Individual per-class vectorizer parameter in weaviate

[pashva]

Checked

• I searched existing ideas and did not find a similar one
• I added a very descriptive title
• I've clearly described the feature request and motivation for it

Feature request

Weaviate allows users to mention a key value pair of vectorizer while creating a class so that users can leverage local vectorization or basically vectorization of their choice for each class.
Example

class_obj = {
    "class": "Article",
    "properties": [
        {
            "name": "title",
            "dataType": ["text"],
        },
    ],
    "vectorizer": "text2vec-openai"  # this could be any vectorizer
}

Currently this is not implemented in langchain and only a default type schema gets created with a singular data property when using the from_documents or from_texts function calls.

Motivation

I was using langchain weaviate modules as my library to manage my weaviate storage. But the main problem was that I wanted to use weaviate's local text2vec transformers but in langchain there was no way to pass this argument to make sure that particular documents are embedded with particular vectorizers.

Proposal (If applicable)

The solution is pretty straightforward.

1.) Allow users to pass a vecotorizer param inside the from_documents function.
2.) If this argument exists then set it before creating the schema, else keep it as "none" which is the default behaviour.

I have implemented this in my local system.
Need a feature request issue to tag it in. If not how should i proceed with this?