U ™ÀÂh< ã@sFdZddlmZmZmZddlmZddlmZGdd„deeƒZ dS)z)Wrapper around text2vec embedding models.é)ÚAnyÚListÚOptional)Ú Embeddings)Ú BaseModelcs¬eZdZUdZdZeeed<dZe ed<dZ e ed<dZ eeed<dZ e ed <ddd œe eee d œ‡fd d „Zeeeeedœdd„Zeeedœdd„Z‡ZS)ÚText2vecEmbeddingsa–text2vec embedding models. Install text2vec first, run 'pip install -U text2vec'. The gitbub 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." ) NÚmodel_name_or_pathZMEANÚ encoder_typeéÚmax_seq_lengthÚdeviceÚmodel©r r)r rÚkwargsc s€zddlm}Wn,tk r<}ztdƒ|‚W5d}~XYnXi}|dk rR||d<|pb|f||—Ž}tƒjf||dœ|—ŽdS)Nr)Ú SentenceModelzIUnable to import text2vec, please install with `pip install -U text2vec`.rr)Ztext2vecrÚ ImportErrorÚsuperÚ__init__)Úselfr rrrÚeZ model_kwargs©Ú __class__©úK/tmp/pip-unpacked-wheel-9gdii04g/langchain_community/embeddings/text2vec.pyr$sÿýzText2vecEmbeddings.__init__)ÚtextsÚreturncCs |j |¡S)zÀEmbed documents using the text2vec embeddings model. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. ©r Úencode)rrrrrÚembed_documents9s z"Text2vecEmbeddings.embed_documents)ÚtextrcCs |j |¡S)z¦Embed a query using the text2vec embeddings model. Args: text: The text to embed. Returns: Embeddings for the text. r)rrrrrÚ embed_queryEs zText2vecEmbeddings.embed_query)Ú__name__Ú __module__Ú __qualname__Ú__doc__rrÚstrÚ__annotations__r rr Úintr r rrÚfloatrr Ú __classcell__rrrrr s    üû rN) r$ÚtypingrrrZlangchain_core.embeddingsrZlangchain_core.pydantic_v1rrrrrrÚs