o Zh@sjddlmZmZmZmZmZmZddlZddlm Z ddl m Z ddl m Z mZmZGddde e ZdS))AnyDictListMappingOptionalTupleN) Embeddingsget_from_dict_or_env) BaseModel ConfigDictmodel_validatorc @seZdZUdZdZeed< dZeed< dZeed< dZ e ed < d Z e eed <e d d ZeddededefddZedeeeffddZ d!deeeefdedeee fddZdeedeee fddZdedee fdd Zd S)"MosaicMLInstructorEmbeddingsaaMosaicML embedding service. To use, you should have the environment variable ``MOSAICML_API_TOKEN`` set with your API token, or pass it as a named parameter to the constructor. Example: .. code-block:: python from langchain_community.llms import MosaicMLInstructorEmbeddings endpoint_url = ( "https://models.hosted-on.mosaicml.hosting/instructor-large/v1/predict" ) mosaic_llm = MosaicMLInstructorEmbeddings( endpoint_url=endpoint_url, mosaicml_api_token="my-api-key" ) zBhttps://models.hosted-on.mosaicml.hosting/instructor-xl/v1/predict endpoint_urlz&Represent the document for retrieval: embed_instructionzError raised by inference API: rate limit exceeded. Response: )dataoutputZoutputsz#No key data or output in response: zUnexpected response type: zError raised by inference API: z . Response: )rrequestspostr exceptionsRequestException ValueError status_codetimesleepr_embedtextr$ isinstancedictlistJSONDecodeError) rr r!payloadr#responseer-Zparsed_responseZ output_keyskeyZ output_item embeddingsrrrr/?sX     z#MosaicMLInstructorEmbeddings._embedtextscs fdd|D}|}|S)zEmbed documents using a MosaicML deployed instructor embedding model. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. csg|]}j|fqSr)r).0r0rrr sz@MosaicMLInstructorEmbeddings.embed_documents..)r/)rr:Zinstruction_pairsr9rrrembed_documents{s z,MosaicMLInstructorEmbeddings.embed_documentsr0cCs|j|f}||gd}|S)zEmbed a query using a MosaicML deployed instructor embedding model. Args: text: The text to embed. Returns: Embeddings for the text. r)rr/)rr0Zinstruction_pairZ embeddingrrr embed_querys z(MosaicMLInstructorEmbeddings.embed_query)F)__name__ __module__ __qualname____doc__rstr__annotations__rrrfloatrrr Z model_configr classmethodrrrpropertyrrrrboolr/r=r>rrrrr s>       < r)typingrrrrrrr'Zlangchain_core.embeddingsrZlangchain_core.utilsr Zpydanticr r r rrrrrs