jRddlmZddlZddlZddlmZmZmZmZm Z m Z m Z m Z m Z ddlZddlmZddlmZddlmZddlmZerddlZej2ZdZGd d eZy) ) annotationsN) TYPE_CHECKINGAnyDictIterableListOptionalSetTupleType)Document) Embeddings) VectorStore)maximal_marginal_relevanceceZdZUdZdZded<edddf ddZeddZ d ddZ dd Z e ddf dd Z e ddf dd Z d d!d Zde dddf d"d Z d# d$dZ d# d%dZ d& d'dZ d( d)dZ d( d*dZ ddZ ddZ d+dZ d,dZeddeddf d-dZededdf d.dZy)/AwaDBz`AwaDB` vector store.langchain_awadbstr_DEFAULT_TABLE_NAMENc  ddl}|||_n0||j||_n|j|_||jk(r7|dz }|t t jjddz }|jj|i|_ |||j|<||_ y#t$r tdwxYw)a@Initialize with AwaDB client. If table_name is not specified, a random table name of `_DEFAULT_TABLE_NAME + last segment of uuid` would be created automatically. Args: table_name: Name of the table created, default _DEFAULT_TABLE_NAME. embedding: Optional Embeddings initially set. log_and_data_dir: Optional the root directory of log and data. client: Optional AwaDB client. kwargs: Any possible extend parameters in the future. Returns: None. rNzRCould not import awadb python package. Please install it with `pip install awadb`._-) awadb ImportError awadb_clientClientrruuiduuid4splitCreatetable2embeddingsusing_table_name)self table_name embeddinglog_and_data_dirclientkwargsrs p/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/vectorstores/awadb.py__init__zAwaDB.__init__s.     &D +$0ELL1A$B!$0ELLN! 11 1 # J #djjl+11#6r: :J   ,79  09D ! !* - *- >  s CCcf|j|jvr|j|jSyN)r$r#)r%s r+ embeddingszAwaDB.embeddingsKs0  D$9$9 9(()>)>? ?c |j tdd}|j|jvr1|j|jj t |}|jj dd||||S)aRun more texts through the embeddings and add to the vectorstore. Args: texts: Iterable of strings to add to the vectorstore. metadatas: Optional list of metadatas associated with the texts. is_duplicate_texts: Optional whether to duplicate texts. Defaults to True. kwargs: any possible extend parameters in the future. Returns: List of ids from adding the texts into the vectorstore. NAwaDB client is None!!!embedding_texttext_embedding)r ValueErrorr$r#embed_documentslistAddTexts)r%texts metadatasis_duplicate_textsr*r/s r+ add_textszAwaDB.add_textsQs"    $67 7  D$9$9 9..t/D/DEUUU J  ))         r0c f|j td|jj|S)zLoad the local specified table. Args: table_name: Table name kwargs: Any possible extend parameters in the future. Returns: Success or failure of loading the local specified table r2)rr5Load)r%r&r*s r+ load_localzAwaDB.load_localts3    $67 7  %%j11r0c "|j tdd}|j|jvr)|j|jj |}nddlm}|j|}hd}|j|||||S)a8Return docs most similar to query. Args: query: Text query. k: The maximum number of documents to return. text_in_page_content: Filter by the text in page_content of Document. meta_filter (Optional[dict]): Filter by metadata. Defaults to None. E.g. `{"color" : "red", "price": 4.20}`. Optional. E.g. `{"max_price" : 15.66, "min_price": 4.20}` `price` is the metadata field, means range filter(4.20<'price'<15.66). E.g. `{"maxe_price" : 15.66, "mine_price": 4.20}` `price` is the metadata field, means range filter(4.20<='price'<=15.66). kwargs: Any possible extend parameters in the future. Returns: Returns the k most similar documents to the specified text query. Nr2r AwaEmbedding>_idscorer4text_in_page_content meta_filternot_include_fields_in_metadata) rr5r$r# embed_queryrrB Embeddingsimilarity_search_by_vector) r%querykrFrGr*r'rBnot_include_fieldss r+similarity_searchzAwaDB.similarity_searchs4    $67 7  D$9$9 9--d.C.CDPPQVWI *$007I'I//  !5#+= 0  r0c |j tdd}|j|jvr)|j|jj |}nddlm}|j|}g}ddh} |j||||| } | D]3} | jd} | jd=| | f} |j| 5|S) aThe most k similar documents and scores of the specified query. Args: query: Text query. k: The k most similar documents to the text query. text_in_page_content: Filter by the text in page_content of Document. meta_filter: Filter by metadata. Defaults to None. kwargs: Any possible extend parameters in the future. Returns: The k most similar documents to the specified text query. 