jddlmZddlmZmZmZmZmZmZm Z m Z ddl Z ddl mZddlmZddlmZddlmZddlmZmZdd lmZd d ZGd d eZy)) annotations)AnyDictIterableListOptionalTupleUnioncastN)Document) Embeddings guard_import) VectorStore) AddableMixinDocstore)InMemoryDocstorectdS)z= Import usearch if available, otherwise raise error. usearch.indexrr/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/vectorstores/usearch.pydependable_usearch_importrs  ((rceZdZdZ ddZ d d dZ d d dZ d d dZe d ddZ y)USearchzc`USearch` vector store. To use, you should have the ``usearch`` python package installed. c<||_||_||_||_y)z%Initialize with necessary components.N) embeddingindexdocstoreids)selfrrrr s r__init__zUSearch.__init__s #   rNc *t|jtstd|jd|jj t |}g}t|D]*\}}|r||ni} |jt|| ,||jrYt|jddz} tjt|D cgc]\} } t| | zc} } }n`tjt|D cgc]\} } t| c} } }n%t|t rtj|}|jj!tj|tj||jj!t#t%|||jj'|t)t*t|j-Scc} } wcc} } w)alRun more texts through the embeddings and add to the vectorstore. Args: texts: Iterable of strings to add to the vectorstore. metadatas: Optional list of metadatas associated with the texts. ids: Optional list of unique IDs. Returns: List of ids from adding the texts into the vectorstore. zSIf trying to add texts, the underlying docstore should support adding items, which z does not page_contentmetadata) isinstancerr ValueErrorrembed_documentslist enumerateappendr r intnparraystrradddictzipextendr rtolist) r!texts metadatasr kwargs embeddings documentsitextr&last_idid_s r add_textszUSearch.add_texts)s"$--6''+}}oY@  ^^33DK@   'GAt'0y|bH   X4(K L( ;xxdhhrl+a/hhy?OP?Oeb!GbL 1?OPQhhYu5EF5EEBB5EFG T "((3-C rxx}bhhz&:; $s3 234 DIszz|,, QFs H H c|jj|}|jjt j ||}g}t |j|jD]]\}}|jjt|}t|tstd|d||j||f_|S)a Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of documents most similar to the query with distance. Could not find document for id , got )r embed_queryrsearchr0r1r5keys distancesrr2r)r r*r.) r!querykquery_embeddingmatchesdocs_with_scoresr@scoredocs rsimilarity_search_with_scorez$USearch.similarity_search_with_scoreTs..44U;**##BHH_$=qA9;W\\7+<+<=IB--&&s2w/Cc8, #B2$fSE!RSS  # #S%L 1 >  rc l|jj|}|jjt j ||}g}|j D]X}|jjt|}t|tstd|d||j|Z|S)zReturn docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of Documents most similar to the query. rDrE) rrFrrGr0r1rHrr2r)r r*r.) r!rJrKr:rLrMdocsr@rPs rsimilarity_searchzUSearch.similarity_searchns..44U;**##BHH_$=qA!,,B--&&s2w/Cc8, #B2$fSE!RSS KK    rc |j|}g}|;tjt|D cgc]\} } t | c} } }n%t |t rtj|}t|D]*\} } |r|| ni} |jt| | ,ttt||}td}|jt|d|}|jtj|tj|||||t!t"t|j%Scc} } w)aWConstruct USearch wrapper from raw documents. This is a user friendly interface that: 1. Embeds documents. 2. Creates an in memory docstore 3. Initializes the USearch database This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import USearch from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() usearch = USearch.from_texts(texts, embeddings) r$rr)ndimmetric)r+r0r1r-r2r)r,r.r rr4r5rIndexlenr3r rr7)clsr8rr9r rWr:r;r<r@rAr=r>r&rusearchrs r from_textszUSearch.from_textss4..u5 $& ;((51AB1AACG1ABCC T "((3-C 'GAt'0y|bH   X4(K L($DS))<$=>/ 3z!}#5f E "((3-*!569eXtDIszz|/LMMCsE )rr rrrrr List[str])NN) r8z Iterable[str]r9Optional[List[Dict]]r &Optional[Union[np.ndarray, list[str]]]r:rreturnr]))rJr2rKr/r`zList[Tuple[Document, float]])rJr2rKr/r:rr`zList[Document])NNcos)r8r]rr r9r^r r_rWr2r:rr`r) __name__ __module__ __qualname____doc__r"rBrQrT classmethodr\rrrrrs2       +/6: )-)-()-4 )-  )-  )-\     &  :    6 +/6: (N(N(N( (N 4 (N  (N(N (N(Nrr)r`r) __future__rtypingrrrrrr r r numpyr0langchain_core.documentsr langchain_core.embeddingsr langchain_core.utilsrlangchain_core.vectorstoresr!langchain_community.docstore.baserr&langchain_community.docstore.in_memoryrrrrrrrqs;"JJJ-0-3DC)\Nk\Nr