hvddlmZddlmZmZmZmZmZmZddl m Z ddl m Z ddl mZddlmZGddeZy ) ) annotations)AnyDictIterableListOptionalTuple)uuid4)Document) Embeddings) VectorStorec,eZdZdZ d dfd Z d ddZ ddZ d ddZ d ddZddZ ddZ d dd Z e dd Z e d dd Ze d dd ZxZS)VLitez?VLite is a simple and fast vector database for semantic search.c t|||_|xsdtj|_ ddlm}|dd|j i||_y#t$r tdwxYw)Nvlite_r)rRCould not import vlite python package. Please install it with `pip install vlite`. collection) super__init__embedding_functionr hexrvliter ImportError)selfrrkwargsr __class__s d/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/langchain_community/vectorstores/vlite.pyrzVLite.__init__sv "4$>& (>  # @doo@@  >  s AA-c t|}|jd|Dcgc]}ttc}}|jj |}|s|Dcgc]}i}}t ||||D cgc]\}}} } ||| | d} } }}} |jj| } | D cgc]} | d c} Scc}wcc}wcc} } }}wcc} w)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. ids)textmetadataid embeddingr) listpopstrr rembed_documentszipradd)rtexts metadatasr_r embeddingsr!r"r#r$ data_pointsresultsresults r add_textszVLite.add_texts#s U jju =!UW =>,,<, 1sC  C<C 3 Cc x|jd|Dcgc]}ttc}}g}g}t||D]\}}d|vr ddlm} | |d} |j| |j|jgt| z|jtt| D cgc] } |d|  c} |j|j|j|j|j|||Scc}w#t $r t dwxYwcc} w)aaAdd 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.utilsr5rextendr"lenrangeappend page_contentr2) r documentsrr-r r+r,docr#r5processed_datais r add_documentszVLite.add_documents?s)jjy A!UW AB 9c* /GCf$8 ".f[.A!B ^,  #,,#n2E!EF s>7J1KLArd!A3KLM S--.  .! /"~~eYC~88)!B#%FMsD D8D7 D4c ^|j||}|Dcgc]\}}| c}}Scc}}w)zReturn docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of Documents most similar to the query. )k)similarity_search_with_score)rqueryrBrdocs_and_scoresr=r-s rsimilarity_searchzVLite.similarity_searchds1;;EQ;G"12Q222s )c |xsi}|jj|}|jj|||d|}|D cgc]\}} }t ||| f} } }}| Scc}} }w)aMReturn docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. filter: Filter by metadata. Defaults to None. Returns: List of Tuples of (doc, score), where score is the similarity score. T)r!top_kr" return_scoresr$r;r")r embed_queryrretriever ) rrDrBfilterrr"r$r0r!scoredocuments_with_scoress rrCz"VLite.similarity_search_with_scorevs" **%% & *1! ! %eX4( ;U C! ! %$ ! sA(ch|jj||j|jy)z/Update an existing document in the vectorstore.)r!r"N)rupdater;r")r document_iddocuments rupdate_documentzVLite.update_documents,  h33h>O>O  c|jj|}|Dcgc]\}}t||}}}|Scc}}w)zGet documents by their IDs.rJ)rgetr )rr r0r!r"r<s rrWz VLite.getsF**..%QX ?MtXH$ :   s=c D||jj|fi|yy)zDelete by ids.NT)rdelete)rr rs rrYz VLite.deletes& ? DJJ  c ,V ,rUc |d||d|}|S)zLoad an existing VLite index. Args: embedding: Embedding function collection: Name of the collection to load. Returns: VLite vector store. rrrr)clsr$rrrs rfrom_existing_indexzVLite.from_existing_indexs RyZR6R rUc D|d||d|}|j||fi||S)aConstruct VLite wrapper from raw documents. This is a user-friendly interface that: 1. Embeds documents. 2. Adds the documents to the vectorstore. This is intended to be a quick way to get started. Example: .. code-block:: python from langchain import VLite from langchain.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() vlite = VLite.from_texts(texts, embeddings) r[r)r2)r\r+r$r,rrrs r from_textszVLite.from_textss24RyZR6Ry3F3 rUc B|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.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() vlite = VLite.from_documents(documents, embeddings) r[r)r@)r\r<r$rrrs rfrom_documentszVLite.from_documentss22RyZR6RI00 rU)N)rr r Optional[str]rr)r+z Iterable[str]r,Optional[List[dict]]rrreturn List[str])r<List[Document]rrrdre))rDr'rBintrrrdrf)rgN) rDr'rBrhrMzOptional[Dict[str, str]]rrrdzList[Tuple[Document, float]])rRr'rSr rdNone)r rerdrf)r zOptional[List[str]]rrrdzOptional[bool])r$r rr'rrrdr)NN) r+rer$r r,rcrrbrrrdr) r<rfr$r rrbrrrdr)__name__ __module__ __qualname____doc__rr2r@rFrCrTrWrY classmethodr]r_ra __classcell__)rs@rrr sI %)A&A"A A,+/11(1 1  18#9!#9#9  #9P33 3 3  3*+/ %% %) %  % & %@    $ +/$( (  "    : %) !"     rUrN) __future__rtypingrrrrrr uuidr langchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr rrrUrrvs,">=.03jKjrU