BGE on Hugging Face
BGE models on the HuggingFace are one ofthe best open-source embedding models.BGE model is created by theBeijing Academy of Artificial Intelligence (BAAI).
BAAIis a private non-profit organization engaged in AI research and development.
This notebook shows how to useBGE Embeddings throughHugging Face
%pip install--upgrade--quiet sentence_transformers
from langchain_community.embeddingsimport HuggingFaceBgeEmbeddings
model_name="BAAI/bge-small-en"
model_kwargs={"device":"cpu"}
encode_kwargs={"normalize_embeddings":True}
hf= HuggingFaceBgeEmbeddings(
model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs
)
API Reference:HuggingFaceBgeEmbeddings
Note that you need to passquery_instruction="" formodel_name="BAAI/bge-m3" seeFAQ BGE M3.
embedding= hf.embed_query("hi this is harrison")
len(embedding)
384
Related
- Embedding modelconceptual guide
- Embedding modelhow-to guides