o Zh@spddlmZddlmZmZmZmZmZmZddl m Z ddl m Z ddl mZddlmZGdddeZd S) ) annotations)AnyDictIterableListOptionalTuple)uuid4Document) Embeddings) VectorStorecseZdZdZ d7d8fd d Z d7d9ddZd:ddZ d;dd!d"Zd?d'd(Z d@d*d+Z d7dAd.d/Z e dBd1d2Z e  dCdDd3d4Ze d7dEd5d6ZZS)FVLitez?VLite is a simple and fast vector database for semantic search.Nembedding_functionr collection Optional[str]kwargsrc sft||_|pdtj|_zddlm}Wn ty%tdw|dd|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__r]/var/www/html/lang_env/lib/python3.10/site-packages/langchain_community/vectorstores/vlite.pyrs  zVLite.__init__texts Iterable[str] metadatasOptional[List[dict]]return List[str]cKsnt|}|ddd|D}|j|}|sdd|D}ddt||||D}|j|}dd|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. idscSg|]}ttqSrstrr .0_rrr 4z#VLite.add_texts..cSsg|]}iqSrrr(rrrr+7scSs"g|] \}}}}||||dqS))textmetadataid embeddingr)r)r-r.r/r0rrrr+8s  cSsg|]}|dqS)rr)r)resultrrrr+=)listpoprZembed_documentszipradd)rrr rr$Z embeddingsZ data_pointsresultsrrr add_texts#s   zVLite.add_texts documentsList[Document]c s|ddd|D}g}g}t||D]O\}d|vrWzddlm}Wn ty/tdw||d}||||jgt||fddtt|Dq| |j | |jq|j |||d S) aaAdd a list of documents to the vectorstore. Args: documents: List of documents to add to the vectorstore. kwargs: vectorstore specific parameters such as "file_path" for processing directly with vlite. Returns: List of ids from adding the documents into the vectorstore. r$cSr%rr&r(rrrr+Nr,z'VLite.add_documents.. file_pathr) process_filercsg|] }d|qS)r*r)r)ir/rrr+^s)r$) r4r5Z vlite.utilsr<rextendr.lenrangeappend page_contentr8) rr9rr$rr docr<Zprocessed_datarr>r add_documents?s&   " zVLite.add_documentsqueryr'kintcKs|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. )rHcSsg|]\}}|qSrr)r)rDr*rrrr+tr2z+VLite.similarity_search..)similarity_search_with_score)rrGrHrZdocs_and_scoresrrrsimilarity_searchdszVLite.similarity_searchfilterOptional[Dict[str, str]]List[Tuple[Document, float]]c 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_scoresr0cSs"g|] \}}}t||d|fqS)rCr.r )r)r-Zscorer.rrrr+sz6VLite.similarity_search_with_score..)rZ embed_queryrretrieve) rrGrHrLrr.r0r7Zdocuments_with_scoresrrrrJvs z"VLite.similarity_search_with_score document_iddocumentr NonecCs|jj||j|jddS)z/Update an existing document in the vectorstore.)r-r.N)rupdaterCr.)rrQrRrrrupdate_documents  zVLite.update_documentr$cCs|j|}dd|D}|S)zGet documents by their IDs.cSsg|] \}}t||dqSrOr )r)r-r.rrrr+szVLite.get..)rget)rr$r7r9rrrrVs z VLite.getOptional[List[str]]Optional[bool]cKs$|dur|jj|fi|dSdS)zDelete by ids.NT)rdelete)rr$rrrrrYsz VLite.deleter0cKs|d||d|}|S)zLoad an existing VLite index. Args: embedding: Embedding function collection: Name of the collection to load. Returns: VLite vector store. rrNrr)clsr0rrrrrrfrom_existing_indexszVLite.from_existing_indexcKs,|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) rZNr)r8)r[rr0r rrrrrr from_textsszVLite.from_textscKs*|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) rZNr)rE)r[r9r0rrrrrrfrom_documentsszVLite.from_documents)N)rr rrrr)rrr r!rrr"r#)r9r:rrr"r#)rF)rGr'rHrIrrr"r:)rFN) rGr'rHrIrLrMrrr"rN)rQr'rRr r"rS)r$r#r"r:)r$rWrrr"rX)r0r rr'rrr"r)NN) rr#r0r r r!rrrrr"r) r9r:r0r rrrrr"r)__name__ __module__ __qualname____doc__rr8rErKrJrUrVrY classmethodr\r]r^ __classcell__rrrrr s0 (    rN) __future__rtypingrrrrrruuidr Zlangchain_core.documentsr Zlangchain_core.embeddingsr Zlangchain_core.vectorstoresr rrrrrs