Embeddings

With langchain It's possible to set device CPU for embedding
For example:

Plain Text

from langchain.embeddings.huggingface import HuggingFaceEmbeddings

       embedding_model = HuggingFaceEmbeddings(
            model_name="sentence-transformers/all-mpnet-base-v2", 
            model_kwargs={"device": "cpu"}, # Use CPU for embedding 
       )

I couldn't find anything in the documentation LlamaIndex HuggingFaceEmbedding (from llama_index.embeddings.huggingface import HuggingFaceEmbedding)
Is this possible with LlamaIndex HuggingFaceEmbedding ?

Find answers from the community

Embeddings