dh7SrSSKJr SSKrSSKrSSKJrJrJrJ r J r J r SSK J r SSKJr SSKJr \(aSSKJr \R("5r"S S \5rg) z'Wrapper around Epsilla vector database.) annotationsN) TYPE_CHECKINGAnyIterableListOptionalTypeDocument) Embeddings) VectorStore)vectordbc\rSrSr%SrSrS\S'SrS\S'SrS\S '\\4SS jjr \ SS j5r SS jr SSS jjr SSSjjrSSSjjrSS SjjrS!S"Sjjr\SS\\\S4S#Sjj5r\S\\\S4S$Sjj5rSrg)%Epsillaa Wrapper around Epsilla vector database. As a prerequisite, you need to install ``pyepsilla`` package and have a running Epsilla vector database (for example, through our docker image) See the following documentation for how to run an Epsilla vector database: https://epsilla-inc.gitbook.io/epsilladb/quick-start Args: client (Any): Epsilla client to connect to. embeddings (Embeddings): Function used to embed the texts. db_path (Optional[str]): The path where the database will be persisted. Defaults to "/tmp/langchain-epsilla". db_name (Optional[str]): Give a name to the loaded database. Defaults to "langchain_store". Example: .. code-block:: python from langchain_community.vectorstores import Epsilla from pyepsilla import vectordb client = vectordb.Client() embeddings = OpenAIEmbeddings() db_path = "/tmp/vectorstore" db_name = "langchain_store" epsilla = Epsilla(client, embeddings, db_path, db_name) langchain_storestr_LANGCHAIN_DEFAULT_DB_NAMEz/tmp/langchain-epsilla_LANGCHAIN_DEFAULT_DB_PATHlangchain_collection_LANGCHAIN_DEFAULT_TABLE_NAMEcSSKn[XRRUR R R45(d[S[U535eXl X@l X l [RUlURR!XCS9 URR#US9 g![an[S5UeSnAff=f)z%Initialize with necessary components.rNziCould not import pyepsilla python package. Please install pyepsilla package with `pip install pyepsilla`.zbclient should be an instance of pyepsilla.vectordb.Client or pyepsilla.cloud.client.Vectordb, got )db_namedb_pathr) pyepsilla ImportError isinstancerClientcloudclientVectordb TypeErrortype_client_db_name _embeddingsrr_collection_nameload_dbuse_db)selfr! embeddingsrrres `/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/vectorstores/epsilla.py__init__Epsilla.__init__4s   ''.. 0F0F0O0OP  88 G,' Q  sB;; C CCcUR$N)r')r+s r.r,Epsilla.embeddingsSscXlg)z^ Set default collection to use. Args: collection_name (str): The name of the collection. N)r(r+collection_names r.use_collectionEpsilla.use_collectionWs !0r4c`U(d URnURRU5 g)z Clear data in a collection. Args: collection_name (Optional[str]): The name of the collection. If not provided, the default collection will be used. N)r(r% drop_tabler6s r. clear_dataEpsilla.clear_data`s$"33O 0r4NcU(d URnURRXS9up4US:wa8[R SUS35 [ SR US55eUS$)atGet the collection. Args: collection_name (Optional[str]): The name of the collection to retrieve data from. If not provided, the default collection will be used. response_fields (Optional[List[str]]): List of field names in the result. If not specified, all available fields will be responded. Returns: A list of the retrieved data. ) table_nameresponse_fieldszFailed to get records: message Error: {}.result)r(r%getloggererror Exceptionformat)r+r7r@ status_coderesponses r.rE Epsilla.getls{"33O $ 0 0&!1!   #  LL28I3F2GH IL//0CDE E!!r4cU(d [S5e[US5nSSS.SSS.SS US ./nUbUVs/sHofS PM nnUHnUR5HupX;aM [U [5(aSn OW[U [ 5(aSn O?[U [ 5(aS n O'[U [5(aS n O[SU S35eURXS.5 URU 5 M M URRXS9upU S:wa[U S:Xa[RSUS35 g[RSUSU S35 [SRU S55egs snf)NzEmbeddings list is empty.ridINT)namedataTypetextSTRINGr, VECTOR_FLOAT)rPrQ dimensionsrPFLOATBOOLzUnsupported data type for .) table_fieldsrAiz#Continuing with the existing table zFailed to create collection : rBrC) ValueErrorlenitemsrrintfloatboolappendr% create_tablerFinforGrHrI)r+r?r, metadatasdimfieldsfield field_namesmetadatakeyvalued_typerJrKs r._create_collectionEpsilla._create_collections89 9*Q- u - 2!~S Q   6<=fU=fK=%"*.."2JC) !%--!)#E3//!&#E511!(#E400!'(+EcU!)LMMMM3"CD&&s+#3&$!% 9 9 !:!   # c! A*QOP 2:,b)AT@UV 3 3HY4G HII ->s E?Fc U(d URnOX0lU(aURRUS9 [U5nURR U5n[U5S:Xa[RS5 /$URX6US9 UVs/sH!n[[R"55PM# n n/n [U 5HEupU XXkS.n Ub"X+R!5nUH unnUX'M U R#U 5 MG URR%X:S9unnUS:wa;[R'SUS US 35 [)S R+US 55eU V s/sHn [-U 5PM sn $![ a3 UVs/sHopRRU5PM Os snfnnGNmf=fs snfs sn f) aA Embed texts and add them to the database. Args: texts (Iterable[str]): The texts to embed. metadatas (Optional[List[dict]]): Metadata dicts attached to each of the texts. Defaults to None. collection_name (Optional[str]): Which collection to use. Defaults to "langchain_collection". If provided, default collection name will be set as well. drop_old (Optional[bool]): Whether to drop the previous collection and create a new one. Defaults to False. Returns: List of ids of the added texts. rrzNothing to insert, skipping.)r?r,rdrNrRr,)r?recordsrAzFailed to add records to rZrBrC)r(r%drop_dblistr'embed_documentsNotImplementedError embed_queryr\rFdebugrmhashuuiduuid4 enumerater]rainsertrGrHrIr)r+textsrdr7drop_oldkwargsr,x_idsrqindexrNrecordrirjrkrJrKs r. add_textsEpsilla.add_textss0"33O$3 !  LL  9U  J))99%@J z?a  LL7 8I &  ,115atDJJL!51"3IE (/F $$+113"*JC"'FK#+ NN6 "(!% 3 3&!4!  X #  LL+O+ST L//0CDE E"%&#BB#&&C# JCHI5a**66q95IJIJ J2,'s*F'G<GG!#GGGc Z^U(d URnURRU5nURR USUUS9upgUS:wa9[ R SUSS35 [SRUS55e/SQm[[U4S jUS 55$) a Return the documents that are semantically most relevant to the query. Args: query (str): String to query the vectorstore with. k (Optional[int]): Number of documents to return. Defaults to 4. collection_name (Optional[str]): Collection to use. Defaults to "langchain_store" or the one provided before. Returns: List of documents that are semantically most relevant to the query r,)r? query_field query_vectorlimitrAzSearch failed: rBrXrCrpc \>[USUVs0sHoT;dM XU_M snS9$s snf)NrR) page_contentrir )itemrj exclude_keyss r.+Epsilla.similarity_search..s:X!%f26263\:Q#Y$s) ) rD) r(r'rvr%queryrFrGrHrIrsmap) r+rkr7rrrJrKrs @r.similarity_searchEpsilla.similarity_searchs"33O''33E: $ 2 2&$% !3!  #  LL?8I+>*?qA BL//0CDE E3   "   r4c  H[XBXVS9n U R"U4UUUS.U D6 U $)aCreate an Epsilla vectorstore from raw documents. Args: texts (List[str]): List of text data to be inserted. embeddings (Embeddings): Embedding function. client (pyepsilla.vectordb.Client): Epsilla client to connect to. metadatas (Optional[List[dict]]): Metadata for each text. Defaults to None. db_path (Optional[str]): The path where the database will be persisted. Defaults to "/tmp/langchain-epsilla". db_name (Optional[str]): Give a name to the loaded database. Defaults to "langchain_store". collection_name (Optional[str]): Which collection to use. Defaults to "langchain_collection". If provided, default collection name will be set as well. drop_old (Optional[bool]): Whether to drop the previous collection and create a new one. Defaults to False. Returns: Epsilla: Epsilla vector store. )rr)rdr7r~)rr) clsr} embeddingrdr!rrr7r~rinstances r. from_textsEpsilla.from_textssAD6gO  +    r4c UV s/sHoRPM n n UV s/sHoRPM n n UR"U U4U UUUUUS.UD6$s sn fs sn f)aCreate an Epsilla vectorstore from a list of documents. Args: texts (List[str]): List of text data to be inserted. embeddings (Embeddings): Embedding function. client (pyepsilla.vectordb.Client): Epsilla client to connect to. metadatas (Optional[List[dict]]): Metadata for each text. Defaults to None. db_path (Optional[str]): The path where the database will be persisted. Defaults to "/tmp/langchain-epsilla". db_name (Optional[str]): Give a name to the loaded database. Defaults to "langchain_store". collection_name (Optional[str]): Which collection to use. Defaults to "langchain_collection". If provided, default collection name will be set as well. drop_old (Optional[bool]): Whether to drop the previous collection and create a new one. Defaults to False. Returns: Epsilla: Epsilla vector store. )rdr!rrr7r~)rrir) r documentsrr!rrr7r~rdocr}rds r.from_documentsEpsilla.from_documentsLsuB.77Yc!!Y7-67Yc\\Y 7~~     +    87s AA)r%r(r&r')r!rr,r r Optional[str]rr)returnzOptional[Embeddings])r7rrNone))rN)r7rr@zOptional[List[str]]rz List[dict]r2)r?rr,rsrdzOptional[list[dict]]rr)NrF) r}z Iterable[str]rdOptional[List[dict]]r7rr~Optional[bool]rrr List[str])r) rrrr^r7rrrrList[Document])r Type[Epsilla]r}rrr rdrr!rrrrrr7rr~rrrrr)rrrrrr r!rrrrrr7rr~rrrrr)__name__ __module__ __qualname____firstlineno____doc__r__annotations__rrr/propertyr,r8r<rErmrr classmethodrr__static_attributes__r4r.rrso8'87&>>)?!3? "  0 1QU""":M" "4TX*J*J+/*J@& &  & 7:& KN& & P +/!;!;)F#(* ***( *  *  **'*!** **X !;!;)F#(- - !- -  -  -  - '- !- -  - - r4r)r __future__rloggingrytypingrrrrrr langchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr rr getLoggerrFrrr4r.rsB-" EE-03"    g kg r4