0 is dissimilar, 1 is the most similar. Nr2rrAr4rCrErD) rr5r$r#rIrrBrJrKmetadataappend)r%rLrMrFrGr*r'rBresultsrNretrieval_docsdocrD doc_tuples r+similarity_search_with_scorez"AwaDB.similarity_search_with_scores,    $67 7  D$9$9 9--d.C.CDPPQVWI *$007I02(8%'@99  !5#+= : "CLL)E W%e I NN9 % " r0c *|j||fi|Sr.)rW)r%rLrMr*s r+(_similarity_search_with_relevance_scoresz.AwaDB._similarity_search_with_relevance_scoress 1t00DVDDr0c F|j tdg}||S|jj|||||}|jdk(r|S|ddD]C} d} i} | D]} | dk(r| | } || |vr| | | | <|j t | | E|S)a Return docs most similar to embedding vector. Args: embedding: Embedding to look up documents similar to. k: Number of Documents to return. Defaults to 4. text_in_page_content: Filter by the text in page_content of Document. meta_filter: Filter by metadata. Defaults to None. not_incude_fields_in_metadata: Not include meta fields of each document. Returns: List of Documents which are the most similar to the query vector. r2)rFrGrNr ResultItemsr3 page_contentrQ)rr5Search__len__rRr ) r%r'rMrFrGrHr*rS show_results item_detailcontent meta_dataitem_keys r+rKz!AwaDB.similarity_search_by_vectors,    $67 7"$  N((//  !5#= 0     !Q &N'?=9KGI'//)(3G3?#AA &1(&; (#( NN89M N:r0c J|j tdg}|j|jvr)|j|jj |}nddlm} | j|}|jdk(rgS|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. text_in_page_content: Filter by the text in page_content of Document. meta_filter (Optional[dict]): Filter by metadata. Defaults to None. Returns: List of Documents selected by maximal marginal relevance. r2rrA) lambda_multrFrG) rr5r$r#rIrrBrJr`'max_marginal_relevance_search_by_vector) r%rLrMfetch_krgrFrGr*r'rBrSs r+max_marginal_relevance_searchz#AwaDB.max_marginal_relevance_search)s:    $67 7!#  D$9$9 9--d.C.CDPPQVWI *$007I    ! #I>>  #!5# ? r0c |j tdg}||Sddh} |j||||| } g} | D] } | j| jd"t t j|t j| } | D]8}d| |jvs| |jd=|j| |:|S)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. text_in_page_content: Filter by the text in page_content of Document. meta_filter (Optional[dict]): Filter by metadata. Defaults to None. Returns: List of Documents selected by maximal marginal relevance. r2rCrDrEr4)dtype)embedding_list) rr5rKrRrQrnparrayfloat32)r%r'rMrirgrFrGr*rSrNretrieved_docstop_embeddingsrU selected_docss_ids r+rhz-AwaDB.max_marginal_relevance_search_by_vector^s<    $67 7"$  N#('"299  !5#+= : !C  ! !#,,/?"@ A"3 HHYbjj 1. "D>$#7#@#@@"4(112BC~d34"r0c |j td|jj|||||}i}|D]@} d} i} | D] } | dk(r| | } | dk(s| dk(r| | | | <"t| | } | || d<B|S)aReturn docs according ids. Args: ids: The ids of the embedding vectors. text_in_page_content: Filter by the text in page_content of Document. meta_filter: Filter by any metadata of the document. not_include_fields: Not pack the specified fields of each document. limit: The number of documents to return. Defaults to 5. Optional. Returns: Documents which satisfy the input conditions. r2)idsrFrGrNlimitr\r3r4rCr])rr5Getr )r%rvrFrGrNrwr* docs_detailrS doc_detailrc meta_infofieldrUs r+getz AwaDB.gets,    $67 7''++!5#1 , (*%JGI#,,(/G..%5.