dh0&SSKJrJrJrJrJrJr SSKJr SSK r SSK r SSK J r SSKJr SSKJr SSKJr SSKJr "S S \5rg) )AnyIterableListOptionalTuplecast)uuid4N)Document) Embeddings) get_from_env) VectorStore)DistanceStrategycD\rSrSr%SrSr\\S'S\-r\ RS4S\S\ S \ S \ S \4 S jjr \S \4Sj5rS \4SjrS \4SjrS \4SjrS$S\\S\\\S\ S\S \\4 Sjjr\S \ 4Sj5rS%S\\\S\S \\4SjjrS&S \\S\ S \\4SjjrS&S\S\ S\S \\4SjjrS&S\S\ S\S \\ \\44Sjjr!S&S \\S\ S\S \\4S jjr"\#SSS!S\ R4S\\S \ S\\\S\S\ S \S \ S\S S4S"jj5r$S#r%g)'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_keychXlX lU=(d [SS5UlX0lX@lg)z#initialize the SemaDB vector store.rSEMADB_API_KEYN)rrr r _embeddingr)selfrrrrrs _/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/semadb.py__init__SemaDB.__init__s/ /&K,y:J"K #!2returnc>SUR[RS.$)zReturn the common headers.zapplication/json)z content-typezX-RapidAPI-KeyzX-RapidAPI-Host)rrrrs rheadersSemaDB.headers.s/"ll%{{  r cUR[R:XagUR[R:Xa [ S5eUR[R :XagUR[R :Xa [ S5eUR[R:Xag[ SUR35e)z&Return the internal distance strategy. euclideanz,Max inner product is not supported by SemaDBdotcosinezUnknown distance strategy )rrEUCLIDEAN_DISTANCEMAX_INNER_PRODUCT ValueError DOT_PRODUCTJACCARDCOSINEr#s r_get_internal_distance_strategy&SemaDB._get_internal_distance_strategy7s  ! !%5%H%H H  # #'7'I'I IKL L  # #'7'C'C C  # #'7'?'? ?KL L  # #'7'>'> >9$:P:P9QRS Sr cURURUR5S.n[R"[ R S-UURS9nURS:H$)z/Creates the corresponding collection in SemaDB.)id vectorSizedistanceMetricz /collectionsjsonr$) rrr0requestspostrBASE_URLr$ status_code)rpayloadresponses rcreate_collectionSemaDB.create_collectionFsb&&**"BBD  == OOn ,LL  ##s**r c[R"[RSUR3-UR S9nUR S:H$)z/Deletes the corresponding collection in SemaDB. /collections/)r$r8)r9deleterr;rr$r<)rr>s rdelete_collectionSemaDB.delete_collectionTsD?? OO d.B.B-CD DLL ##s**r Ntexts metadatas batch_sizekwargsc [U[5(d [U5nURRU5n[ US5UR :wa'[ S[ US5SUR 35eUR[R:Xad[R"U5nU[RRUSSS9- n[[[[ UR#55n/n/nUbV[%XU5HEupn ['[)55n UR+U 5 UR+U U 0U ESU 0ES.5 MG OO[%X5H@up['[)55n UR+U 5 UR+U U SU 0S.5 MB [-S[ U5U5Hn XX-n[.R0"[2R4S UR6S 3-S U0UR8S 9nUR:S :wa$[=SU5 [ SUR>35eURA5Sn[ U5S:dM[ SU35e U$)zAdd texts to the vector store.rzEmbedding size mismatch z != T)axiskeepdimstext)r3vectormetadatarB/pointspointsr6r8zHERE--zError adding points: failedRanges)! isinstancelistrembed_documentslenrr,rrr/nparraylinalgnormrrfloattolistzipstrr appendranger9r:rr;rr$r<printrNr7)rrFrGrHrI embeddings embed_matrixidsrRrNrrPnew_idibatchr> failed_rangess r add_textsSemaDB.add_texts\sQ%&&KE__44U; z!} !1!1 1*3z!}+=*>d4CSCSBTU   ! !%5%<%< <88J/L'"))..1t+9+Ld4;/1D1D1FGJ  -0I-N)UW 6" $"+$Bx$BFD>$B.O$'u#9UW 6" $"+%+TN$:q#f+z2Aq~.E}}M$2F2F1Gw"OO& H ##s*h& #8!HII$MMON;M=!A% #8!HII3 r cUR$)zReturn the embeddings.)rr#s rrcSemaDB.embeddingssr rec SU0n[R"[RSURS3-UUR S9nUR S:H=(a [UR5S5S:H$)zDelete 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. rerBrQr6r8 failedPointsr) r9rCrr;rr$r<rWr7)rrerIr=r>s rrC SemaDB.deletest 3 ?? OO d.B.B-C7K KLL  ##s*Xs8==?>3R/SWX/XXr kcUR[R:Xa][R"U5nU[R R U5- n[[[UR55nUUS.n[R"[RSURS3-UUR S9nUR"S:wa[%SUR&35eUR)5S$)zSearch points.)rOlimitrBz/points/searchr6r8zError searching: rR)rrr/rXrYrZr[rrr\r]r9r:rr;rr$r<r,rNr7)rrrqvecr=r>s r_search_pointsSemaDB._search_pointss  ! !%5%<%< <((9%C s++CT%[#**,7I  == OO d.B.B-C>R RLL    3 &0@A A}}x((r queryc VURRU5nURXBS9$)z"Return docs most similar to query.rq)r embed_querysimilarity_search_by_vector)rrwrqrIquery_embeddings rsimilarity_searchSemaDB.similarity_searchs,//55e<///EEr c URRU5nURXBS9nUVs/sHn[USSUSS9US4PM sn$s snf)z$Run similarity search with distance.ryrPrN page_contentrPdistance)rrzrur )rrwrqrIr|rRps rsimilarity_search_with_score#SemaDB.similarity_search_with_scoresv//55e<$$_$:   a mF&;a mT*      s!Ac pURXS9nUVs/sHn[USSUSS9PM sn$s snf)zReturn docs most similar to embedding vector. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of Documents most similar to the query vector. ryrPrNr)rur )rrrqrIrRrs rr{"SemaDB.similarity_search_by_vectorsR$$Y$4  !J-"7!J- P   s3rc U(d [S5eU(d [S5eU(d [S5eU"UUUUUS9n U R5(d [S5eU RXS9 U $)z9Return VectorStore initialized from texts and embeddings.z Collection name must be providedzVector size must be providedzAPI key must be provided)rrzError creating collection)rG)r,r?rj) clsrFrrGrrrrrIsemadbs r from_textsSemaDB.from_textss}?@ @;< <78 8   /  ''))89 94 r )rrrrr)Ni)N))&__name__ __module__ __qualname____firstlineno____doc__rr___annotations__r;rr*intr rpropertydictr$r0boolr?rDrrrrrjrcrCr\rur r}rrr{ classmethodr__static_attributes__r rrrs (D#'D H/?.Q.Q 3 3 3 3 , 3  3    T T +4 ++4++/ ?}?DJ'? ?  ? c ?BJY(49-YYQUY*)U ))DJ),$%FF F03F hF$%       03  eHeO$ %  01 e ), .Q.QCyDJ'     , r r)typingrrrrrruuidr numpyrXr9langchain_core.documentsr langchain_core.embeddingsr langchain_core.utilsr langchain_core.vectorstoresr &langchain_community.vectorstores.utilsrrrr rrs1==-0-3CB[Br