Ng3ddlmZddlZddlZddlmZmZmZmZm Z ddl Z ddl m Z ddlmZddlmZddlmZejeZGdd eZdS) ) annotationsN)AnyIterableListOptionalTuple)Document) Embeddings) VectorStore)maximal_marginal_relevancec eZdZdZddddddddd=dZed>dZ d?d@d&Z dAdBd/Z dAdCd1Z dDdEd8Z dDdFd9Z e ddddddd:gdddf dGd;Z dHdId<ZdS)JDingoax`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_id embeddingr text_keystrrrr Optional[str]rintrOptional[List[str]]rrrboolc ddl} n#t$rtdwxYw||ndg}||} n= | |||} n$#t$r} td| d} ~ wwxYw||_| |_|r|| vr\|| vr4| dur| ||dn| || ||_ ||_ dS) zInitialize with Dingo client.rNzSCould not import dingo python package. Please install it with `pip install dingodb.172.20.31.10:13000Dingo failed to connect: TFrauto_idr) dingodb ImportErrorDingoDB ValueError _text_key_client get_indexupper create_index _index_name _embedding) selfrrrrrrrrrr% dingo_clientes b/var/www/html/ai-engine/env/lib/python3.11/site-packages/langchain_community/vectorstores/dingo.py__init__zDingo.__init__ sp  NNNN   ?   'tt.B-C  !LL B&tXtDD  B B B !@Q!@!@AAA B"#   ","8"8":":::  "",*@*@*B*BBB$)))U*))* )JJJ%#s!A A*A%%A*returnOptional[Embeddings]c|jSN)r/)r0s r3 embeddingszDingo.embeddingsTs texttexts Iterable[str] metadatasOptional[List[dict]]ids batch_sizekwargs List[str]c |p d|D}g}t|}|j|}t|D]0\} } |r|| ni} | | |j<|| 1t dtt||D]R} | |z} |j |j || | || | || | } | stdS|S)aRun 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. chg|]/}ttjjdd0SN ruuiduuid4r.0_s r3 z#Dingo.add_texts..n2@@@Qc$*,,*++CRC0@@@r:rvector add fail) listr/embed_documents enumerater)appendrangelenr* vector_addr. Exception)r0r=r?rArrBrCmetadatas_listembedsir;metadatajadd_ress r3 add_textszDingo.add_textsXs%,@@@%@@@U 0077 '' , ,GAt'08y||bH'+HT^ $  ! !( + + + +q#d5kk**J77 3 3AJAl-- .1"5vac{C!HG 3 1222 3 r:queryk search_paramsOptional[dict]timeout Optional[int]List[Document]c <|j|f||d|}d|DS)vReturn 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 )rcrdcg|]\}}|Srl)rMdocrNs r3rOz+Dingo.similarity_search..s222Q222r:)similarity_search_with_score)r0rbrcrdrfrCdocs_and_scoress r3similarity_searchzDingo.similarity_searchsH$<$;  m  7=  32/2222r:List[Tuple[Document, float]]c Bg}|j|}|j|j|||}|sgS|ddD]} | d} d|vr/|d| |dkr=| d} | d} | |jd dd } | | | d }| D]}| |d dd ||< |t| | | f|S) rj)xqtop_krdrvectorWithDistancesdistancescore_thresholdN scalarDataidfieldsdata)ryr;score page_contentr]) r/ embed_queryr* vector_searchr.getr)keysrUr )r0rbrcrdrfrCdocs query_objresultsresr|r?ryr;r]meta_keys r3rnz"Dingo.similarity_search_with_scoresW$O//66 ,,,  !