NgYddlmZddlZddlmZmZmZmZmZm Z m Z m Z ddl m Z ddlmZddlmZddlmZerddlmZe d d d Gd deZdS)) annotationsN) TYPE_CHECKINGAnyDictIterableListOptionalTupleType) deprecated)Document) Embeddings) VectorStoreClusterz0.2.4z1.0z(langchain_couchbase.CouchbaseVectorStore)sinceremovalalternative_importceZdZUdZdZded<dZded<dZded <d Zded <dDdZ dDdZ dDdZ eedddEdZ dFdGd,Z dHdId.ZedJd/ZdKd2Zd3ifdLd9Zd3ifdMd<Zd3ifdNd=Zd3ifdOd>ZedPdAZe dHdQdCZd S)RCouchbaseVectorStoreah`Couchbase Vector Store` vector store. To use it, you need - a recent installation of the `couchbase` library - a Couchbase database with a pre-defined Search index with support for vector fields Example: .. code-block:: python from langchain_community.vectorstores import CouchbaseVectorStore from langchain_openai import OpenAIEmbeddings from couchbase.cluster import Cluster from couchbase.auth import PasswordAuthenticator from couchbase.options import ClusterOptions from datetime import timedelta auth = PasswordAuthenticator(username, password) options = ClusterOptions(auth) connect_string = "couchbases://localhost" cluster = Cluster(connect_string, options) # Wait until the cluster is ready for use. cluster.wait_until_ready(timedelta(seconds=5)) embeddings = OpenAIEmbeddings() vectorstore = CouchbaseVectorStore( cluster=cluster, bucket_name="", scope_name="", collection_name="", embedding=embeddings, index_name="vector-index", ) vectorstore.add_texts(["hello", "world"]) results = vectorstore.similarity_search("ola", k=1) dintDEFAULT_BATCH_SIZEmetadatastr _metadata_keytext_default_text_key embedding_default_embedding_keyreturnboolc|j} ||jdS#t$rYdSwxYw)z:Check if the bucket exists in the linked Couchbase clusterTF)_clusterbuckets get_bucket _bucket_name Exception)selfbucket_managers f/var/www/html/ai-engine/env/lib/python3.11/site-packages/langchain_community/vectorstores/couchbase.py_check_bucket_existsz)CouchbaseVectorStore._check_bucket_existsDsX..00   % %d&7 8 8 84   55 s7 AAci}|jD];}g||j<|jD]'}||j|j(<|j|vrtd|jd|j|j ||jvr'td|j d|jd|jdS)zzCheck if the scope and collection exists in the linked Couchbase bucket Raises a ValueError if either is not foundzScope z not found in Couchbase bucket z Collection z not found in scope z in Couchbase bucket T) _bucket collectionsget_all_scopesnameappend _scope_namekeys ValueErrorr'_collection_name)r)scope_collection_mapscope collections r+"_check_scope_and_collection_existsz7CouchbaseVectorStore._check_scope_and_collection_existsMs@02\--//>>@@ I IE/1  ,$/ I I $UZ077 HHHH I  #7#<#<#>#> > >.)..+..   (:KNN  tcn|jrWd|jD}|j|vrt d|jdnVd|jD}|j|vrt d|jddS)zxCheck if the Search index exists in the linked Couchbase cluster Raises a ValueError if the index does not existcg|] }|j Sr1.0indexs r+ z.n'$ r;zIndex z; does not exist. Please create the index before searching.cg|] }|j Sr>r?r@s r+rCz.wrDr;T) _scoped_index_scopesearch_indexesget_all_indexes _index_namer5r$)r) all_indexess r+_check_index_existsz(CouchbaseVectorStore._check_index_existsjs    (, (B(B(D(D(T(T(V(VK{22 AT-AAA3 (, (D(D(F(F(V(V(X(XK{22 AT-AAA tr;T)text_key embedding_key scoped_indexclusterr bucket_name scope_namecollection_namer index_namerM Optional[str]rNrONonec ddlm} n"#t$r} td| d} ~ wwxYwt|| st dt |||_|st d|st d|st d|st d |st d ||_||_||_ ||_ ||_ ||_ ||_ | |_|st d |jd  |j|j|_|j|j|_|j|j |_n"#t,$r} t d | d} ~ wwxYw |n#t,$r} | d} ~ wwxYw |dS#t,$r} | d} ~ wwxYw)av Initialize the Couchbase Vector Store. Args: cluster (Cluster): couchbase cluster object with active