a bg@spddlmZddlmZmZmZmZmZmZddl m Z ddl m Z ddl mZddlmZGdddeZd S) ) annotations)AnyDictIterableListOptionalTuple)uuid4Document) Embeddings) VectorStorec s eZdZdZd4ddddfdd Zd5d d dd d d dZddd dddZd6dddddddZd7ddddddddZdddd d!d"Z d dd#d$d%Z d8d&dd'd(d)d*Z e ddddd+d,d-Z e d9d dd dddd.d/d0Ze d:dddddd1d2d3ZZS);VLitez?VLite is a simple and fast vector database for semantic search.Nr z Optional[str]r)embedding_function collectionkwargsc sjt||_|p dtj|_zddlm}WntyNtdYn0|fd|ji||_dS)NZvlite_r)rRCould not import vlite python package. Please install it with `pip install vlite`.r) super__init__rr hexrvliter ImportError)selfrrrr __class__t/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_community/vectorstores/vlite.pyrs   zVLite.__init__z Iterable[str]zOptional[List[dict]]z List[str])texts metadatasrreturncKsnt|}|ddd|D}|j|}|s4z#VLite.add_texts..cSsg|]}iqSrrr#rrrr&7r'cSs"g|]\}}}}||||dqS))textmetadataid embeddingr)r$r(r)r*r+rrrr&8s cSsg|] }|dqS)rr)r$resultrrrr&=r')listpoprZembed_documentszipradd)rrrrr Z embeddingsZ data_pointsresultsrrr add_texts#s   zVLite.add_textszList[Document]) documentsrrc s|ddd|D}g}g}t||D]\}d|vrzddlm}WntybtdYn0||d}||||jgt||fddtt|Dq(| |j | |jq(|j |||d S) aaAdd a list of documents to the vectorstore. Args: documents: List of documents to add to the vectorstore. kwargs: vectorstore specific parameters such as "file_path" for processing directly with vlite. Returns: List of ids from adding the documents into the vectorstore. r cSsg|]}ttqSrr!r#rrrr&Nr'z'VLite.add_documents.. file_pathr) process_filercsg|]}d|qS)r%r)r$ir*rrr&^r')r ) r.r/Z vlite.utilsr5rextendr)lenrangeappend page_contentr2) rr3rr rrdocr5Zprocessed_datarr7r add_documents?s$    " zVLite.add_documentsr"int)querykrrcKs|j||d}dd|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. )rBcSsg|] \}}|qSrr)r$r=r%rrrr&tr'z+VLite.similarity_search..)similarity_search_with_score)rrArBrZdocs_and_scoresrrrsimilarity_searchdszVLite.similarity_searchzOptional[Dict[str, str]]zList[Tuple[Document, float]])rArBfilterrrc Ks<|pi}|j|}|jj|||d|d}dd|D}|S)aMReturn docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. filter: Filter by metadata. Defaults to None. Returns: List of Tuples of (doc, score), where score is the similarity score. T)r(Ztop_kr)Z return_scoresr+cSs"g|]\}}}t||d|fqS)r<r)r )r$r(Zscorer)rrrr&sz6VLite.similarity_search_with_score..)rZ embed_queryrretrieve) rrArBrErr)r+r1Zdocuments_with_scoresrrrrCvs z"VLite.similarity_search_with_scorer None) document_iddocumentrcCs|jj||j|jddS)z/Update an existing document in the vectorstore.)r(r)N)rupdater<r))rrIrJrrrupdate_documents zVLite.update_document)r rcCs|j|}dd|D}|S)zGet documents by their IDs.cSsg|]\}}t||dqSrFr )r$r(r)rrrr&szVLite.get..)rget)rr r1r3rrrrMs  z VLite.getzOptional[List[str]]zOptional[bool])r rrcKs$|dur |jj|fi|dSdS)zDelete by ids.NT)rdelete)rr rrrrrNsz VLite.delete)r+rrrcKs|f||d|}|S)zLoad an existing VLite index. Args: embedding: Embedding function collection: Name of the collection to load. Returns: VLite vector store. rrr)clsr+rrrrrrfrom_existing_indexszVLite.from_existing_index)rr+rrrrcKs,|f||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) rO)r2)rPrr+rrrrrrr from_textsszVLite.from_texts)r3r+rrrcKs*|f||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) rO)r>)rPr3r+rrrrrrfrom_documentsszVLite.from_documents)N)N)r?)r?N)N)NN)N)__name__ __module__ __qualname____doc__rr2r>rDrCrLrMrN classmethodrQrRrS __classcell__rrrrr s.( rN) __future__rtypingrrrrrruuidr Zlangchain_core.documentsr Zlangchain_core.embeddingsr Zlangchain_core.vectorstoresr rrrrrs