tj0&ddlmZmZmZmZmZmZddlmZddl Z ddl Z ddl m Z ddlmZddlmZddlmZddlmZGd d eZdS) )AnyIterableListOptionalTuplecast)uuid4NDocument) Embeddings) get_from_env) VectorStore)DistanceStrategycxeZdZUdZdZeed<dezZej dfdede de d ed ef d Z e d efd Zd efdZd efdZd efdZ d$deedeeede ded eef dZe d e fdZd%deeeded eefdZd&deede d eefdZ d&dede ded eefdZ d&dede ded eeeeffd Z d&deede ded eefd!Z!e"ddd"dej fdeede deeedede d ed eded dfd#Z#dS)'SemaDBa`SemaDB` vector store. This vector store is a wrapper around the SemaDB database. Example: .. code-block:: python from langchain_community.vectorstores import SemaDB db = SemaDB('mycollection', 768, embeddings, DistanceStrategy.COSINE) zsemadb.p.rapidapi.comHOSTzhttps://collection_name vector_size embeddingdistance_strategyapi_keycl||_||_|ptdd|_||_||_dS)z#initialize the SemaDB vector store.rSEMADB_API_KEYN)rrr r _embeddingr)selfrrrrrs e/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_community/vectorstores/semadb.py__init__zSemaDB.__init__s@ /&K,y:J"K"K #!2returnc,d|jtjdS)zReturn the common headers.zapplication/json)z content-typezX-RapidAPI-KeyzX-RapidAPI-Host)rrrrs rheaderszSemaDB.headers.s /"l%{   rcJ|jtjkrdS|jtjkrt d|jtjkrdS|jtjkrt d|jtjkrdSt d|j)z&Return the internal distance strategy. euclideanz,Max inner product is not supported by SemaDBdotcosinezUnknown distance strategy )rrEUCLIDEAN_DISTANCEMAX_INNER_PRODUCT ValueError DOT_PRODUCTJACCARDCOSINEr"s r_get_internal_distance_strategyz&SemaDB._get_internal_distance_strategy7s  !%5%H H H;  #'7'I I IKLL L  #'7'C C C5  #'7'? ? ?KLL L  #'7'> > >8R$:PRRSS Src|j|j|d}tjt jdz||j}|jdkS)z/Creates the corresponding collection in SemaDB.)id vectorSizedistanceMetricz /collectionsjsonr#) rrr.requestspostrBASE_URLr# status_code)rpayloadresponses rcreate_collectionzSemaDB.create_collectionFse&*"BBDD   = On ,L    #s**rcxtjtjd|jz|j}|jdkS)z/Deletes the corresponding collection in SemaDB. /collections/)r#r5)r6deleterr8rr#r9)rr;s rdelete_collectionzSemaDB.delete_collectionTsC? ODd.BDD DL   #s**rNtexts metadatas batch_sizekwargsc rt|tst|}|j|}t |d|jkr-t dt |dd|j|jtj krvtj |}|tj |ddz }tttt |}g}g}|ht%|||D]U\} } } t't)} || || | i| d| id Vnat%||D]P\} } t't)} || || | d| id Qt-dt ||D]} || | |z}t/jt2jd |jd zd |i|j }|jdkr't=d|t d|j| d}t |dkrt d||S)zAdd texts to the vector store.rzEmbedding size mismatch z != T)axiskeepdimsNtext)r0vectormetadatar>/pointspointsr3r5zHERE--zError adding points: failedRanges)! isinstancelistrembed_documentslenrr*rrr-nparraylinalgnormrrfloattolistzipstrr appendranger6r7rr8rr#r9printrJr4)rrBrCrDrE embeddings embed_matrixidsrNrJrrLnew_idibatchr; failed_rangess r add_textszSemaDB.add_texts\s%&& KKE_44U;; z!}  !1 1 1U3z!}+=+=UU4CSUU   !%5%< < <8J//L'")..1t+9++Ld4;/1D1D1F1FGGJ  -0 I-N-N  )iUWW 6""" $"+$Bx$BFD>$B $'uj#9#9  iUWW 6""" $"+%+TNq#f++z22 J JA1q:~-.E}"O$2F"O"O"OO& H #s**h&&& !H!H!HIII$MMOON;M=!!A%% !H!H!HIII& rc|jS)zReturn the embeddings.)rr"s rr_zSemaDB.embeddingss rrac d|i}tjtjd|jdz||j}|jdko*t|ddkS)a3Delete by vector ID or other criteria. Args: ids: List of ids to delete. **kwargs: Other keyword arguments that subclasses might use. Returns: Optional[bool]: True if deletion is successful, False otherwise, None if not implemented. rar>rMr3r5 failedPointsr) r6r?rr8rr#r9rSr4)rrarEr:r;s rr?z SemaDB.deletesy 3 ? OKd.BKKK KL    #s*Xs8==??>3R/S/SWX/XXrkc|jtjkrhtj|}|tj|z }ttt| }||d}tj tjd|jdz||j}|jdkrt%d|j|dS)zSearch points.)rKlimitr>z/points/searchr3r5zError searching: rN)rrr-rTrUrVrWrrrXrYr6r7rr8rr#r9r*rJr4)rrrkvecr:r;s r_search_pointszSemaDB._search_pointss  !%5%< < <(9%%C s+++CT%[#**,,77I   = ORd.BRRR RL     3 & &@@@AA A}}x((rqueryc d|j|}|||S)z"Return docs most similar to query.rk)r embed_querysimilarity_search_by_vector)rrprkrEquery_embeddings rsimilarity_searchzSemaDB.similarity_searchs2/55e<<//1/EEErc ||j|}|||}d|DS)z$Run similarity search with distance.rrcdg|]-}t|dd|d|df.S)rLrJ page_contentrLdistancer .0ps r z7SemaDB.similarity_search_with_score..sP   a mF&;a mTTT*     r)rrsro)rrprkrErurNs rsimilarity_search_with_scorez#SemaDB.similarity_search_with_scoresT/55e<<$$_$::       rc H|||}d|DS)aReturn docs most similar to embedding vector. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of Documents most similar to the query vector. rrcTg|]%}t|dd|d&S)rLrJryr r|s rrz6SemaDB.similarity_search_by_vector..sB    !J-"7!J- P P P   r)ro)rrrkrErNs rrtz"SemaDB.similarity_search_by_vectors=$$Y!$44      rrc |std|std|std||||||} | std| ||| S)z9Return VectorStore initialized from texts and embeddings.z Collection name must be providedzVector size must be providedzAPI key must be provided)rrzError creating collection)rC)r*r<rf) clsrBrrCrrrrrEsemadbs r from_textszSemaDB.from_textss A?@@ @ =;<< < 9788 8   /    '')) :899 9)444 r)NrA)N)rj)$__name__ __module__ __qualname____doc__rr[__annotations__r8rr(intr rpropertydictr#r.boolr<r@rrrrrfr_r?rXror rvrrrt classmethodrrrrrs  (D#'''D H/?.Q 3 3 3 3 3 , 3  3 3 3 3    X  T T T T T +4 + + + ++4+++++/ ??}?DJ'? ?  ? c ????BJXYY(49-YYQUYYYY*))U ))DJ)))),$%FFF F03F hFFFF$%        03  eHeO$ %     01  e ), .QCyDJ'     , [rr)typingrrrrrruuidr numpyrTr6langchain_core.documentsr langchain_core.embeddingsr langchain_core.utilsr langchain_core.vectorstoresr&langchain_community.vectorstores.utilsrrrrrrs================------000000------333333CCCCCCBBBBB[BBBBBr