NgddlmZddlmZmZmZmZmZmZm Z ddl Z ddl m Z ddlmZddlmZddlmZddlmZmZdd lmZdd ZGd deZdS)) annotations)AnyDictIterableListOptionalTupleUnionN)Document) Embeddings guard_import) VectorStore) AddableMixinDocstore)InMemoryDocstorereturnrc tdS)z= Import usearch if available, otherwise raise error. usearch.indexr d/var/www/html/ai-engine/env/lib/python3.11/site-packages/langchain_community/vectorstores/usearch.pydependable_usearch_importrs  ( ((rc`eZdZdZd d Z d!d"dZ d#d$dZ d#d%dZe d&d'dZ d S)(USearchzc`USearch` vector store. To use, you should have the ``usearch`` python package installed. embeddingr indexrdocstorerids List[str]c>||_||_||_||_dS)z%Initialize with necessary components.N)rrrr)selfrrrrs r__init__zUSearch.__init__s$#   rNtexts Iterable[str] metadatasOptional[List[Dict]]&Optional[Union[np.ndarray, list[str]]]kwargsrc t t|jtstd|jd|jt |}g}t|D]5\}}|r||ni} |t|| 6t|j ddz |.tj fdt|D}n)t|t rtj |}|jtj |tj ||jt!t#|||j ||S)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_contentmetadataNc:g|]\}}t|zSrstr).0id_last_ids r z%USearch.add_texts..Gs)LLL%"aC" --LLLr) isinstancerr ValueErrorrembed_documentslist enumerateappendr intrnparrayradddictzipextendtolist) r"r$r&rr) embeddings documentsitextr-r6s @r add_textszUSearch.add_texts)s"$-66 @'+}@@@  ^33DKK@@   '' M MGAt'08y||bH   X4(KKK L L L Ldhrl##a' ;(LLLL9U;K;KLLLMMCC T " " (3--C rx}}bhz&:&:;;; $s3 2233444 zz||rqueryr2kr>List[Tuple[Document, float]]c|j|}|jt j||}g}t |j|jD]m\}}|j t|}t|tstd|d||||fn|S)a Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of documents most similar to the query with distance. Could not find document for id , got )r embed_queryrsearchr?r@rCkeys distancesrr2r8r r9r=) r"rLrMquery_embeddingmatchesdocs_with_scoresr4scoredocs rsimilarity_search_with_scorez$USearch.similarity_search_with_scorePs.44U;;*##BH_$=$=qAA9;W\7+<== 2 2IB-&&s2ww//Cc8,, T !R2!R!RS!R!RSSS  # #S%L 1 1 1 1rList[Document]c x|j|}|jt j||}g}|jD]h}|jt|}t|tstd|d|| |i|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. rPrQ) rrRrrSr?r@rTrr2r8r r9r=) r"rLrMr)rVrWdocsr4rZs rsimilarity_searchzUSearch.similarity_searchjs.44U;;*##BH_$=$=qAA!,  B-&&s2ww//Cc8,, T !R2!R!RS!R!RSSS KK     rcosmetricc ||}g}|,tjdt|D}n)t |t rtj|}t|D]5\} } |r|| ni} |t| | 6ttt||} td} | t|d|}|tj|tj||||| |S)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) Nc2g|]\}}t|Srr1)r3r4r5s rr7z&USearch.from_texts..s"BBBACGGBBBrr+rr)ndimra)r:r?r@r<r8r;r=r rrBrCrIndexlenrArE)clsr$rr&rrar)rFrGrHrIr-rusearchrs r from_textszUSearch.from_textssL4..u55 $& ;(BB51A1ABBBCCCC T " " (3--C '' M MGAt'08y||bH   X4(KKK L L L L#DS))<)<$=$=>>// 3z!}#5#5f EE "(3--*!5!5666s9eXszz||<<rrN)rLr2rMr>r)rrr\)NNr`)r$r rr r&r'rr(rar2r)rrr) __name__ __module__ __qualname____doc__r#rJr[r_ classmethodrirrrrrs     +/6: %%%%%T     :6 +/6: (=(=(=(=[(=(=(=rr)rr) __future__rtypingrrrrrr r numpyr?langchain_core.documentsr langchain_core.embeddingsr langchain_core.utilsrlangchain_core.vectorstoresr!langchain_community.docstore.baserr&langchain_community.docstore.in_memoryrrrrrrrxs""""""DDDDDDDDDDDDDDDDDD------000000------333333DDDDDDDDCCCCCC))))X=X=X=X=X=kX=X=X=X=X=r