Quick Start

First, load one of the BGE embedding model:

from FlagEmbedding import FlagAutoModel

model = FlagAutoModel.from_finetuned('BAAI/bge-base-en-v1.5',
                                    query_instruction_for_retrieval="Represent this sentence for searching relevant passages:",
                                    use_fp16=True)

Tip

If there’s difficulty connecting to Hugging Face, you can use the HF mirror instead.

export HF_ENDPOINT=https://hf-mirror.com

Then, feed some sentences to the model and get their embeddings:

Once we get the embeddings, we can compute similarity by inner product:

similarity = embeddings_1 @ embeddings_2.T
print(similarity)