# Multi-Lingual Cosine Similarity Search
**URL:** https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647
**Category:** Support
**Created:** [March 8, 2024, 12:29am UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647 "2024-03-08T00:29:06Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@SomebodySysop](https://forum.weaviate.io/u/SomebodySysop)
#### Post date: [March 8, 2024, 12:29am UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647/1 "2024-03-08T00:29:06Z")
### Description
I have added some Hebrew texts to my embeddings. I use NearText queries under the Tex2Vec OpenAI transformer.
I am curious if these queries will match similar contexts in the Hebrew texts?
### Server Setup Information
- Weaviate Server Version:
- Deployment Method: WCS
- Multi Node? Number of Running Nodes:
- Client Language and Version: 1.23.10
### Any additional Information
---
### Author:  [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)
#### Post date: [March 8, 2024, 2:30pm UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647/2 "2024-03-08T14:30:52Z")
Hi!
It will depend on the LLM inference you use.
If it supports your language, it should work fine as long as Weaviate is aware ๐
Let me know if this helps!
---
### Author:  [@SomebodySysop](https://forum.weaviate.io/u/SomebodySysop)
#### Post date: [March 8, 2024, 8:06pm UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647/3 "2024-03-08T20:06:45Z")
gpt-4 is the model. It supports Hebrew.
> [@DudaNogueira](#):
>
> as long as Weaviate is aware
How is Weaviate made aware?
---
### Author:  [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)
#### Post date: [March 8, 2024, 9:34pm UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647/4 "2024-03-08T21:34:01Z")
When you create a collection, you can specify a vectorizer model.
As long as this vectorizer model support multi language, and your class was configured to use it, it should work.
> **[Manage collections | Weaviate - Vector Database](https://weaviate.io/developers/weaviate/manage-data/collections#specify-vectorizer-settings)**
>
> Every object in Weaviate belongs to exactly one collection. Use the examples on this page to manage your collections.
for example:
```auto
import weaviate.classes as wvc
client.collections.create(
"Article",
vectorizer_config=wvc.config.Configure.Vectorizer.text2vec_cohere(
model="embed-multilingual-v2.0",
vectorize_collection_name=True
),
)
```
Cohere has a nice multi language model:
> **[Multilingual Embed Models](https://docs.cohere.com/docs/multilingual-language-models)**
>
> Cohere offers multilingual language models that map text to a semantic vector space, improving search results and enabling use cases such as multilingual semantic search, customer feedback aggregation, and cross-lingual content moderation. The model...
Let me know if this helps ๐
---
### Author:  [@SomebodySysop](https://forum.weaviate.io/u/SomebodySysop)
#### Post date: [March 8, 2024, 11:46pm UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647/5 "2024-03-08T23:46:46Z")
Yes, thanks.
Actually, I want to create a new cluster and use text-embedding-3-large as my embedding model. Do you have a way of finding out if it is multi-lingual? I have asked on the OpenAI developer forum, but so far nobody seems to know.
---
### Author:  [@SomebodySysop](https://forum.weaviate.io/u/SomebodySysop)
#### Post date: [March 9, 2024, 9:24am UTC](https://forum.weaviate.io/t/multi-lingual-cosine-similarity-search/1647/6 "2024-03-09T09:24:13Z")
It looks like regardless of whether the model is multi-lingual or not, if I add the English translation to the embedding, the cosine similarity search will find it. Thatโs good to know.
