BAAI

/

bge-reranker-v2-m3

like 991

Follow

Beijing Academy of Artificial Intelligence 3.73k

You should pass the query and document to the model at the same time, and it will produce a score for how closely the document relates to the query.

scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']], normalize=True)
print(scores) # [0.00027803096387751553, 0.9948403768236574]

@nbroad when i using this code to predict the scores, there is an error as follow:

@saiyanhuang

Ask in the FlagEmbedding repo: https://github.com/FlagOpen/FlagEmbedding