connection. bucket_name (str): name of bucket to store documents in. scope_name (str): name of scope in the bucket to store documents in. collection_name (str): name of collection in the scope to store documents in embedding (Embeddings): embedding function to use. index_name (str): name of the Search index to use. text_key (optional[str]): key in document to use as text. Set to text by default. embedding_key (optional[str]): key in document to use for the embeddings. Set to embedding by default. scoped_index (optional[bool]): specify whether the index is a scoped index. Set to True by default. rrzfCould not import couchbase python package. Please install couchbase SDK with `pip install couchbase`.Nz8cluster should be an instance of couchbase.Cluster, got z%Embeddings instance must be provided.zbucket_name must be provided.zscope_name must be provided.z!collection_name must be provided.zindex_name must be provided.zBucket z< does not exist. Please create the bucket before searching.zKError connecting to couchbase. Please check the connection and credentials.)couchbase.clusterr ImportError isinstancer5typer$r'r3r6_embedding_function _text_key_embedding_keyrJrFr,bucketr.r8rGr9 _collectionr(r:rL) r)rPrQrRrSrrTrMrNrOres r+__init__zCouchbaseVectorStore.__init__s>  1 1 1 1 1 1 1   N   '7++ 'G}}''     FDEE E ><== = =;<< < B@AA A =;<< <'% /#, !+%)((** >$+>>>   =//0ABBDL,,,T-=>>DK#{55d6KLLD     ?     3 3 5 5 5 5   G    $ $ & & & & &   G sY (#(A,F F'F""F'+G G G  GG++ G<5G77G<Ntexts Iterable[str] metadatasOptional[List[Dict[str, Any]]]idsOptional[List[str]] batch_size Optional[int]kwargsr List[str]c 2ddlm}|sj}g}| d|D}| d|D}jt |}fdt ||||Dg} tdt| |D]} | | | |z} j | d} | j r-| | d e#|$r} td| d} ~ wwxYw|S)aKRun texts through the embeddings and persist in vectorstore. If the document IDs are passed, the existing documents (if any) will be overwritten with the new ones. Args: texts (Iterable[str]): Iterable of strings to add to the vectorstore. metadatas (Optional[List[Dict]]): Optional list of metadatas associated with the texts. ids (Optional[List[str]]): Optional list of ids associated with the texts. IDs have to be unique strings across the collection. If it is not specified uuids are generated and used as ids. batch_size (Optional[int]): Optional batch size for bulk insertions. Default is 100. Returns: List[str]:List of ids from adding the texts into the vectorstore. r)DocumentExistsExceptionNc>g|]}tjjSr>)uuiduuid4hexrA_s r+rCz2CouchbaseVectorStore.add_texts..s!3334:<<#333r;cg|]}iSr>r>rss r+rCz2CouchbaseVectorStore.add_texts.. s++++++r;c Ji|]\}}}}|j|j|j|i Sr>)r]r^r)rAidrvectorrr)s r+ z2CouchbaseVectorStore.add_texts..sO    /Bfh ND'&   r;zDocument already exists: )couchbase.exceptionsrnrr\embed_documentslistziprangelenr` upsert_multiall_okextendr4r5)r)rcrergrirkrndoc_idsembedded_textsdocuments_to_insertibatchresultras` r+ add_textszCouchbaseVectorStore.add_textss4 A@@@@@ 10J ;33U333C  ++U+++I1AA$u++NN     36 33     q#122J?? B BA'A N(:;E B)66uQx@@=4NN58==??333* B B B !@Q!@!@AAA Bs#AC88D=DDOptional[bool]c Xddlm}|td|d|j}d}t dt ||D]V}||||z} |j|}n!