#-e#4 % $)DC),GJu% &&r0c |j tdd}||jdk(r|S|jj|}|S)aJDelete the documents which have the specified ids. Args: ids: The ids of the embedding vectors. **kwargs: Other keyword arguments that subclasses might use. Returns: Optional[bool]: True if deletion is successful. False otherwise, None if not implemented. Nr2r)rr5r`Delete)r%rvr*rets r+deletez AwaDB.deletesS    $67 7" ;#++-1,J&&s+ r0c n|j td|jj|d||S)a@Update the documents which have the specified ids. Args: ids: The id list of the updating embedding vector. texts: The texts of the updating documents. metadatas: The metadatas of the updating documents. Returns: the ids of the updated documents. r2r3)rvtext_field_namer9r:)rr5 UpdateTexts)r%rvr9r:r*s r+updatez AwaDB.updatesD"    $67 7  ,,%5Ui-  r0c h|jy|jj|}|r||_|S)zCreate a new table.F)rr"r$r%r&r*rs r+ create_tablezAwaDB.create_tables9    $&&z2 $.D ! r0c h|jy|jj|}|r||_|S)zJUse the specified table. Don't know the tables, please invoke list_tables.F)rUser$rs r+usez AwaDB.use s9    $##J/ $.D ! r0c R|jgS|jjS)z*List all the tables created by the client.)r ListAllTablesr%r*s r+ list_tableszAwaDB.list_tabless*    $I  ..00r0c |jS)zGet the current table.)r$rs r+get_current_tablezAwaDB.get_current_table(s $$$r0c D|||||}|j|||S)a3Create an AwaDB vectorstore from a raw documents. Args: texts (List[str]): List of texts to add to the table. embedding (Optional[Embeddings]): Embedding function. Defaults to None. metadatas (Optional[List[dict]]): List of metadatas. Defaults to None. table_name (str): Name of the table to create. log_and_data_dir (Optional[str]): Directory of logging and persistence. client (Optional[awadb.Client]): AwaDB client Returns: AwaDB: AwaDB vectorstore. )r&r'r(r))r9r:)r<) clsr9r'r:r&r(r)r*rs r+ from_textszAwaDB.from_texts0s50!-  Ui@r0c |Dcgc]}|j}}|Dcgc]}|j} }|j||| |||Scc}wcc}w)avCreate an AwaDB vectorstore from a list of documents. If a log_and_data_dir specified, the table will be persisted there. Args: documents (List[Document]): List of documents to add to the vectorstore. embedding (Optional[Embeddings]): Embedding function. Defaults to None. table_name (str): Name of the table to create. log_and_data_dir (Optional[str]): Directory to persist the table. client (Optional[awadb.Client]): AwaDB client. Any: Any possible parameters in the future Returns: AwaDB: AwaDB vectorstore. )r9r'r:r&r(r))r^rQr) r documentsr'r&r(r)r*rUr9r:s r+from_documentszAwaDB.from_documentsQsf2.77Yc!!Y7-67YcS\\Y 7~~!-   87s A A) r&rr'Optional[Embeddings]r( Optional[str]r)Optional[awadb.Client]r*rreturnNone)rr)NN) r9 Iterable[str]r:Optional[List[dict]]r;Optional[bool]r*rr List[str])r&rr*rrbool) rLrrMintrFrrGOptional[dict]r*rrList[Document]) rLrrMrrFrrGrr*rrList[Tuple[Document, float]])r)rLrrMrr*rrr)r'zOptional[List[float]]rMrrFrrGrrHOptional[Set[str]]r*rrr)rg?NN)rLrrMrrirrgfloatrFrrGrr*rrr)r'z List[float]rMrrirrgrrFrrGrr*rrr)NNNNN)rvOptional[List[str]]rFrrGrrNrrwz Optional[int]r*rrzDict[str, Document]r.)rvrr*rrr) rvrr9rr:rr*rrr)r*rrr)r*rrr)r Type[AwaDB]r9rr'rr:rr&rr(rr)rr*rrr)rrrrr'rr&rr(rr)rr*rrr)__name__ __module__ __qualname____doc__r__annotations__r,propertyr/r<r? DEFAULT_TOPNrOrWrYrKrjrhr}rrrrrr classmethodrrr0r+rrs00.*.*.)- /+/+(/+( /+ ' /+  /+ /+b+/-1 ! ! (! + !  !  ! F222  2..2&* , ,  , , , $ ,  ,  , b.2&* 22 2, 2 $ 2  2 &2nEE E E & E,0.2&*=A 5(5 5, 5 $ 5 ); 55 5t .2&*33 3 3  3 , 3$33 3p .2&*<< < <  < , <$<< <@$(.2&*15# 0 0,0$ 0 / 0  00 0h$(   6+/    (      0      1 1  1%% %+/*.-*.)- ((    ( ' @+/-*.)- ! ! !! (!  ! ( ! ' ! !  ! ! r0r) __future__rloggingrtypingrrrrrr r r r numpyrnlangchain_core.documentsr langchain_core.embeddingsrlangchain_core.vectorstoresr&langchain_community.vectorstores.utilsrr getLoggerloggerrrrr0r+rsO" WWW-03M     ^  K^  r0