Used to perform sparse vector search via text_expansion. Used for when you want to use ELSER model to perform document search.
At build index time, this strategy will create a pipeline that will embed the text using the ELSER model and store the resulting tokens in the index.
At query time, the text will be embedded using the ELSER model and the resulting tokens will be used to perform a text_expansion query.
SparseVectorRetrievalStrategy(
model_id: Optional[str] = None,
) -> SparseRetrievalStrategy