dh3SSKJr SSKrSSKrSSKJrJrJrJrJ r SSK r SSK J r SSKJr SSKJr SSKJr \R("\5r"SS \5rg) ) annotationsN)AnyIterableListOptionalTuple)Document) Embeddings) VectorStore)maximal_marginal_relevancec \rSrSrSrSSSSSSSS.SS jjr\SS j5rSSS jjrSSSjjr SSSjjr SSSjjr SSSjjr \ SSS SSSS/SSS 4 S Sjj5rS!S"SjjrSrg)#DingoaX`Dingo` vector store. To use, you should have the ``dingodb`` python package installed. Example: .. code-block:: python from langchain_community.vectorstores import Dingo from langchain_community.embeddings.openai import OpenAIEmbeddings embeddings = OpenAIEmbeddings() dingo = Dingo(embeddings, "text") Niroot123123F)client index_name dimensionhostuserpasswordself_idcSSKn UbUOS/nUbUn OU RXxU5n X lXlUbZXKR 5;aGUR5U R 5;a%U SLaU RXESS9 OU RXES 9 X@l Xl g![a [S5ef=f![an [SU 35eSn A ff=f) zInitialize with Dingo client.rNzSCould not import dingo python package. Please install it with `pip install dingodb.172.20.31.10:13000Dingo failed to connect: TFrauto_idr) dingodb ImportErrorDingoDB ValueError _text_key_client get_indexupper create_index _index_name _embedding) self embeddingtext_keyrrrrrrrr dingo_clientes ^/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/dingo.py__init__Dingo.__init__ s  't.B-C  !L B&ttD "#   ""8"8"::  ",*@*@*BB$))U*))*)J%#E ?   B #[S5e U$s snf)aJRun 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. ids: Optional list of ids to associate with the texts. Returns: List of ids from adding the texts into the vectorstore. N rvector add fail)struuiduuid4intlistr)embed_documents enumerater#appendrangelenr$ vector_addr( Exception)r*texts metadatasidsr, batch_sizekwargs_metadatas_listembedsir7metadatajadd_ress r/ add_textsDingo.add_textsXs,@%@%Qc$**,**+CR0%@U 007 'GA'0y|bH'+T^^ $  ! !( +( q#d5k*J7AAll--  .1"5v{C!HG7 122 8 #As4Dc dUR"U4X#S.UD6nUVVs/sHupxUPM snn$s snnf)>Return Dingo documents most similar to query, along with scores. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. search_params: Dictionary of argument(s) to filter on metadata Returns: List of Documents most similar to the query and score for each )k search_params)similarity_search_with_score) r*queryrXrYtimeoutrLdocs_and_scoresdocrMs r/similarity_searchDingo.similarity_searchsC$;;   7= #22//222s ,c /nURRU5nURRURXrUS9nU(d/$USSHn U Sn SU;a(UR S5bXR S5:aM6U Sn U Sn XR SSS n XU S .nU R5HnXSSS X'M UR[XS 9U 45 M U$) rW)xqtop_krYrvectorWithDistancesdistancescore_threshold scalarDataidfieldsdata)rhr7score page_contentrQ) r) embed_queryr$ vector_searchr(getr#keysrCr )r*r[rXrYr\rLdocs query_objresultsresrkrIrhr7rQmeta_keys r/rZ"Dingo.similarity_search_with_scores$OO//6 ,,,,   =- I1:34C OE!V+JJ01=::&788L)ITB^^,X6q9&AD ?H%NN,%.%8%B1%Ef%M"- KKtGO P5  r6c ,URRURU/XRS9n[[R "U/[R S9USSVs/sH nUSSPM snUUS9n /n U H`n 0n USSU SR5H*up-U R[U5U S SS 05 M, U RU 5 Mb U Vs/sH&n[URUR5US 9PM( sn$s snfs snf) aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. Returns: List of Documents selected by maximal marginal relevance. )rYrc)dtyperrdvector floatValues)rX lambda_multrgrirjrl)r$ror(r nparrayfloat32itemsupdater<rCr popr#)r*r+rXfetch_kr|rYrLrtitem mmr_selectedselectedrP meta_datavrQs r/'max_marginal_relevance_search_by_vector-Dingo.max_marginal_relevance_search_by_vectors42,,,,   yk- 2 HHi[ 3$AJ'<= =DX}-= # AI #89!<\JPPR  #a&!H+a.*@!ABS OOI & % $ (,,t~~"> R$    s D ,Dc ^URRU5nURXrX4U5$)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. fetch_k: Number of Documents to fetch to pass to MMR algorithm. lambda_mult: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. Returns: List of Documents selected by maximal marginal relevance. )r)rnr)r*r[rXrr|rYrLr+s r/max_marginal_relevance_search#Dingo.max_marginal_relevance_searchs22OO//6 ;; '   r6rc SSKnUbUnOURXU 5nU b]U R S5SLaIUbEXoR 5;a2UR 5UR 5;aURXgSS9 OGUbDXoR 5;a1UR 5UR 5;aURXgS 9 U=(d; UVs/sH.n[[R"5R5SS PM0 snn/n[U5nURU5n[U5H*unnU(aUUO0nUUU'URU5 M, [!S[#[U55U 5H7nUU -nUR%UUUUUUUUUU5nU(aM.['S 5e U"X%XS 9$![a [S5ef=f![an[SU35eSnAff=fs snf) aConstruct Dingo wrapper from raw documents. This is a user friendly interface that: 1. Embeds documents. 2. Adds the documents to a provided Dingo index This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import Dingo from langchain_community.embeddings import OpenAIEmbeddings import dingodb sss embeddings = OpenAIEmbeddings() dingo = Dingo.from_texts( texts, embeddings, index_name="langchain-demo" ) rNzTCould not import dingo python package. Please install it with `pip install dingodb`.rrTFrrr:r;)rr)rr r!r"rpr%r&r'r<r=r>r?r@rArBrCrDrErFrG)clsrHr+rIrJr,rrrrrrrKrLrr-r.rMrNrOrPr7rQrRrSs r/ from_textsDingo.from_textssN    !L B&ttD   &**Y"74"?&&<&<&>>$$&l.D.D.FF))U* &&<&<&>>$$&l.D.D.FF))*)J@%@%Qc$**,**+CR0%@U **51 'GAt'0y|bH!%HX   ! !( +( q#d5k*J7AJA"--N1Q/!c!AhG7 122 89|SSe @   B # &$($( 2$2$2$  2$ " 2$2$"2$2$2$2$h +/#' ''('! '  '  '' 'X(,!% 33 3& 3  3  3 34(,!% ++ +& +  +  + &+` (, / /  /  /  / & / /  / h (,         &     < +/#'$(/0 ZTZTZT( ZT ! ZT  ZT"ZTZTZTZTZTZTZTZT ZTZT|$( E  E E E Er6r) __future__rloggingr=typingrrrrrnumpyr}langchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr &langchain_community.vectorstores.utilsr getLoggerrloggerrrr6r/rsC" 77-03M   8 $mEKmEr6