Using huggingface models with a vectorstoreindexcreator()

[lucas0]

I'm simply trying to load a document (CSV) but I would like to use a custom llm and not the openAI llm. Is that possible?

When trying to run:

from langchain.indexes import VectorstoreIndexCreator
from langchain.document_loaders import DataFrameLoader

loader = DataFrameLoader(dataframe, page_content_column="TRANSLATED_COMMENT")
index = VectorstoreIndexCreator().from_loaders([loader])

I get:

Did not find openai_api_key, please add an environment variable OPENAI_API_KEYwhich contains it, or pass openai_api_key as a named parameter.

I understand that the class instantiation goes straight to openAI API and thats why it requires the key. I would like to know if there is a way to use a HF model instead.