jD.ddlmZddlZddlZddlZddlZddlmZmZm Z m Z m Z m Z m Z mZddlZddlmZddlmZddlmZddlmZddlmZdd lmZdd lmZmZerdd l m!Z!ejDe#Z$dd Z%dd Z&edddGddeZ'y)) annotationsN) TYPE_CHECKINGAnyCallableIterableListOptionalTupleUnion) deprecated)Document) Embeddings) batch_iterate) VectorStore)version)DistanceStrategymaximal_marginal_relevance)IndexcJ ddl}|S#t$r}td|d}~wwxYw)NrzYCould not import pinecone python package. Please install it with `pip3 install pinecone`.)pinecone ImportError)res s/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/vectorstores/pinecone.py_import_pineconers: O  >  s " "ct}|j}tj|tjdk\S)Nz 3.0.0.dev)r __version__rparse)rpinecone_client_versions r_is_pinecone_v3r's4!H&22 ==0 1W]];5O OOz0.0.18z1.0zlangchain_pinecone.Pinecone)sinceremovalalternative_importcReZdZdZdej f ddZeddZddZ ddZ d ddZ d dd Z dddd  dd Z d dd Zdd Zed dZ d! d"dZ d! d#dZe d$ d%dZe d& d'dZe d( d)dZ d* d+dZy),Pineconez`Pinecone` vector store. To use, you should have the ``pinecone`` python package installed. This version of Pinecone is deprecated. Please use `langchain_pinecone.Pinecone` instead. Nct}t|tstjdt||j st dt|||_||_ ||_ ||_ ||_ y)z Initialize with Pinecone client.z`Passing in `embedding` as a Callable is deprecated. Please pass in an Embeddings object instead.z4client should be an instance of pinecone.Index, got N) r isinstancerwarningswarnr ValueErrortype_index _embedding _text_key _namespacedistance_strategy)selfindex embeddingtext_key namespacer0rs r__init__zPinecone.__init__9sx$%)Z0 MM. %0FtE{mT  #!#!2r cPt|jtr |jSy)z/Access the query embedding object if available.N)r'r-rr1s r embeddingszPinecone.embeddingsRs dooz 2?? "r ct|jtr$|jjt |S|Dcgc]}|j|c}Scc}w)zEmbed search docs.)r'r-rembed_documentslist)r1textsts r_embed_documentszPinecone._embed_documentsYsJ dooz 2??224;? ?,12Eq"E222sAct|jtr|jj|S|j|S)zEmbed query text.)r'r-r embed_query)r1texts r _embed_queryzPinecone._embed_query_s4 dooz 2??..t4 4t$$r c t| |j}t|}|xs+|Dcgc]}ttj!c}}|xs|Dcgc]}ic}}t ||D]\} } | | |j <tdt||D]} || | |z} || | |z} || | |z}|j| }t|t | ||Dcgc]"}|jjd||dd|$}}|Dcgc]}|jc}|Scc}wcc}wcc}wcc}w)aRun more texts through the embeddings and add to the vectorstore. Upsert optimization is done by chunking the embeddings and upserting them. This is done to avoid memory issues and optimize using HTTP based embeddings. For OpenAI embeddings, use pool_threads>4 when constructing the pinecone.Index, embedding_chunk_size>1000 and batch_size~64 for best performance. Args: texts: Iterable of strings to add to the vectorstore. metadatas: Optional list of metadatas associated with the texts. ids: Optional list of ids to associate with the texts. namespace: Optional pinecone namespace to add the texts to. batch_size: Batch size to use when adding the texts to the vectorstore. embedding_chunk_size: Chunk size to use when embedding the texts. Returns: List of ids from adding the texts into the vectorstore. rT)vectorsr5 async_req)r/r<struuiduuid4zipr.rangelenr?rr,upsertget)r1r= metadatasidsr5 batch_sizeembedding_chunk_sizekwargs_metadatarBi chunk_texts chunk_idschunk_metadatasr9batch async_resress r add_textszPinecone.add_textsesq8  IU 77Ac$**,'74e!4e"e!4 !)U3NHd'+HT^^ $4 q#e*&:;AA(<$<=KA$8 89I'A0D,DEO..