o Zhn @sJdZddlmZmZmZddlmZddlmZm Z GdddeeZ dS)z)Wrapper around text2vec embedding models.)AnyListOptional) Embeddings) BaseModel ConfigDictcseZdZUdZdZeeed<dZe ed<dZ e ed<dZ eeed<dZ e ed <ed d Zddd d e deed e ffddZdeedeeefddZdedeefddZZS)Text2vecEmbeddingsatext2vec embedding models. Install text2vec first, run 'pip install -U text2vec'. The github repository for text2vec is : https://github.com/shibing624/text2vec Example: .. code-block:: python from langchain_community.embeddings.text2vec import Text2vecEmbeddings embedding = Text2vecEmbeddings() embedding.embed_documents([ "This is a CoSENT(Cosine Sentence) model.", "It maps sentences to a 768 dimensional dense vector space.", ]) embedding.embed_query( "It can be used for text matching or semantic search." ) Nmodel_name_or_pathZMEAN encoder_typemax_seq_lengthdevicemodel)Zprotected_namespacesrr kwargsc szzddlm}Wnty}ztd|d}~wwi}|dur$||d<|p.|di||}tjd||d|dS)Nr) SentenceModelzIUnable to import text2vec, please install with `pip install -U text2vec`.r rr)Ztext2vecr ImportErrorsuper__init__)selfrr rreZ model_kwargs __class__r^/var/www/html/lang_env/lib/python3.10/site-packages/langchain_community/embeddings/text2vec.pyr&szText2vecEmbeddings.__init__textsreturncC |j|S)zEmbed documents using the text2vec embeddings model. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. rencode)rrrrrembed_documents; z"Text2vecEmbeddings.embed_documentstextcCr)zEmbed a query using the text2vec embeddings model. Args: text: The text to embed. Returns: Embeddings for the text. r)rr"rrr embed_queryGr!zText2vecEmbeddings.embed_query)__name__ __module__ __qualname____doc__r rstr__annotations__r rr intr rrZ model_configrrfloatr r# __classcell__rrrrr s&      rN) r'typingrrrZlangchain_core.embeddingsrZpydanticrrrrrrrs