j>dZddlmZmZmZddlmZGddeZy)z+Wrapper around Xinference embedding models.)AnyListOptional) EmbeddingsceZdZUdZeed<eeed< eeed< d deedeeffd Zde ede e e fdZ d ede e fd Z xZ S) XinferenceEmbeddingsaqXinference embedding models. To use, you should have the xinference library installed: .. code-block:: bash pip install xinference If you're simply using the services provided by Xinference, you can utilize the xinference_client package: .. code-block:: bash pip install xinference_client Check out: https://github.com/xorbitsai/inference To run, you need to start a Xinference supervisor on one server and Xinference workers on the other servers. Example: To start a local instance of Xinference, run .. code-block:: bash $ xinference You can also deploy Xinference in a distributed cluster. Here are the steps: Starting the supervisor: .. code-block:: bash $ xinference-supervisor If you're simply using the services provided by Xinference, you can utilize the xinference_client package: .. code-block:: bash pip install xinference_client Starting the worker: .. code-block:: bash $ xinference-worker Then, launch a model using command line interface (CLI). Example: .. code-block:: bash $ xinference launch -n orca -s 3 -q q4_0 It will return a model UID. Then you can use Xinference Embedding with LangChain. Example: .. code-block:: python from langchain_community.embeddings import XinferenceEmbeddings xinference = XinferenceEmbeddings( server_url="http://0.0.0.0:9997", model_uid = {model_uid} # replace model_uid with the model UID return from launching the model ) client server_url model_uidc ddlm}t|| t d| t d||_||_|||_ y#t$r( ddlm}n#t$r}td|d}~wwxYwYtwxYw)Nr) RESTfulClientzCould not import RESTfulClient from xinference. Please install it with `pip install xinference` or `pip install xinference_client`.zPlease provide server URLzPlease provide the model UID) xinference.clientr ImportErrorxinference_clientsuper__init__ ValueErrorr r r )selfr r r e __class__s s/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/embeddings/xinference.pyrzXinferenceEmbeddings.__init__Rs  7   89 9  ;< <$"#J/ +  ; !Y < s5A A>AA> A8' A33A88A>=A>textsreturnc |jj|j}|Dcgc]}|j|ddd}}|Dcgc]}t t t |c}Scc}wcc}w)zEmbed a list of documents using Xinference. Args: texts: The list of texts to embed. Returns: List of embeddings, one for each text. datar embeddingr get_modelr create_embeddinglistmapfloat)rrmodeltext embeddingsrs rembed_documentsz$XinferenceEmbeddings.embed_documentsns %%dnn5NS MRTE " "4 ( 0 3K @U  .88ZS]#Z88 9s !A4 A9r$c|jj|j}|j|}|ddd}t t t |S)zEmbed a query of documents using Xinference. Args: text: The text to embed. Returns: Embeddings for the text. rrrr)rr$r# embedding_resrs r embed_queryz XinferenceEmbeddings.embed_query}sR %%dnn5..t4 !&)!,[9 Cy)**)NN)__name__ __module__ __qualname____doc__r__annotations__rstrrrr"r&r) __classcell__)rs@rrrsAF K &}#LP0"3-0;CC=08 9T#Y 94U 3D 9++U +r*rN)r.typingrrrlangchain_core.embeddingsrrr*rr5s1&&0C+:C+r*