we can try using the new OpenAI “text-embedding-3-large” model? We’re curious to see if that improves retrieval for unusual words.

And is it possible to play with changing chunk size?

---

<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:** [February 7, 2024, 7:27pm UTC](https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419/2 "2024-02-07T19:27:11Z")

</div>

Hi!

Verba has now a modularized structure that easily allows new embedding components.

This is the one that controls the current OpenAi embedding:

> <https://github.com/weaviate/Verba/blob/main/goldenverba/components/embedding/ADAEmbedder.py>

We should have some contents around this new model soon.

You can probably experiment with it by adapting this recipe:

> <https://github.com/weaviate/recipes/blob/main/generative-search/generative_search_openai.ipynb>

Let me know if this helps.

Thanks!

---

<div class="post-metadata">

**Author:** ![Mike\_Hudson](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/mike_hudson/32/355_2.png) [@Mike\_Hudson](https://forum.weaviate.io/u/Mike_Hudson)\
**Post date:** [February 7, 2024, 7:45pm UTC](https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419/3 "2024-02-07T19:45:32Z")

</div>

Thanks. I think that means that for now there isn’t an easy way to use the 3072 dimension “text-embedding-3-large” embedder with Verba. [https://openai.com/blog/new-embedding-models-and-api-updates](https://openai.com/blog/new-embedding-models-and-api-updates)

---

<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:** [February 7, 2024, 7:51pm UTC](https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419/4 "2024-02-07T19:51:22Z")

</div>

Not without changing the code.

But hopefully we get it soon.

It would be interesting to point this out as an issue:

> **[Issues · weaviate/Verba](https://github.com/weaviate/Verba/issues)**
>
> Retrieval Augmented Generation (RAG) chatbot powered by Weaviate - Issues · weaviate/Verba

---

<div class="post-metadata">

**Author:** ![Mike\_Hudson](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/mike_hudson/32/355_2.png) [@Mike\_Hudson](https://forum.weaviate.io/u/Mike_Hudson)\
**Post date:** [February 8, 2024, 8:50am UTC](https://forum.weaviate.io/t/verba-changing-openai-embeddings-chunk-size/1419/5 "2024-02-08T08:50:31Z")

</div>

Done – issue created. Thanks Duda.