hRddlmZddlZddlZddlZddlmZmZmZm Z m Z m Z m Z m Z mZddlZddlmZddlmZddlmZddlmZmZerddlmZdd lmZmZej>e Z!dd Z"e d d Z#Gdd eZ$y)) annotationsN) TYPE_CHECKINGAnyCallableIterableListOptionalTupleTypeVarUnion)Document) Embeddings) VectorStore)DistanceStrategymaximal_marginal_relevanceClient)NeighborVectorDistanceMetriccN ddlm}|S#t$r}td|d}~wwxYw)NrrzoCould not import aerospike_vector_search python package. Please install it with `pip install aerospike_vector`.)aerospike_vector_searchr ImportError)res h/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/langchain_community/vectorstores/aerospike.py_import_aerospiker#s;2 M  E  s $ $AVST Aerospike)boundcNeZdZdZdddddej f ddZeddZddZ dd Z e dd Z d dd Z d dd Z d d d Z d d!dZ d d"dZ d d#dZd$dZe d%dZ d& d'dZ d& d(dZe d) d*dZy)+rzu`Aerospike` vector store. To use, you should have the ``aerospike_vector_search`` python package installed. N_vector_text_idc Dt} t|tstjdt|| st dt |||_||_||_ ||_ ||_ ||_ ||_ ||_|j| |_y)aInitialize with Aerospike client. Args: client: Aerospike client. embedding: Embeddings object or Callable (deprecated) to embed text. namespace: Namespace to use for storing vectors. This should match index_name: Name of the index previously created in Aerospike. This vector_key: Key to use for vector in metadata. This should match the key used during index creation. text_key: Key to use for text in metadata. id_key: Key to use for id in metadata. set_name: Default set name to use for storing vectors. distance_strategy: Distance strategy to use for similarity search This should match the distance strategy used during index creation. z`Passing in `embedding` as a Callable is deprecated. Please pass in an Embeddings object instead.zDclient should be an instance of aerospike_vector_search.Client, got N)r isinstancerwarningswarn ValueErrortype_client _embedding _text_key _vector_key_id_key _index_name _namespace _set_nameconvert_distance_strategy_distance_strategy) selfclient embedding namespace index_name vector_keytext_keyid_keyset_namedistance_strategy aerospikes r__init__zAerospike.__init__7s<&' )Z0 MM.  &),F|n&   #!% %#!"&"@"@AR"ScPt|jtr |jSy)z/Access the query embedding object if available.N)r$r*rr3s r embeddingszAerospike.embeddingsms dooz 2?? "r?ct|jtr$|jjt |S|Dcgc]}|j|c}Scc}w)zEmbed search docs.)r$r*rembed_documentslist)r3textsts r_embed_documentszAerospike._embed_documentstsF dooz 2??224;? ?,12q"222sAct|jtr|jj|S|j|S)zEmbed query text.)r$r*r embed_query)r3texts r _embed_queryzAerospike._embed_queryzs4 dooz 2??..t4 4t$$r?cddlm}t|tr|S||jk(rtjS||j k(rtj S||j k(rtjStd)z Convert Aerospikes distance strategy to langchains DistanceStrategy enum. This is a convenience method to allow users to pass in the same distance metric used to create the index. r)rDUnknown distance strategy, must be cosine, dot_product, or euclidean) aerospike_vector_search.typesrr$rCOSINE DOT_PRODUCTSQUARED_EUCLIDEANEUCLIDEAN_DISTANCEr')r<rs rr1z#Aerospike.convert_distance_strategys{ G ')9 :$ $  4 ; ; ;#** *  4 @ @ @#// /  4 F F F#66 6 R  r?c 4| |j}| |j}|r | tdt|}|xs+|D cgc]} t t j !c} }|r|D cgc]} | j}} n|xs|D cgc]} ic} }tdt||D]} || | |z} || | |z} || | |z}|j| }t||| D]$\}}}|||j<|||j<&t| |D]?