1.安装包

conda create -n bge-m3 python=3.12
pip install -U FlagEmbedding

 2.密集嵌入使用

from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('BAAI/bge-m3',use_fp16=True)

sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]

embeddings_1 = model.encode(sentences_1,batch_size=12,max_length=8192,)['dense_vecs']
#默认batch_size=256，max_length=512
embeddings_2 = model.encode(sentences_2)['dense_vecs']

#句子相似度计算
similarity = embeddings_1 @ embeddings_2.T
print(similarity)
#[[0.6259035  0.34749585]
#[0.349868   0.6782462 ]]

3.稀疏嵌入使用

from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 

sentences_1 = ["What is BGE M3?", "Defination of BM25"]
#sentences_1 = ["What is embedding model BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]

#return_dense=True			返回稠密向量
#return_sparse=True		    返回稀疏向量
#return_colbert_vecs=False	禁用多向量
#默认参数batch_size=256，max_length=512
output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=False)
output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=False)

#词权重比
print(model.convert_id_to_token(output_1['lexical_weights']))
# [{'What': 0.08356, 'is': 0.0814, 'B': 0.1296, 'GE': 0.252, 'M': 0.1702, '3': 0.2695, '?': 0.04092}, 
#  {'De': 0.05005, 'fin': 0.1368, 'ation': 0.04498, 'of': 0.0633, 'BM': 0.2515, '25': 0.3335}]

#共享词项
lexical_scores = model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_2['lexical_weights'][0])
print(lexical_scores)
# 0.19554451
# 0.2668
print(model.compute_lexical_matching_score(output_1['lexical_weights'][0], output_1['lexical_weights'][1]))
# 0.0

4.多向量使用

from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=True) 

sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]

output_1 = model.encode(sentences_1, return_dense=True, return_sparse=True, return_colbert_vecs=True)
output_2 = model.encode(sentences_2, return_dense=True, return_sparse=True, return_colbert_vecs=True)

#语义相关度
print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][0]))
print(model.colbert_score(output_1['colbert_vecs'][0], output_2['colbert_vecs'][1]))
# 0.7796
# 0.4621

5.混比例使用

from FlagEmbedding import BGEM3FlagModel

model = BGEM3FlagModel('BAAI/bge-m3',  use_fp16=False) 

#sentences_1 = ["What is BGE M3?", "Defination of BM25"]
sentences_1 = ["What is the embedding BGE M3?", "Defination of BM25"]
sentences_2 = ["BGE M3 is an embedding model supporting dense retrieval, lexical matching and multi-vector interaction.", 
               "BM25 is a bag-of-words retrieval function that ranks a set of documents based on the query terms appearing in each document"]

sentence_pairs = [[i,j] for i in sentences_1 for j in sentences_2]

print(model.compute_score(sentence_pairs, 
                          max_passage_length=128, # a smaller max length leads to a lower latency
                          weights_for_different_modes=[0.4, 0.2, 0.4])) # weights_for_different_modes(w) is used to do weighted sum: w[0]*dense_score + w[1]*sparse_score + w[2]*colbert_score

# {
#   'colbert': [0.7796499729156494, 0.4621465802192688, 0.4523794651031494, 0.7898575067520142], 
#   'sparse': [0.195556640625, 0.00879669189453125, 0.0, 0.1802978515625], 
#   'dense': [0.6259765625, 0.347412109375, 0.349853515625, 0.67822265625], 
#   'sparse+dense': [0.482503205537796, 0.23454029858112335, 0.2332356721162796, 0.5122477412223816], 
#   'colbert+sparse+dense': [0.6013619303703308, 0.3255828022956848, 0.32089319825172424, 0.6232916116714478]
# }

# {
#	'colbert': [0.7796695828437805, 0.4162615239620209, 0.45241814851760864, 0.7898669838905334], 
#	'sparse': [0.22662657499313354, 0.0025286339223384857, 0.0, 0.18041232228279114], 
#	'dense': [0.6880049109458923, 0.3501098155975342, 0.3498679995536804, 0.678246259689331], 
#	'sparse+dense': [0.5342121124267578, 0.23424942791461945, 0.2332453429698944, 0.5123016238212585], 
#	'colbert+sparse+dense': [0.6323951482772827, 0.3070542812347412, 0.32091444730758667, 0.6233277320861816]
# }