a bg3@sddlmZddlZddlZddlmZmZmZmZm Z ddl Z ddl m Z ddlmZddlmZddlmZeeZGdd d eZdS) ) annotationsN)AnyIterableListOptionalTuple)Document) Embeddings) VectorStore)maximal_marginal_relevancec@s2eZdZdZdddddddddd d d d d d d dd ddZeddddZd9ddd d d d ddddZd:d d dd d d!d"d#d$Zd;d d dd d d%d"d&d'Z dd d d d6d7d8ZdS)?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") NirootZ123123F)client index_name dimensionhostuserpasswordself_idr strrz Optional[str]intzOptional[List[str]]bool) embeddingtext_keyrrrrrrrc Csz ddl} Wnty&tdYn0|dur4|ndg}|durH|} nFz| |||} Wn2ty} ztd| WYd} ~ n d} ~ 00||_| |_|dur|| vr|| vr| dur| j||ddn| j||d ||_ ||_ 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: TFrZauto_idr) dingodb ImportErrorDingoDB ValueError _text_key_client get_indexupper create_index _index_name _embedding) selfrrrrrrrrrr dingo_clienter,t/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_community/vectorstores/dingo.py__init__ s8   $ zDingo.__init__zOptional[Embeddings])returncCs|jS)N)r(r)r,r,r- embeddingsTszDingo.embeddingstextz Iterable[str]zOptional[List[dict]]z List[str])texts metadatasidsr batch_sizekwargsr/c Ks|pdd|D}g}t|}|j|}t|D],\} } |rF|| ni} | | |j<|| q2tdtt||D]D} | |} |j |j || | || | || | } | stt dqt|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. cSs"g|]}ttjddqSN ruuiduuid4r.0_r,r,r- nz#Dingo.add_texts..rvector add fail) listr(embed_documents enumerater"appendrangelenr# vector_addr' Exception)r)r4r5r6rr7r8metadatas_listembedsir2metadatajadd_resr,r,r- add_textsXs    " zDingo.add_textszOptional[dict]z Optional[int]zList[Document])queryk search_paramstimeoutr8r/cKs&|j|f||d|}dd|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 )rUrVcSsg|] \}}|qSr,r,)r?docr@r,r,r-rArBz+Dingo.similarity_search..)similarity_search_with_score)r)rTrUrVrWr8Zdocs_and_scoresr,r,r-similarity_searchszDingo.similarity_searchzList[Tuple[Document, float]]cKsg}|j|}|jj|j|||d}|s.gS|ddD]} | d} d|vrl|ddurl| |dkrlq:| d} | d} | |jd dd } | | | d }| D]}| |d dd ||<q|t | |d | fq:|S) rX)xqtop_krVrvectorWithDistancesZdistanceZscore_thresholdN scalarDataidfieldsdata)r`r2scoreZ page_contentrO) r( embed_queryr# vector_searchr'getr"keysrGr)r)rTrUrVrWr8docsZ query_objresultsresrcr5r`r2rOZmeta_keyr,r,r-rZs.     z"Dingo.similarity_search_with_score?z List[float]float)rrUfetch_k lambda_multrVr8r/c  sjjj|g||d}ttj|gtjddd|ddD||d}g} |D]R} i} |dd| dD]&\}} | t || d dd iqp| | qPfd d| 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. )rVr])ZdtypecSsg|]}|ddqS)ZvectorZ floatValuesr,)r?itemr,r,r-rAszADingo.max_marginal_relevance_search_by_vector..rr^)rUrpr_rarbcs g|]}t|j|dqS)rd)rpopr")r?rOr0r,r-rAs) r#rfr'r nparrayZfloat32itemsupdaterrG) r)rrUrorprVr8rjZ mmr_selectedselectedrNZ meta_datavr,r0r-'max_marginal_relevance_search_by_vectors(       z-Dingo.max_marginal_relevance_search_by_vector)rTrUrorprVr8r/cKs|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(rery)r)rTrUrorprVr8rr,r,r-max_marginal_relevance_searchs  z#Dingo.max_marginal_relevance_searchr)r4rr5r6rrrrrrrr7r8r/c  Ksz ddl}Wnty&tdYn0|dur6|}nFz|| | | }Wn2tyz}ztd|WYd}~n d}~00| dur| ddur|dur||vr||vr|j||ddn2|dur||vr||vr|j||d |p d d |D}g}t|}| |}t |D].\}}|rB||ni}|||<| |q,t dt t|| D]D}|| }|||||||||||}|sptd qp|||||d 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`.rrTFrrcSs"g|]}ttjddqSr9r;r>r,r,r-rA^rBz$Dingo.from_texts..rC)rr)rrr r!rgr$r%r&rDrErFrGrHrIrJrK)clsr4rr5r6rrrrrrrr7r8rr*r+rLrMrNr2rOrPrQr,r,r- from_textssZ'   $     zDingo.from_texts)r6r8r/cKs"|durtd|jj|j|dS)z^Delete by vector IDs or filter. Args: ids: List of ids to delete. NzNo ids provided to delete.)r6)r!r#Z vector_deleter')r)r6r8r,r,r-deleteqs z Dingo.delete)NNr2r3)rSNN)rSNN)rSrlrmN)rSrlrmN)N)__name__ __module__ __qualname____doc__r.propertyr1rRr[rZryrz classmethodr|r}r,r,r,r-r s`"4,04,^r ) __future__rloggingr<typingrrrrrnumpyrsZlangchain_core.documentsrZlangchain_core.embeddingsr Zlangchain_core.vectorstoresr Z&langchain_community.vectorstores.utilsr getLoggerr~loggerr r,r,r,r-s