{;J+Iz? K E # ""!'"    #, ,)3SWWY) ,!<$ 58!4  -s$D& D+'D0D5cJ|j|j||||S)aReturn pinecone documents most similar to query, along with scores. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. filter: Dictionary of argument(s) to filter on metadata namespace: Namespace to search in. Default will search in '' namespace. Returns: List of Documents most similar to the query and score for each kfilterr5)&similarity_search_by_vector_with_scorerC)r1queryrbrcr5s rsimilarity_search_with_scorez%Pinecone.similarity_search_with_scores0$::   e $&I;  r racf| |j}g}|jj|g|d||}|dD]w}|d}|j|vr?|j |j} |d} |j t | || fUtjd|jdy|S) zGReturn pinecone documents most similar to embedding, along with scores.T)vectortop_kinclude_metadatar5rcmatchesrVscore page_contentrVzFound document with no `z` key. Skipping.) r/r,rer.popappendr loggerwarning) r1r3rbrcr5docsresultsr]rVrBrls rrdz/Pinecone.similarity_search_by_vector_with_scores  I++##;! $ 9%C:H~~)||DNN3G  X4(KUST.t~~.>>NO& r c f|j|f|||d|}|Dcgc]\}}| c}}Scc}}w)aReturn pinecone documents most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. filter: Dictionary of argument(s) to filter on metadata namespace: Namespace to search in. Default will search in '' namespace. Returns: List of Documents most similar to the query and score for each ra)rf) r1rerbrcr5rTdocs_and_scoresdocrUs rsimilarity_searchzPinecone.similarity_searchsK&<$;;  v >D #22/Q/222s -c|jtjk(r |jS|jtjk(r |j S|jtj k(r |jStd)a8 The 'correct' relevance function may differ depending on a few things, including: - the distance / similarity metric used by the VectorStore - the scale of your embeddings (OpenAI's are unit normed. Many others are not!) - embedding dimensionality - etc. zXUnknown distance strategy, must be cosine, max_inner_product (dot product), or euclidean) r0rCOSINE_cosine_relevance_score_fnMAX_INNER_PRODUCT%_max_inner_product_relevance_score_fnEUCLIDEAN_DISTANCE_euclidean_relevance_score_fnr*r8s r_select_relevance_score_fnz#Pinecone._select_relevance_score_fnsy  ! !%5%<%< <22 2  # #'7'I'I I== =  # #'7'J'J J55 5. r c|dzdz S)z8Pinecone returns cosine similarity scores between [-1,1]rG)rls rr{z#Pinecone._cosine_relevance_score_fns Qr c | |j}|jj|g|dd||}tt j |gtj |dD cgc]} | d c} ||} | D cgc] } |d| d} } | D cgc](} t| j|j| *c} Scc} wcc} wcc} w) 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. T)rhriinclude_valuesrjr5rc)dtyperkvalues)rb lambda_multrVrm) r/r,rernparrayfloat32r ror.)r1r3rbfetch_krrcr5rTrtitem mmr_selectedrWselectedrVs r'max_marginal_relevance_search_by_vectorz0Pinecone.max_marginal_relevance_search_by_vector s4  I++##;! $ 2 HHi[ 3(/ (: ;(:T(^(: ;#  @LL|!GI&q)*5|L% $ (,,"@8 T$  <M s" C <C -Cc P|j|}|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. )rCr) r1rerbrrrcr5rTr3s rmax_marginal_relevance_searchz&Pinecone.max_marginal_relevance_search:s44%%e, ;; q';   r ct}trg|jtjj d|}|j }|jdDcgc]}|j}}n|j }||vr2trj|}|S|j||}|St|dk(r tdtd|dd j|cc}w) zReturn a Pinecone Index instance. Args: index_name: Name of the index to use. pool_threads: Number of threads to use for index upsert. Returns: Pinecone Index instance.PINECONE_API_KEY)api_key pool_threadsindexes)rrzNo