\}}|||j<|jj d|j"|||d|A|r'|jj%|j"||Scc} wcc} wcc} w)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 metadata associated with the texts. ids: Optional list of ids to associate with the texts. set_name: Optional aerospike set name 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. index_name: Optional aerospike index name used for waiting for index completion. If not provided, the default index_name will be used. wait_for_index: If True, wait for the all the texts to be indexed before returning. Requires index_name to be provided. Defaults to True. kwargs: Additional keyword arguments to pass to the client upsert call. Returns: List of ids from adding the texts into the vectorstore. z6if wait_for_index is True, index_name must be providedr)r6keyr; record_data)r6name)r0r.r'rEstruuiduuid4copyrangelenrHzipr,r+r-r)upsertr/wait_for_index_completion)r3rF metadatasidsr;embedding_chunk_sizer7wait_for_indexkwargs_mi chunk_texts chunk_idschunk_metadatasrBmetadatar5rKids r add_textszAerospike.add_textss@  ~~H  ))J j0UV VU 77Ac$**,'7 +45a5I5!8%%8Qb%8Iq#e*&:; AA(<$<=KA$8 89I'A0D,DEO..{;J-0[. 0))T.7))*+/(  0 !$I ?  H)+&# ##"oo% (     ,  LL 2 2// 3   I86%8s$F ,F Fc ddlm}|r2|D]-} |jjd|j||d|/y#|$rYywxYw)a7Delete by vector ID or other criteria. Args: ids: List of ids to delete. **kwargs: Other keyword arguments to pass to client delete call. Returns: Optional[bool]: True if deletion is successful, False otherwise, None if not implemented. r)AVSServerError)r6rUr;FTrX)rrqr)deleter/)r3rcr;rfrqrns rrrzAerospike.deletesg ;  !!'DLL''"&//!)!  !&! !s*<AAc N|j|j|f|||d|S)aReturn aerospike 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. metadata_keys: List of metadata keys to return with the documents. If None, all metadata keys will be returned. Defaults to None. index_name: Name of the index to search. Overrides the default index_name. kwargs: Additional keyword arguments to pass to the search method. Returns: List of Documents most similar to the query and associated scores. k metadata_keysr7)&similarity_search_by_vector_with_scorerL)r3queryrurvr7rfs rsimilarity_search_with_scorez&Aerospike.similarity_search_with_score s?.;t::   e $ '!     r?c g}|r|j|vr|jg|z}| |j}| td|jjd||j |||d|}|D]}|j } |j| vrF| j|j} |j} |jt| | | fctjd|jd|S)aReturn aerospike documents most similar to embedding, along with scores. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. metadata_keys: List of metadata keys to return with the documents. If None, all metadata keys will be returned. Defaults to None. index_name: Name of the index to search. Overrides the default index_name. kwargs: Additional keyword arguments to pass to the client vector_search method. Returns: List of Documents most similar to the query and associated scores. zindex_name must be provided)r7r6rxlimit field_names) page_contentrmzFound document with no `z` key. Skipping.rX) r+r.r'r) vector_searchr/fieldspopdistanceappendr loggerwarning) r3r5rurvr7rfdocsresultsresultrmrKscores rrwz0Aerospike.similarity_search_by_vector_with_score*s2 T^^=@!^^,}>NO  r?c b|j|f|||d|Dcgc]\}}| c}}Scc}}w)akReturn docs most similar to embedding vector. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. metadata_keys: List of metadata keys to return with the documents. If None, all metadata keys will be returned. Defaults to None. index_name: Name of the index to search. Overrides the default index_name. kwargs: Additional keyword arguments to pass to the search method. Returns: List of Documents most similar to the query vector. rt)rw)r3r5rurvr7rfdocrgs rsimilarity_search_by_vectorz%Aerospike.similarity_search_by_vectorfsQ2F$EE+%     Q    s +c f|j|f|||d|}|Dcgc]\}}| c}}Scc}}w)a*Return aerospike documents most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. metadata_keys: List of metadata keys to return with the documents. If None, all metadata keys will be returned. Defaults to None. index_name: Optional name of the index to search. Overrides the default index_name. Returns: List of Documents most similar to the query and score for each rt)ry) r3rxrurvr7rfdocs_and_scoresrrgs rsimilarity_searchzAerospike.similarity_searchsG*<$;;  m  NT #22Q222s -c|jtjk(r |jS|jtjk(r |j S|jtj k(r |jStd)a 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. 