tj:#ddlmZddlZddlmZddlmZmZmZm Z m Z m Z m Z ddl mZddlmZddlmZGdd eZdS) ) annotationsN)repeat)AnyDictIterableListOptionalTupleTypeDocument) Embeddings) VectorStoreceZdZdZd;d ZeddZ d?d@dZ d=d>dZ e d=dAdZ e dBdCd$Z dDdEd+Z dDdFd-ZdGd0Z d?dHd3ZdId4ZdJdKd:Zd S)LXataVectorStorez`Xata` vector store. It assumes you have a Xata database created with the right schema. See the guide at: https://integrations.langchain.com/vectorstores?integration_name=XataVectorStore api_keystrdb_url embeddingr table_namereturnNonec ddlm}n#t$rtdwxYw||||_||_|pd|_dS)zInitialize with Xata client.r) XataClientzPCould not import xata python package. Please install it with `pip install xata`.)rrvectorsN) xata.clientr ImportError_client _embedding _table_name)selfrrrrrs c/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_community/vectorstores/xata.py__init__zXataVectorStore.__init__s  . . . . . . .   =   "z'&AAA &/%2s #c|jSN)r)r!s r" embeddingszXataVectorStore.embeddings(s NrList[List[float]] documentsList[Document]idsOptional[List[str]] List[str]c0||||Sr%) _add_vectors)r!rr)r+s r" add_vectorszXataVectorStore.add_vectors,s   )S999r'texts Iterable[str] metadatasOptional[List[Dict[Any, Any]]]kwargsrc |}|||}|jt|}||||Sr%)_texts_to_documentsrembed_documentslistr0)r!r1r3r+r5docsrs r" add_textszXataVectorStore.add_texts4sQ''y99/11$u++>>s333r'c@g}t|D]e\}}||j|d}|r |||d<||jD]\}} |dvr| ||<||fd} g} t dt || D]} || | | z} |j |j d| i}|j dkrtd|j d || |d | S) z!Add vectors to the Xata database.)contentrid)r>r=rirrecordszError adding vectors to Xata:  recordIDs) enumerate page_contentmetadataitemsappendrangelenrr? bulk_insertr status_code Exceptionextend)r!rr)r+rowsidxrrowkeyval chunk_sizeid_listichunkrs r"r/zXataVectorStore._add_vectorsAs^&('00  NC$S>6&C %HD %cN399;; # #S<<<"CH KK     q#d))Z00 + +AQ^+,E $$&&2243CiQVEWXXA}## T T TQR T TUUU NN1[> * * * *r'"Optional[Iterable[Dict[Any, Any]]]c\|ti}dt||D}|S)z:Return list of Documents from list of texts and metadatas.Nc6g|]\}}t||S)rDrEr ).0textrEs r" z7XataVectorStore._texts_to_documents..ls9   h $ : : :   r')rzip)r1r3r:s r"r7z#XataVectorStore._texts_to_documentscsD  r I  "%eY"7"7     r'clsType['XataVectorStore']Optional[List[dict]] Optional[str]'XataVectorStore'c |r|std||} d}|||} |||||} | | | || S)z9Return VectorStore initialized from texts and embeddings.z$Xata api_key and db_url must be set.N)rrrr) ValueErrorr8r7r/) r`r1rr3rrrr+r5r&r: vector_dbs r" from_textszXataVectorStore.from_textsss Ef ECDD D..u55 &&ui88C!     z4555r'querykintfilterOptional[dict]c N||||}d|D}|S)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. )rmcg|] }|d S)r)r\ds r"r^z5XataVectorStore.similarity_search..s333aQqT333r')similarity_search_with_score)r!rjrkrmr5docs_and_scoresr)s r"similarity_searchz!XataVectorStore.similarity_searchs7;;E1V;TT33?333 r'List[Tuple[Document, float]]c 