a bgD@sddlmZddlmZmZmZmZmZmZm Z m Z ddl Z ddl mZddlmZddlmZddlmZddlmZmZdd lmZd d d d ZGdddeZdS)) annotations)AnyDictIterableListOptionalTupleUnioncastN)Document) Embeddings guard_import) VectorStore) AddableMixinDocstore)InMemoryDocstorer)returncCstdS)z= Import usearch if available, otherwise raise error. usearch.indexr rrv/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_community/vectorstores/usearch.pydependable_usearch_importsrc @seZdZdZdddddddZdd d d ddd ddZd ddddddZd!dddddddZed"ddd d ddddddZ d S)#USearchzc`USearch` vector store. To use, you should have the ``usearch`` python package installed. r rrz List[str] embeddingindexdocstoreidscCs||_||_||_||_dS)z%Initialize with necessary components.Nr)selfrrrrrrr__init__szUSearch.__init__Nz Iterable[str]zOptional[List[Dict]]z&Optional[Union[np.ndarray, list[str]]])texts metadatasrkwargsrc  st|jtstd|jd|jt|}g}t|D]*\}}|rN||ni} |t || dq:t |j dd|durt fddt|D}nt|trt |}|jt |t ||jtt|||j |ttt|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 notZ page_contentmetadataNcsg|]\}}t|qSrstr.0id_Zlast_idrr Gz%USearch.add_texts..) isinstancerr ValueErrorrembed_documentslist enumerateappendr intrnparrayradddictzipextendr rr(tolist) rr r!rr" embeddings documentsitextr$rr-r add_texts)s(    zUSearch.add_textsr(r6zList[Tuple[Document, float]])querykrc Cs||j|}|jt||}g}t|j|jD]D\}}|j t |}t |t sht d|d||||fq2|S)a Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of documents most similar to the query with distance. Could not find document for id , got )r embed_queryrsearchr7r8r;keysZ distancesrr(r0r r1r5) rrDrEquery_embeddingmatchesZdocs_with_scoresr+Zscoredocrrrsimilarity_search_with_scorePs  z$USearch.similarity_search_with_scorezList[Document])rDrEr"rc Ksl|j|}|jt||}g}|jD]<}|jt|}t |t s\t d|d|| |q*|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. rFrG) rrHrrIr7r8rJrr(r0r r1r5) rrDrEr"rKrLdocsr+rMrrrsimilarity_searchjs    zUSearch.similarity_searchcos)r rr!rmetricr"rcKs||}g}|dur0tddt|D}nt|trDt|}t|D]*\} } |r`|| ni} |t| | dqLtt t ||} t d} | j t |d|d}|t|t||||| ttt|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) NcSsg|]\}}t|qSrr'r)rrrr.r/z&USearch.from_texts..r#rr)ndimrR)r2r7r8r4r0r3r5r rr:r;rIndexlenr9r rr(r=)clsr rr!rrRr"r>r?r@rAr$rZusearchrrrr from_textss   zUSearch.from_texts)NN)rC)rC)NNrQ) __name__ __module__ __qualname____doc__rrBrNrP classmethodrWrrrrrs*r) __future__rtypingrrrrrrr r numpyr7Zlangchain_core.documentsr Zlangchain_core.embeddingsr Zlangchain_core.utilsrZlangchain_core.vectorstoresrZ!langchain_community.docstore.baserrZ&langchain_community.docstore.in_memoryrrrrrrrs (