dhPtSSKJrJrJrJrJr SSKrSSKJr SSK J r J r SSK J r Jr SrSr"SS \ \5rg) )AnyDictListMappingOptionalN) Embeddings)get_from_dict_or_envpre_init) BaseModel ConfigDictz#sentence-transformers/clip-ViT-B-32icB\rSrSr%Sr\r\\S'Sr \ \S'Sr \\S'Sr \\S 'S r \\\S 'S r\\\S '\r\\S '\"SSS9r\S\S\4Sj5r\S\\\44Sj5rS\\S\\\4SjrS\\S\\\4Sjr S\S\\4Sjr!Sr"g )DeepInfraEmbeddings amDeep Infra's embedding inference service. To use, you should have the environment variable ``DEEPINFRA_API_TOKEN`` set with your API token, or pass it as a named parameter to the constructor. There are multiple embeddings models available, see https://deepinfra.com/models?type=embeddings. Example: .. code-block:: python from langchain_community.embeddings import DeepInfraEmbeddings deepinfra_emb = DeepInfraEmbeddings( model_id="sentence-transformers/clip-ViT-B-32", deepinfra_api_token="my-api-key" ) r1 = deepinfra_emb.embed_documents( [ "Alpha is the first letter of Greek alphabet", "Beta is the second letter of Greek alphabet", ] ) r2 = deepinfra_emb.embed_query( "What is the second letter of Greek alphabet" ) model_idF normalizez passage: embed_instructionzquery: query_instructionN model_kwargsdeepinfra_api_token batch_sizeforbid)extraprotected_namespacesvaluesreturnc([USS5nX!S'U$)z?Validate that api key and python package exists in environment.rDEEPINFRA_API_TOKEN)r )clsrrs `/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/embeddings/deepinfra.pyvalidate_environment(DeepInfraEmbeddings.validate_environment;s(3 )+@ )<$% cSUR0$)zGet the identifying parameters.r)r)selfs r _identifying_params'DeepInfraEmbeddings._identifying_paramsDsDMM**r#inputc<UR=(d 0nSUR3SS.n[R"SUR3UXR S.UES9nURS:wa'[S UR<S UR<35eUR5nUS nU$![R Ran[SU35eSnAff=f![R Ra n[S US UR35eSnAff=f)Nzbearer zapplication/json) Authorizationz Content-Typez'https://api.deepinfra.com/v1/inference/)inputsr)headersjsonz$Error raised by inference endpoint: z)Error raised by inference API HTTP code: z, embeddingszError raised by inference API: z . Response: ) rrrequestspostrr exceptionsRequestException ValueError status_codetextr-JSONDecodeError)r%r( _model_kwargsr,resetr/s r _embedDeepInfraEmbeddings._embedIs"))/R  't'?'?&@A.   I--9$--I %NNTmTC ??c !??CHH.   A<J !""33 ICA3GH H I""22 1!M#((L  s/1B)C)CCCD;DDtextsc /nUVs/sHo0RU3PM nn[S[U5UR5Vs/sHnXEXPR-PM nnUHnX R U5- nM U$s snfs snf)aEmbed documents using a Deep Infra deployed embedding model. For larger batches, the input list of texts is chunked into smaller batches to avoid exceeding the maximum request size. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. r)rrangelenrr<)r%r>r/r6instruction_pairsichunkschunks r embed_documents#DeepInfraEmbeddings.embed_documentsis KPQ54 6 67v>5Q1c"34dooF F !oo"5 6F  E ++e, ,JR s A<Br6cPURU3nURU/5SnU$)zEmbed a query using a Deep Infra deployed embedding model. Args: text: The text to embed. Returns: Embeddings for the text. r)rr<)r%r6instruction_pair embeddings r embed_queryDeepInfraEmbeddings.embed_querys7#445dV<KK!1 23A6 r#)#__name__ __module__ __qualname____firstlineno____doc__DEFAULT_MODEL_IDrstr__annotations__rboolrrrrdictrMAX_BATCH_SIZErintr model_configr rr!propertyrrr&rfloatr<rFrK__static_attributes__rr#r rr s8%Hc$"It6(s(.&s&.#'L(4.'")-#-D$J$,H2FL $4+WS#X%6++DI$tE{*;@T#Y4U 3D0  U r#r)typingrrrrrr0langchain_core.embeddingsrlangchain_core.utilsr r pydanticr r rRrWrrr#r ras2550?*8@)Z@r#