2j|}|d|d}|r||d<jj|}|jdkrtd|jd||d}fd |D} | S) aRun similarity search with Chroma with distance. Args: query (str): Query text to search for. k (int): Number of results to return. Defaults to 4. filter (Optional[dict]): Filter by metadata. Defaults to None. Returns: List[Tuple[Document, float]]: List of documents most similar to the query text with distance in float. r) queryVectorcolumnsizermpayloadr@z!Error running similarity search: rAr?cg|]:}t|d||ddf;S)r=r[xatascore)r _extractMetadata)r\hitr!s r"r^z@XataVectorStore.similarity_search_with_score..se     !$Y!22377F G$      r')r embed_queryrdata vector_searchr rKrL) r!rjrkrmr5rr|rWhitsrts ` r"rsz,XataVectorStore.similarity_search_with_scoresO//66 $!    ' &GH  L     - -d.> - P P =C  S SSPQSSTT T|         r'recorddictcPi}|D]\}}|dvr|||<|S)z:Extract metadata from a record. Filters out known columns.)r>r=rr~)rF)r!rrErQrRs r"rz XataVectorStore._extractMetadatas=  $ $HC@@@ # r' delete_allOptional[bool]c `|r,ddS|od}tdt||D]L}||||z}fd|D}jd|iMdStd) zDelete by vector IDs. Args: ids: List of ids to delete. delete_all: Delete all records in the table. r)ndocsNic(g|]}dj|diSdelete)tabler>r r\r>r!s r"r^z*XataVectorStore.delete..s6JLX)9DDEr' operationsr{z%Either ids or delete_all must be set.) _delete_allwait_for_indexingrHrIrr? transactionrf)r!r+rr5rSrUrVrs` r"rzXataVectorStore.deletes  F        " " " + + + + + _J1c#hh 33 W WAJ./PU  $$&&22L*;U2VVVV  W WDEE Er'c jjddgi}|jdkrt d|jd|d|d D}t |d krd Sfd |D}jd |i)z Delete all records in the table.Tcolumnsr>r{r@zError running query: rAcg|] }|d S)r>rq)r\recs r"r^z/XataVectorStore._delete_all..s5553t9555r'r?rc(g|]}dj|diSrrrs r"r^z/XataVectorStore._delete_all..s6FHT%5R@@Ar'rN) rrrjr rKrLrIr?r)r!rWr+rs` r"rzXataVectorStore._delete_alls S !!##))$*:YQUPVDW)XXA}## K K K K KLLL55) 555C3xx1}}LOJ L " " . . j7Q . R R R Sr'timeoutfloatrc|tj} |j|jdddid}|jdkrt d|jd ||d |krd Stj|z |krt d tjd )zeWait for the search index to contain a certain number of documents. Useful in tests. Trzr)rjpager{r@zError running search: rA totalCountz+Timed out waiting for indexing to complete.g?N)timerr search_tabler rKrLsleep)r!rrstartrWs r"rz!XataVectorStore.wait_for_indexings   !!##00 B *L*L1A}## L L L L LMMM%''y{{U"W,, MNNN JsOOO r') rrrrrrrrrr)rrr%)rr(r)r*r+r,rr-)NN) r1r2r3r4r+r,r5rrr-)r1r2r3rXrr*)NNNrN)r`rar1r-rrr3rbrrcrrcrrr+r,r5rrrd)riN) rjrrkrlrmrnr5rrr*) rjrrkrlrmrnr5rrrv)rrrr)r+r,rrr5rrr)rr)rr)rrrrlrr)__name__ __module__ __qualname____doc__r#propertyr&r0r;r/ staticmethodr7 classmethodrhrursrrrrrqr'r"rr s3333&X$( :::::59#' 4 4 4 4 4"$(     D9=    \  +/!% $##'[>@D"@D$$$$$L$(%)FFFFF4 S S S Sr'r) __future__rr itertoolsrtypingrrrrr r r langchain_core.documentsr langchain_core.embeddingsrlangchain_core.vectorstoresrrrqr'r"rs"""""" CCCCCCCCCCCCCCCCCC------000000333333{{{{{k{{{{{r'