#|$r} d}td| d} ~ wwxYw||j z}W|S) aFDelete documents from the vector store by ids. Args: ids (List[str]): List of IDs of the documents to delete. batch_size (Optional[int]): Optional batch size for bulk deletions. Returns: bool: True if all the documents were deleted successfully, False otherwise. r)DocumentNotFoundExceptionNz#No document ids provided to delete.riTFzDocument not found: ) rzrr5getrr~rr` remove_multir) r)rgrkrrideletion_statusrrrras r+deletezCouchbaseVectorStore.delete's CBBBBB ;BCC CZZ d.EFF q#c((J// - -AA N*+E =)66u==, = = ="' !;!;!;<<< = v} ,OOs#A>>BBBc|jS)z"Return the query embedding object.)r\)r)s r+ embeddingszCouchbaseVectorStore.embeddingsGs ''r; row_fieldsDict[str, Any]ci}|D]M\}}||jr)||jdzd}|||<H|||<N|S)zHelper method to format the metadata from the Couchbase Search API. Args: row_fields (Dict[str, Any]): The fields to format. Returns: Dict[str, Any]: The formatted metadata. .)items startswithrsplit)r)rrkeyvaluenew_keys r+_format_metadataz%CouchbaseVectorStore._format_metadataLs|$**,, & &JC~~d011 &))D$6$<==bA$)!! % r; List[float]ksearch_optionsOptional[Dict[str, Any]]List[Tuple[Document, float]]c @ddlm}ddlm}ddlm}m}|ddg} | dgkr#|j| vr| |j|j | ||j ||} |jr.|j|j| ||| |} n.|j|j| ||| |} g} | D]k} | j|jd }|| j}| j}t/|| }| ||fln$#t0$r}t3d |d}~wwxYw| S) aReturn docs most similar to embedding vector with their scores. Args: embedding (List[float]): Embedding vector to look up documents similar to. k (int): Number of Documents to return. Defaults to 4. search_options (Optional[Dict[str, Any]]): Optional search options that are passed to Couchbase search. Defaults to empty dictionary. fields (Optional[List[str]]): Optional list of fields to include in the metadata of results. Note that these need to be stored in the index. If nothing is specified, defaults to all the fields stored in the index. Returns: List of (Document, score) that are the most similar to the query vector. rN) SearchOptions) VectorQuery VectorSearchfields*)limitrraw)rBrequestoptions) page_contentrzSearch failed with error: )couchbase.searchsearchcouchbase.optionsrcouchbase.vector_searchrrrr]r2 SearchRequestcreatefrom_vector_queryr^rFrGrJr$rowsrpoprscorer r(r5)r)rrrrkrrrrr search_req search_iterdocs_with_scorerowrrrdocras r+&similarity_search_with_score_by_vectorz;CouchbaseVectorStore.similarity_search_with_score_by_vector`s. *)))))333333EEEEEEEEHse,, cU??t~V;; MM$. ) ) ))00  * * '    ! ?! "k00$!M%* #m22*&)M&nUUU3 !O#'')) 5 5z~~dnb99 00<< D8DDD&&U|4444 5 ? ? ?=!==>> > ?sC%E:: FFFqueryList[Document]c n|j|}|j|||fi|}d|DS)aReturn documents most similar to embedding vector with their scores. Args: query (str): Query to look up for similar documents k (int): Number of Documents to return. Defaults to 4. search_options (Optional[Dict[str, Any]]): Optional search options that are passed to Couchbase search. Defaults to empty dictionary fields (Optional[List[str]]): Optional list of fields to include in the metadata of results. Note that these need to be stored in the index. If nothing is specified, defaults to all the fields stored in the index. Returns: List of Documents most similar to the query. cg|]\}}|Sr>r>rArrts r+rCz:CouchbaseVectorStore.similarity_search..s333Q333r;r embed_queryr)r)rrrrkquery_embeddingdocs_with_scoress r+similarity_searchz&CouchbaseVectorStore.similarity_searchsY./55e<<F4F Q  28  43"23333r;c Z|j|}|j|||fi|}|S)aReturn documents that are most similar to the query with their scores. Args: query (str): Query to look up for similar documents k (int): Number of Documents to return. Defaults to 4. search_options (Optional[Dict[str, Any]]): Optional search options that are passed to Couchbase search. Defaults to empty dictionary. fields (Optional[List[str]]): Optional list of fields to include in the metadata of results. Note that these need to be stored in the index. If