dhvSSKJr SSKJrJrJrJrJrJr SSK J r SSK J r SSK Jr SSKJr "SS\5rg ) ) annotations)AnyDictIterableListOptionalTuple)uuid4)Document) Embeddings) VectorStorecZ^\rSrSrSrSSU4SjjjrSSSjjrSSjrSSSjjrSSSjjr SSjr SS jr SSS jjr \ SS j5r\ SSS jj5r\ SSS jj5rSrU=r$)VLite z?VLite is a simple and fast vector database for semantic search.c >[TU]5 XlU=(d S[5R3UlSSKJn U"SSUR 0UD6Ulg![a [S5ef=f)Nvlite_r)rRCould not import vlite python package. Please install it with `pip install vlite`. collection) super__init__embedding_functionr hexrvliter ImportError)selfrrkwargsr __class__s ^/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/vlite.pyrVLite.__init__st "4$>& (>  # @doo@@  >  s AA2c [U5nURSUVs/sHn[[55PM sn5nURR U5nU(dUVs/sHn0PM nn[ XXV5VVV V s/sH upxpXxXS.PM n n nnn URRU 5n U V s/sHoSPM sn $s snfs snfs sn n nnfs sn f)a:Run more texts through the embeddings and add to the vectorstore. Args: texts: Iterable of strings to add to the vectorstore. metadatas: Optional list of metadatas associated with the texts. kwargs: vectorstore specific parameters Returns: List of ids from adding the texts into the vectorstore. ids)textmetadataid embeddingr) listpopstrr rembed_documentszipradd)rtexts metadatasr_r" embeddingsr#r$r%r& data_pointsresultsresults r add_textsVLite.add_texts#s U jju =u!UWu =>,,<, 1sC % C C 8 Cc ~URSUVs/sHn[[55PM sn5n/n/n[X5HupxSU;aSSKJn U "US5n URU 5 URUR/[U 5-5 UR[[U 55V s/sH oSU 3PM sn 5 MURUR5 URUR5 M URXVUS9$s snf![ a [ S5ef=fs sn f)a)Add a list of documents to the vectorstore. Args: documents: List of documents to add to the vectorstore. kwargs: vectorstore specific parameters such as "file_path" for processing directly with vlite. Returns: List of ids from adding the documents into the vectorstore. r" file_pathr) process_filerr/)r")r(r)r r+ vlite.utilsr8rextendr$lenrangeappend page_contentr4) r documentsrr/r"r-r.docr%r8processed_datais r add_documentsVLite.add_documents?s&jjy Ay!UWy AB 9*GCf$8 ".f[.A!B ^,  #,,#n2E!EF s>7J1KL1KAd!A3K1KLM S--.  .!+"~~eC~88)!B#%FMsD D!:D: !D7c XURXS9nUVVs/sHupVUPM snn$s snnf)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. )k)similarity_search_with_score)rqueryrFrdocs_and_scoresr@r/s rsimilarity_searchVLite.similarity_searchds1;;E;G"12//222s &c U=(d 0nURRU5nURRUUUSUS9nUVV Vs/sHupn[ XS9U 4PM n n nnU $s snn nf)aReturn docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. filter: Filter by metadata. Defaults to None. Returns: List of Tuples of (doc, score), where score is the similarity score. T)r#top_kr$ return_scoresr&r>r$)r embed_queryrretriever ) rrHrFfilterrr$r&r2r#scoredocuments_with_scoress rrG"VLite.similarity_search_with_scorevs" **%% & *1! )0%X4 ;U C)0 ! %$ ! s A'c`URRXRURS9 g)z/Update an existing document in the vectorstore.)r#r$N)rupdater>r$)r document_iddocuments rupdate_documentVLite.update_documents*  33h>O>O  c URRU5nUVVs/sHup4[X4S9PM nnnU$s snnf)zGet documents by their IDs.rO)rgetr )rr"r2r#r$r?s rr^ VLite.getsE**..%QX QX~tH$ :QX   s:c FUbURR"U40UD6 gg)zDelete by ids.NT)rdelete)rr"rs rra VLite.deletes$ ? JJ  c ,V ,r\c U"SXS.UD6nU$)zLoad an existing VLite index. Args: embedding: Embedding function collection: Name of the collection to load. Returns: VLite vector store. rrrr)clsr&rrrs rfrom_existing_indexVLite.from_existing_indexs RyR6R r\c @U"SX$S.UD6nUR"X40UD6 U$)aConstruct VLite wrapper from raw documents. This is a user-friendly interface that: 1. Embeds documents. 2. Adds the documents to the vectorstore. This is intended to be a quick way to get started. Example: .. code-block:: python from langchain import VLite from langchain.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() vlite = VLite.from_texts(texts, embeddings) rdr)r4)rer-r&r.rrrs r from_textsVLite.from_textss,4RyR6R 3F3 r\c @U"SX#S.UD6nUR"U40UD6 U$)aConstruct VLite wrapper from a list of documents. This is a user-friendly interface that: 1. Embeds documents. 2. Adds the documents to the vectorstore. This is intended to be a quick way to get started. Example: .. code-block:: python from langchain import VLite from langchain.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() vlite = VLite.from_documents(documents, embeddings) rdr)rC)rer?r&rrrs rfrom_documentsVLite.from_documentss.2RyR6R I00 r\)rrr)N)rr r Optional[str]rr)r-z Iterable[str]r.Optional[List[dict]]rrreturn List[str])r?List[Document]rrrprq))rHr)rFintrrrprr)rsN) rHr)rFrtrRzOptional[Dict[str, str]]rrrpzList[Tuple[Document, float]])rXr)rYr rpNone)r"rqrprr)r"zOptional[List[str]]rrrpzOptional[bool])r&r rr)rrrpr)NN) r-rqr&r r.rorrnrrrpr) r?rrr&r rrnrrrpr)__name__ __module__ __qualname____firstlineno____doc__rr4rCrJrGrZr^ra classmethodrfrirl__static_attributes__ __classcell__)rs@rrr sI %)A&A"A AA,+/11(1 1  18#9!#9#9  #9P33 3 3  3*+/ %% %) %  % & %@    $ +/$( (  "    : %) !"     r\rN) __future__rtypingrrrrrr uuidr langchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr rrr\rrs,">=.03jKjr\