j ddlmZmZmZmZddlmZddlmZddl m Z m Z ddl m Z Gdde eeeeefZGdd e eZy ) )AnyDictListOptional) Embeddings)pre_init) BaseModel ConfigDict)ContentHandlerBaseceZdZdZy)EmbeddingsContentHandlerzContent handler for LLM class.N)__name__ __module__ __qualname____doc__{/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/embeddings/sagemaker_endpoint.pyr r s(rr c $eZdZUdZ dZeed<dZeed< dZ eed< dZ e eed< e ed< dZ e eed < dZe eed < ed d d ZededefdZdeedeeefdZ ddeededeeefdZdedeefdZy)SagemakerEndpointEmbeddingsaCustom Sagemaker Inference Endpoints. To use, you must supply the endpoint name from your deployed Sagemaker model & the region where it is deployed. To authenticate, the AWS client uses the following methods to automatically load credentials: https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html If a specific credential profile should be used, you must pass the name of the profile from the ~/.aws/credentials file that is to be used. Make sure the credentials / roles used have the required policies to access the Sagemaker endpoint. See: https://docs.aws.amazon.com/IAM/latest/UserGuide/access_policies.html Nclient endpoint_name region_namecredentials_profile_namecontent_handler model_kwargsendpoint_kwargsTforbidr)arbitrary_types_allowedextraprotected_namespacesvaluesreturnc2|jd|S ddl} |d|j|d}n|j}|jd|d|d<|S#t$r}t d ||d}~wwxYw#t $r t d wxYw) z.Dont do anything if client provided externallyrNrr) profile_namezsagemaker-runtimer)rzCould not load credentials to authenticate with AWS client. Please check that credentials in the specified profile name are valid. zRCould not import boto3 python package. Please install it with `pip install boto3`.)getboto3Sessionr Exception ValueError ImportError)clsr#r(sessiones rvalidate_environmentz0SagemakerEndpointEmbeddings.validate_environmentus ::h  +MX   45A#mm%+,F%G,G $mmoG#*>>'VM5J$2$x    //0c3   >  s)BAA!! A>*A99A>>BBtextscttd|}|jxsi}|jxsi}|jj ||}|jj }|jj} |jjd|j|||d|}|jj|dS#t$r}td|d}~wwxYw)z3Call out to SageMaker Inference embedding endpoint.c&|jddS)N  )replace)xs rz=SagemakerEndpointEmbeddings._embedding_func..s199T3#7r) EndpointNameBody ContentTypeAcceptz$Error raised by inference endpoint: Nr:r)listmaprrrtransform_input content_typeacceptsrinvoke_endpointrr*r+transform_output) selfr1 _model_kwargs_endpoint_kwargsbodyr@rAresponser/s r_embedding_funcz+SagemakerEndpointEmbeddings._embedding_funcsS7?@))/R //52##33E=I++88 &&.. I2t{{22!//(  # H##44Xf5EFF ICA3GH H Is+C C%C  C% chunk_sizecg}|t|kDr t|n|}tdt||D]*}|j||||z}|j|,|S)aCompute doc embeddings using a SageMaker Inference Endpoint. Args: texts: The list of texts to embed. chunk_size: The chunk size defines how many input texts will be grouped together as request. If None, will use the chunk size specified by the class. Returns: List of embeddings, one for each text. r)lenrangerIextend)rDr1rJresults _chunk_sizeirHs rembed_documentsz+SagemakerEndpointEmbeddings.embed_documentssd$.U$;c%j q#e*k2A++E!a+o,FGH NN8 $3rtextc,|j|gdS)zCompute query embeddings using a SageMaker inference endpoint. Args: text: The text to embed. Returns: Embeddings for the text. r)rI)rDrSs r embed_queryz'SagemakerEndpointEmbeddings.embed_querys##TF+A..r)@)rrrrrr__annotations__rstrrrrr rrrr model_configrr0rfloatrIintrRrUrrrrrs!"<FCM3,KP.2hsm2.- &$(L(4.'1&*OXd^*  $H2L"$"4""HGT#YG4U 3DG435#Y,/ d5k , / /U /rrN)typingrrrrlangchain_core.embeddingsrlangchain_core.utilsrpydanticr r +langchain_community.llms.sagemaker_endpointr rXrZr rrrrrasK,,0)*J)1$s)T$u+=N2NO)D/)ZD/r