nothing is specified, defaults to text and metadata fields. Returns: List of (Document, score) that are most similar to the query. r)r)rrrrkrrs r+similarity_search_with_scorez1CouchbaseVectorStore.similarity_search_with_scoresI./55e<<E$E Q  28  r;c :|j|||fi|}d|DS)aReturn documents that are most similar to the vector embedding. Args: embedding (List[float]): Embedding to look up documents similar to. k (int): Number of Documents to return. Defaults to 4. search_options (Optional[Dict[str, Any]]): Optional search options that are passed to Couchbase search. Defaults to empty dictionary. fields (Optional[List[str]]): Optional list of fields to include in the metadata of results. Note that these need to be stored in the index. If nothing is specified, defaults to document text and metadata fields. Returns: List of Documents most similar to the query. cg|]\}}|Sr>r>rs r+rCzDCouchbaseVectorStore.similarity_search_by_vector..s222Q222r;)r)r)rrrrkrs r+similarity_search_by_vectorz0CouchbaseVectorStore.similarity_search_by_vectorsC.F$E q.  ,2  32/2222r;clsType[CouchbaseVectorStore]c |dd}|dd}|dd}|dd}|dd}|d|j}|d|j} |d d } ||||||||| | S) a4Initialize the Couchbase vector store from keyword arguments for the vector store. Args: embedding: Embedding object to use to embed text. **kwargs: Keyword arguments to initialize the vector store with. Accepted arguments are: - cluster - bucket_name - scope_name - collection_name - index_name - text_key - embedding_key - scoped_index rPNrQrRrSrTrMrNrOT) rrPrQrRrSrTrMrNrO)rrr ) rrrkrPrQrRrSrTrMrNrOs r+ _from_kwargsz!CouchbaseVectorStore._from_kwargss.**Y--jj55 ZZ d33  **%6==ZZ d33 ::j#*?@@ ?C4NOO zz.$77 s#!+!'%    r;Optional[List[Dict[Any, Any]]]c |j|fi|}|d|j}|dd}||||||S)aConstruct a Couchbase vector store from a list of texts. Example: .. code-block:: python from langchain_community.vectorstores import CouchbaseVectorStore from langchain_openai import OpenAIEmbeddings from couchbase.cluster import Cluster from couchbase.auth import PasswordAuthenticator from couchbase.options import ClusterOptions from datetime import timedelta auth = PasswordAuthenticator(username, password) options = ClusterOptions(auth) connect_string = "couchbases://localhost" cluster = Cluster(connect_string, options) # Wait until the cluster is ready for use. cluster.wait_until_ready(timedelta(seconds=5)) embeddings = OpenAIEmbeddings() texts = ["hello", "world"] vectorstore = CouchbaseVectorStore.from_texts( texts, embedding=embeddings, cluster=cluster, bucket_name="", scope_name="", collection_name="", index_name="vector-index", ) Args: texts (List[str]): list of texts to add to the vector store. embedding (Embeddings): embedding function to use. metadatas (optional[List[Dict]): list of metadatas to add to documents. **kwargs: Keyword arguments used to initialize the vector store with and/or passed to `add_texts` method. Check the constructor and/or `add_texts` for the list of accepted arguments. Returns: A Couchbase vector store. rirgN)rergri)rrrr)rrcrrerk vector_storerirgs r+ from_textszCouchbaseVectorStore.from_texts1svn(s' <r;r+rrs! ''T"!!!!#M#########"-----:B#4'=!bbbbbbN59#'$( ?????B@(((X(.35 MMMMMd35 44444@35 @35 333338) ) ) [) V 59 ====[===r;r) __future__rrptypingrrrrrr r r langchain_core._api.deprecationr langchain_core.documentsr langchain_core.embeddingsrlangchain_core.vectorstoresrrXrrr>r;r+rs%"""""" RRRRRRRRRRRRRRRRRRRR666666------000000333333*))))))   A [ [ [ [ [ ;[ [   [ [ [ r;