BM25SparseEmbedding

class langchain_milvus.utils.sparse.BM25SparseEmbedding(corpus: List[str], language: str = 'en')

Sparse embedding model based on BM25.

This class uses the BM25 model in Milvus model to implement sparse vector embedding. This model requires pymilvus[model] to be installed. pip install pymilvus[model] For more information please refer to: https://milvus.io/docs/embed-with-bm25.md

Methods

__init__(corpus[, language])
embed_documents(texts)	Embed search docs.
embed_query(text)	Embed query text.

Parameters:

• corpus (List[str]) –

• language (str) –

__init__(corpus: List[str], language: str = 'en')

Parameters:

• corpus (List[str]) –

• language (str) –

embed_documents(texts: List[str]) → List[Dict[int, float]]

Embed search docs.

Parameters:

texts (List[str]) –

Return type:

List[Dict[int, float]]

embed_query(text: str) → Dict[int, float]

Embed query text.

Parameters:

text (str) –

Return type:

Dict[int, float]