# Mistral-embed as custom vectorizer
**URL:** https://forum.weaviate.io/t/mistral-embed-as-custom-vectorizer/1602
**Category:** General
**Tags:** python
**Created:** [February 29, 2024, 11:33am UTC](https://forum.weaviate.io/t/mistral-embed-as-custom-vectorizer/1602 "2024-02-29T11:33:04Z")
**Posts on this page:** 2
**Page:** 1
### Author:  [@mehmet\_ali\_abdulhayo](https://forum.weaviate.io/u/mehmet_ali_abdulhayo)
#### Post date: [February 29, 2024, 11:33am UTC](https://forum.weaviate.io/t/mistral-embed-as-custom-vectorizer/1602/1 "2024-02-29T11:33:04Z")
As a novice to llama index and weaviate, I am following the codes in [Structured Hierarchical Retrieval - LlamaIndex 🦙 v0.10.14](https://docs.llamaindex.ai/en/stable/examples/query_engine/multi_doc_auto_retrieval/multi_doc_auto_retrieval.html).
Here weaviate uses the default openai embedding models. How can I customize it with **mistral-embed**. From my searches, if I am not mistaken, I need to introduce schema mentioning which text2vec to be used. But in the code I keep failing how to do this.
How to adjust the code below so that it would create the embeddings based ona custom embedding model?
> import weaviate
>
> auth\_config = weaviate.AuthApiKey(
> api\_key=“XRa15cDIkYRT7AkrpqT6jLfE4wropK1c1TGk”
> )
> client = weaviate.Client(
> “[https://llama-index-test-v0oggsoz.weaviate.network](https://llama-index-test-v0oggsoz.weaviate.network)”,
> auth\_client\_secret=auth\_config,
> )
>
> class\_name = “LlamaIndex\_docs”
>
> from llama\_index.vector\_stores.weaviate import WeaviateVectorStore
> from llama\_index.core import VectorStoreIndex, StorageContext
>
> vector\_store = WeaviateVectorStore(
> weaviate\_client=client, index\_name=class\_name
> )
> storage\_context = StorageContext.from\_defaults(vector\_store=vector\_store)
>
> doc\_index = VectorStoreIndex.from\_documents(
> docs, storage\_context=storage\_context
> )
---
### Author:  [@DudaNogueira](https://forum.weaviate.io/u/DudaNogueira)
#### Post date: [February 29, 2024, 2:38pm UTC](https://forum.weaviate.io/t/mistral-embed-as-custom-vectorizer/1602/2 "2024-02-29T14:38:21Z")
Hi!
When using those integrations, is a good one to initiate the class beforehand an have the correct vectorizer configured.
I have not played with llamaindex yet, only with langchain, and I did exactly that in a integration in our recipes:
> **[GitHub - weaviate/recipes: This repository shares end-to-end notebooks on how...](https://github.com/weaviate/recipes)**
>
> This repository shares end-to-end notebooks on how to use various features and integrations with Weaviate at the core! - weaviate/recipes
This will allow you run queries thru llama index as well as directly in Weaviate.
I believe you can run this model thru Hugging Face? [text2vec-huggingface | Weaviate - Vector Database](https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-huggingface)
Another options is using text2vec-transformers, where you can customize a container with the model you want:
> **[text2vec-transformers | Weaviate - Vector Database](https://weaviate.io/developers/weaviate/modules/retriever-vectorizer-modules/text2vec-transformers#model-selection)**
>
> Overview
Let me know if that helps.