=-   I1:34 Q QC OE!V++JJ011=6::&78888L)ITBT^,X6q9&AD $??H%NN,, N N%.x%8%B1%Ef%M"" KKthGGGO P P P P r:? List[float]fetch_k lambda_multfloatc jj|g||}tt j|gtjd|ddD||}g} |D]} i} |dd| dD];\}} | t|| ddd i<| | fd | DS) 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. )rdrt)dtypec*g|]}|ddS)vector floatValuesrl)rMitems r3rOzADingo.max_marginal_relevance_search_by_vector..s1   X}-   r:rru)rcrrxrzr{cbg|]+}t|j|,S)r})r popr))rMr]r0s r3rOzADingo.max_marginal_relevance_search_by_vector..sD    (,,t~">"> R R R   r:) r*rr.r nparrayfloat32itemsupdaterrU) r0rrcrrrdrCr mmr_selectedselectedr\ meta_datavs ` r3'max_marginal_relevance_search_by_vectorz-Dingo.max_marginal_relevance_search_by_vectorsH2,,,  yka-  2 Hi[ 3 3 3  #AJ'<=   #    ' 'AI #89!<\JPPRR C C1  #a&&!H+a.*@!ABBBB OOI & & & &    $    r:c h|j|}||||||S)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/rr)r0rbrcrrrdrCrs r3max_marginal_relevance_searchz#Dingo.max_marginal_relevance_searchs<2O//66 ;; q';    r:r c B ddl}n#t$rtdwxYw||}n= || | | }n$#t$r}td|d}~wwxYw| p| ddurY|V||vr@||vr|||dnW|U||vr?||vr||| |p d |D}g}t|}| |}t|D]+\}}|r||ni}|||<| |,tdtt|| D]H}|| z}|||||||||||}|std I||||| S) a=Construct Dingo wrapper from raw documents. This is a user friendly interface that: 1. Embeds documents. 2. Adds the documents to a provided Dingo index This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import Dingo from langchain_community.embeddings import OpenAIEmbeddings import dingodb sss embeddings = OpenAIEmbeddings() dingo = Dingo.from_texts( texts, embeddings, index_name="langchain-demo" ) rNzTCould not import dingo python package. Please install it with `pip install dingodb`.r!rTFr"r$chg|]/}ttjjdd0SrGrIrLs r3rOz$Dingo.from_texts..^rPr:rQ)rr)r%r&r'r(rr+r,r-rRrSrTrUrVrWrXrY)clsr=rr?rArrrrrrrrBrCr%r1r2rZr[r\r;r]r^r_s r3 from_textszDingo.from_textssN  NNNN   @    !LL B&tXtDD  B B B !@Q!@!@AAA B  &**Y"7"74"?"?&l&<&<&>&>>>$$&&l.D.D.F.FFF)))U* &l&<&<&>&>>>$$&&l.D.D.F.FFF))* )JJJ@@@%@@@U **511 '' , ,GAt'08y||bH!%HX   ! !( + + + +q#d5kk**J77 3 3AJA"--N1Q3/!c!A#hG 3 1222 3s9h| SSSSs!A A# AA#c f|td|j|j|S)z^Delete by vector IDs or filter. Args: ids: List of ids to delete. NzNo ids provided to delete.)rA)r(r* vector_deleter.)r0rArCs r3deletez Dingo.deleteqs6 ;9:: :|))$*:)DDDr:)rr rrrrrrrrrrrrrrrr)r5r6)NNr;r<)r=r>r?r@rArrrrBrrCrr5rD)raNN) rbrrcrrdrerfrgrCrr5rh) rbrrcrrdrerfrgrCrr5rq)rarrN)rrrcrrrrrrdrerCrr5rh)rbrrcrrrrrrdrerCrr5rh)r=rDrr r?r@rArrrrrrrrrrrDrrrrrBrrCrr5rr8)rArrCrr5r)__name__ __module__ __qualname____doc__r4propertyr9r`rprnrr classmethodrrrlr:r3rrs  &$($( 2$2$2$2$2$2$hX +/#' '''''X(,!% 333334(,!% +++++` (, / / / / / h (,      < +/#'$(/0 ZTZTZTZT[ZT|$( E E E E E E Er:r) __future__rloggingrJtypingrrrrrnumpyrlangchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr &langchain_community.vectorstores.utilsr getLoggerrloggerrrlr:r3rs"""""" 77777777777777------000000333333MMMMMM  8 $ $mEmEmEmEmEKmEmEmEmEmEr: