tj~ddlmZddlmZmZmZmZmZmZddl m Z ddl m Z ddl mZddlmZGddeZd S) ) annotations)AnyDictIterableListOptionalTuple)uuid4Document) Embeddings) VectorStoreceZdZdZ d,d-fd Z d,d.dZd/dZ d0d1dZ d2d3dZd4d"Z d5d$Z d,d6d'Z e d7d)Z e d8d9d*Ze d,d:d+ZxZS);VLitez?VLite is a simple and fast vector database for semantic search.Nembedding_functionr collection Optional[str]kwargsrc t||_|pdtj|_ ddlm}n#t$rtdwxYw|dd|ji||_dS)Nvlite_r)rRCould not import vlite python package. Please install it with `pip install vlite`.r) super__init__rr hexrvliter ImportError)selfrrrr __class__s d/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_community/vectorstores/vlite.pyrzVLite.__init__s "4$>(>(>(>  # # # # # # #   >   U@@do@@@ s AA(texts Iterable[str] metadatasOptional[List[dict]]return List[str]c 4t|}|dd|D}|j|}|s d|D}dt ||||D}|j|}d|DS)arRun 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. idscDg|]}ttSrstrr .0_s r z#VLite.add_texts..4s" = = =!UWW = = =cg|]}iSrrr,s r r/z#VLite.add_texts..7s++++++r0c&g|]\}}}}||||dS))textmetadataid embeddingr)r-r3r4r5r6s r r/z#VLite.add_texts..8s<   -hIxr R R   r0cg|] }|d S)rr)r-results r r/z#VLite.add_texts..=s000fq 000r0)listpoprembed_documentszipradd)rr!r#rr( embeddings data_pointsresultss r add_textszVLite.add_texts#s U jj = =u = = =>>,<.Ns" A A A!UWW A A Ar0 file_pathr) process_filercg|] }d| S)r.r)r-ir5s r r/z'VLite.add_documents..^s#LLLArKKAKKLLLr0)r() r:r< vlite.utilsrGrextendr4lenrangeappend page_contentrA) rrBrr(r!r#docrGprocessed_datar5s @r add_documentszVLite.add_documents?ssjj A Ay A A ABB 9c** / /GCf$$8888888"%F ".f[.A!B!B ^,,,  #,#n2E2E!EFFF LLLLs>7J7J1K1KLLLMMMM S-...  ....~~eYC~888s AA!queryr+kintc H|||}d|DS)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. )rUcg|]\}}|Srr)r-rPr.s r r/z+VLite.similarity_search..ts222Q222r0)similarity_search_with_score)rrTrUrdocs_and_scoress r similarity_searchzVLite.similarity_searchds0;;EQ;GG22/2222r0filterOptional[Dict[str, str]]List[Tuple[Document, float]]c |pi}|j|}|j|||d|}d|D}|S)aMReturn 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)r3top_kr4 return_scoresr6c<g|]\}}}t|||fS)rOr4r )r-r3scorer4s r r/z6VLite.similarity_search_with_score..s@! ! ! %eX4( ; ; ;U C! ! ! r0)r embed_queryrretrieve) rrTrUr\rr4r6r@documents_with_scoress r rYz"VLite.similarity_search_with_scorevsu"> *%% &  ! ! )0! ! ! %$r0 document_iddocumentr NonecT|j||j|jdS)z/Update an existing document in the vectorstore.)r3r4N)rupdaterOr4)rrhris r update_documentzVLite.update_documents8  h3h>O      r0r(cR|j|}d|D}|S)zGet documents by their IDs.c6g|]\}}t||Srcr )r-r3r4s r r/zVLite.get..s6   ?MtXH$ : : :   r0)rget)rr(r@rBs r rpz VLite.gets;*..%%  QX   r0Optional[List[str]]Optional[bool]c 4||jj|fi|dSdS)zDelete by ids.NT)rdelete)rr(rs r rtz VLite.deletes. ? DJ c , ,V , , ,4tr0r6c |d||d|}|S)zLoad an existing VLite index. Args: embedding: Embedding function collection: Name of the collection to load. Returns: VLite vector store. rrrr)clsr6rrrs r from_existing_indexzVLite.from_existing_indexs% RyZRR6RR r0c :|d||d|}|j||fi||S)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_classic.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() vlite = VLite.from_texts(texts, embeddings) rvr)rA)rwr!r6r#rrrs r from_textszVLite.from_textssA4RyZRR6RRy33F333 r0c 8|d||d|}|j|fi||S)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_classic.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() vlite = VLite.from_documents(documents, embeddings) rvr)rR)rwrBr6rrrs r from_documentszVLite.from_documentss@2RyZRR6RRI00000 r0)N)rr rrrr)r!r"r#r$rrr%r&)rBrCrrr%r&)rS)rTr+rUrVrrr%rC)rSN) rTr+rUrVr\r]rrr%r^)rhr+rir r%rj)r(r&r%rC)r(rqrrr%rr)r6r rr+rrr%r)NN) r!r&r6r r#r$rrrrr%r) rBrCr6r rrrrr%r)__name__ __module__ __qualname____doc__rrArRr[rYrmrprt classmethodrxrzr| __classcell__)rs@r rr sII %)AAAAAAA,+/111118#9#9#9#9P33333*+/ %%%%%@    [$ +/$( [: %) [r0rN) __future__rtypingrrrrrr uuidr langchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresrrrr0r rs"""""">===============.-----000000333333jjjjjKjjjjjr0