0 is dissimilar, 1 is similar. Aerospike's relevance_fn assume euclidean and dot product embeddings are normalized to unit norm. rN) r2rrP_cosine_relevance_score_fnrQ%_max_inner_product_relevance_score_fnrS_euclidean_relevance_score_fnr'rAs r_select_relevance_score_fnz$Aerospike._select_relevance_score_fnsw  " "&6&=&= =22 2  $ $(8(D(D D== =  $ $(8(K(K K55 5V r?cd|dz z S)zgAerospike returns cosine distance scores between [0,2] 0 is dissimilar, 1 is similar. rX)rs rrz$Aerospike._cosine_relevance_score_fns EAIr?c |r|j|vr|jg|z}|j|f|||d|}ttj|gtj |D cgc]} | j |jc} ||} |r=|j|vr/| D]*} || j j|j,| D cgc]} ||  c} Scc} 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. metadata_keys: List of metadata keys to return with the documents. If None, all metadata keys will be returned. Defaults to None. index_name: Optional name of the index to search. Overrides the default index_name. Returns: List of Documents selected by maximal marginal relevance. rt)dtype)ru lambda_mult)r,rrnparrayfloat32rmr) r3r5rufetch_krrvr7rfrr mmr_selectedris r'max_marginal_relevance_search_by_vectorz1Aerospike.max_marginal_relevance_search_by_vectors< T--]B!--.>M/t//  '!    2 HHi[ 37; <S\\$** + <#   T-->! 7Q  $$T%5%56 7"..AQ.. =/s & C"  C'c V|j|}|j||||f||d|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. index_name: Name of the index to search. Returns: List of Documents selected by maximal marginal relevance. )rvr7)rLr) r3rxrurrrvr7rfr5s rmax_marginal_relevance_searchz'Aerospike.max_marginal_relevance_searchsL6%%e, ;t;;     (!    r?c  T||||fi| } | j|f||||d| xsi| S)a This is a user friendly interface that: 1. Embeds text. 2. Converts the texts into documents. 3. Adds the documents to a provided Aerospike index This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import Aerospike from langchain_openai import OpenAIEmbeddings from aerospike_vector_search import Client, HostPort client = Client(seeds=HostPort(host="localhost", port=5000)) aerospike = Aerospike.from_texts( ["foo", "bar", "baz"], embedder, client, "namespace", index_name="index", vector_key="vector", distance_strategy=MODEL_DISTANCE_CALC, ) )rbrcr7rd)ro) clsrFr5rbr4r6r7rcembeddings_chunk_size client_kwargsrfr=s r from_textszAerospike.from_textss_P          !!6  "  r?)r4rr5zUnion[Embeddings, Callable]r6rYr7 Optional[str]r8rYr9rYr:rYr;rr<z7Optional[Union[DistanceStrategy, VectorDistanceMetric]])returnzOptional[Embeddings])rF Iterable[str]rzList[List[float]])rKrYr List[float])r<z-Union[VectorDistanceMetric, DistanceStrategy]rr)NNNNT)rFrrbOptional[List[dict]]rcOptional[List[str]]r;rrdintr7rreboolrfrr List[str])NN)rcrr;rrfrrzOptional[bool])NN) rxrYrurrvrr7rrfrrList[Tuple[Document, float]]) r5rrurrvrr7rrfrrr) r5rrurrvrr7rrfrrList[Document]) rxrYrurrvrr7rrfrrr)rzCallable[[float], float])rfloatrr)rg?NN)r5rrurrrrrrvrr7rrfrrr)rxrYrurrrrrrvrr7rrfrrr)NNtestNNrN)rFrr5rrbrr4rr6rYr7rrcrrrrzOptional[dict]rfrrr)__name__ __module__ __qualname____doc__rrSr>propertyrBrHrL staticmethodr1rorrryrwrrrrrr classmethodrrXr?rrr1s"%)#"&  / /4T4T/4T 4T " 4T  4T4T4T 4T 4Tl 3 %  H   :+/#'"&$($(#NN(N! N  N " N"NNN Nd$("&     F-1$(     +  "     & D-1$( :: :+ : " :  : &:~-1$(       +  "       J-1$( 33 3+ 3 " 3  3 342 -1$(3/3/ 3/ 3/  3/ + 3/"3/3/ 3/p -1$($ $  $  $  $ + $ "$ $  $ L +/$(#'%)(,666( 6  6  6"6!6 #6&66 66r?)rr)% __future__rloggingrZr%typingrrrrrr r r r numpyrlangchain_core.documentsr langchain_core.embeddingsrlangchain_core.vectorstoresr&langchain_community.vectorstores.utilsrrrrrOrr getLoggerrrrrrrXr?rrsq"    -03 .L   8 $v[)d dr?