NgG`ddlmZmZmZmZddlmZddlmZm Z m Z dZ GddeeZ dS))AnyDictListOptional) Embeddings) BaseModel ConfigDictFieldz'sentence-transformers/all-mpnet-base-v2cHeZdZUdZeZeed< dZe eed< e e Z e eefed< e e Ze eefed< dZeed < dZeed < d effd Zed dZdeedeeefdZdedeefdZxZS)HuggingFaceEmbeddingsa`HuggingFace sentence_transformers embedding models. To use, you should have the ``sentence_transformers`` python package installed. Example: .. code-block:: python from langchain_huggingface import HuggingFaceEmbeddings model_name = "sentence-transformers/all-mpnet-base-v2" model_kwargs = {'device': 'cpu'} encode_kwargs = {'normalize_embeddings': False} hf = HuggingFaceEmbeddings( model_name=model_name, model_kwargs=model_kwargs, encode_kwargs=encode_kwargs ) model_nameN cache_folder)default_factory model_kwargs encode_kwargsF multi_process show_progresskwargsc tjdi| ddl}n"#t$r}td|d}~wwxYw|j|jfd|ji|j|_dS)z$Initialize the sentence_transformer.rNzrCould not import sentence_transformers python package. Please install it with `pip install sentence-transformers`.r) super__init__sentence_transformers ImportErrorSentenceTransformerr rr_client)selfrrexc __class__s h/var/www/html/ai-engine/env/lib/python3.11/site-packages/langchain_huggingface/embeddings/huggingface.pyrzHuggingFaceEmbeddings.__init__0s""6"""  ( ( ( ( (   N   A,@ O  *.*; ?C?P   s! A;Aforbidr)extraprotected_namespacestextsreturncddl}ttd|}|jrO|j}|j||}|j|n|jj |fd|j i|j }t|trtd|S)zCompute doc embeddings using a HuggingFace transformer model. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. rNc.|ddS)N  )replace)xs r z7HuggingFaceEmbeddings.embed_documents..Os199T3#7#7show_progress_barzHExpected embeddings to be a Tensor or a numpy array, got a list instead.)rlistmaprrstart_multi_process_poolencode_multi_processrstop_multi_process_poolencoderr isinstance TypeErrortolist)rr$rpool embeddingss r embed_documentsz%HuggingFaceEmbeddings.embed_documentsDs %$$$S77??@@   <88::D::5$GGJ ! 5 M Md S S S S,,"&"4$J j$ ' ' &    """r-textc:||gdS)zCompute query embeddings using a HuggingFace transformer model. Args: text: The text to embed. Returns: Embeddings for the text. r)r:)rr;s r embed_queryz!HuggingFaceEmbeddings.embed_querycs##TF++A..r-)__name__ __module__ __qualname____doc__DEFAULT_MODEL_NAMEr str__annotations__rrr dictrrrrrboolrrr model_configrfloatr:r= __classcell__)rs@r r r sr&)J((("&L(3-&&&K#(5#>#>#>L$sCx.>>>d%*E$$?$?$?M4S>???k M4(M4)         :L #T#Y#4U 3D####> / /U / / / / / / / /r-r N) typingrrrrlangchain_core.embeddingsrpydanticrr r rBr rr-r rMs,,,,,,,,,,,,0000001111111111>c/c/c/c/c/Izc/c/c/c/c/r-