active indexes found in your Pinecone project, are you sure you're using the right Pinecone API key and Environment? Please double check your Pinecone dashboard.zIndex 'zQ' not found in your Pinecone project. Did you mean one of the following indexes: z, ) rrr%osenvironrO list_indexes index_listnamerrMr*join) cls index_namerrpinecone_instancerrW index_namesr2s rget_pinecone_indexzPinecone.get_pinecone_indexYs$%   ( 1 1 '9:!2! (446G+2+=+=i+HI+Ha166+HKI"//1K  $#$"'' 3   ^^J\^J     "?  *&>>Bii >T=UW #Js&C;c ||j|| } || |||fi| }|j|f||||| d| xsi|S)a DEPRECATED: use langchain_pinecone.PineconeVectorStore.from_texts instead: Construct Pinecone wrapper from raw documents. This is a user friendly interface that: 1. Embeds documents. 2. Adds the documents to a provided Pinecone index This is intended to be a quick way to get started. The `pool_threads` affects the speed of the upsert operations. Example: .. code-block:: python from langchain_pinecone import PineconeVectorStore from langchain_openai import OpenAIEmbeddings embeddings = OpenAIEmbeddings() index_name = "my-index" namespace = "my-namespace" vectorstore = Pinecone( index_name=index_name, embedding=embedding, namespace=namespace, ) )rPrQr5rRrS)rr^)rr=r3rPrQrRr4r5r upsert_kwargsrembeddings_chunk_sizerTpinecone_indexrs r from_textszPinecone.from_textssiV// LI~y(IPP  !!6  " r c<|j||}|||||S)z*Load pinecone vectorstore from index name.)r)rrr3r4r5rrs rfrom_existing_indexzPinecone.from_existing_indexs'// LI>9h BBr c J| |j}|r |jjd d|d|y|Ed}tdt ||D])}||||z}|jjd ||d|+y| |jjd ||d|yt d) zDelete by vector IDs or filter. Args: ids: List of ids to delete. filter: Dictionary of conditions to filter vectors to delete. NT) delete_allr5r)rQr5)rcr5z3Either ids, delete_all, or filter must be provided.rG)r/r,deleterLrMr*) r1rQrr5rcrT chunk_sizerWchunks rrzPinecone.deletes  I  DKK   N$) Nv N_J1c#h 3AJ/" ""Lu LVL4   DKK   Lf LV LRS Sr ) r2rr3zUnion[Embeddings, Callable]r4rHr5 Optional[str]r0zOptional[DistanceStrategy])returnzOptional[Embeddings])r= Iterable[str]rzList[List[float]])rBrHr List[float])NNN r)r=rrPOptional[List[dict]]rQOptional[List[str]]r5rrRintrSrrTrr List[str])r_NN) rerHrbrrcOptional[dict]r5rrList[Tuple[Document, float]]) r3rrbrrcrr5rrr) rerHrbrrcrr5rrTrrList[Document])rzCallable[[float], float])rlfloatrr)r_g?NN)r3rrbrrrrrrcrr5rrTrrr)rerHrbrrrrrrcrr5rrTrrr)r_)rrrrrr) NNrrBNNNr_r)r=rr3rrPrrQrrRrr4rHr5rrrrrrrrrrTrrr%)rBNr_) rrHr3rr4rHr5rrrrr%)NNNN) rQrrzOptional[bool]r5rrcrrTrrNone)__name__ __module__ __qualname____doc__rrzr6propertyr9r?rCr^rfrdrxr staticmethodr{rr classmethodrrrrrGr rr%r%-s$(8H8O8O 33/3 3 ! 3 6 32 3 %+/#'#'$(::(:! : ! :  :":: :~!%#'       !  &  4!%#'      !  &F!%#' 33 3 3 ! 3  3 30, !%#'. .  .  .  .  . !. .  . f !%#'          !    >)!))  ))V +/#'#'$((,%)666( 6 ! 6  66!6"6&66 #66 66p #' C C C C ! C  C  C C$(%)#'!%  #!      r r%)rr)rbool)( __future__rloggingrrIr(typingrrrrrr r r numpyrlangchain_core._api.deprecationr langchain_core.documentsr langchain_core.embeddingsrlangchain_core.utils.iterrlangchain_core.vectorstoresr packagingr&langchain_community.vectorstores.utilsrrrr getLoggerrrqrrr%rGr rrs" WWW6-033    8 $P  E6Sx{xxr