j7dZddlmZddlZddlZddlmZmZmZm Z m Z m Z ddl m Z ddlmZddlmZerddlmZej(ZGd d eZy) z'Wrapper around Epsilla vector database.) annotationsN) TYPE_CHECKINGAnyIterableListOptionalTypeDocument) Embeddings) VectorStore)vectordbc~eZdZUdZdZded<dZded<dZded<eef dd Ze dd Z dd Z ddd Z d ddZ d ddZ d ddZ d d dZed d eeedf d!dZed eeedf d"dZy )#Epsillaar 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_NAMEc ddl}t||jj|j j jfstdt|||_ ||_ ||_ tj|_|jj!|||jj#|y#t$r}td|d}~wwxYw)z%Initialize with necessary components.rNziCould not import pyepsilla python package. Please install pyepsilla package with `pip install pyepsilla`.zbclient should be an instance of pyepsilla.vectordb.Client or pyepsilla.cloud.client.Vectordb, got )db_namedb_pathr) pyepsilla ImportError isinstancerClientcloudclientVectordb TypeErrortype_client_db_name _embeddingsrr_collection_nameload_dbuse_db)selfr embeddingsrrres r/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/vectorstores/epsilla.py__init__zEpsilla.__init__4s   Y''.. 0F0F0O0OP 88 G,' Q  sC C CCc|jSN)r&)r*s r-r+zEpsilla.embeddingsSsc||_y)z~ Set default collection to use. Args: collection_name (str): The name of the collection. N)r'r*collection_names r-use_collectionzEpsilla.use_collectionWs !0r1cV|s |j}|jj|y)z Clear data in a collection. Args: collection_name (Optional[str]): The name of the collection. If not provided, the default collection will be used. N)r'r$ drop_tabler3s r- clear_datazEpsilla.clear_data`s$"33O 0r1Nc|s |j}|jj||\}}|dk7r8tj d|dt dj |d|dS)aGet the collection. Args: collection_name (Optional[str]): The name of the collection to retrieve data from. If not provided, the default collection will be used. response_fields (Optional[List[str]]): List of field names in the result. If not specified, all available fields will be responded. Returns: A list of the retrieved data. ) table_nameresponse_fieldszFailed to get records: message Error: {}.result)r'r$getloggererror Exceptionformat)r*r4r; status_coderesponses r-r@z Epsilla.getls"33O $ 0 0&!1!  X #  LL28I3F2GH IL//0CDE E!!r1c|s tdt|d}dddddddd |d g}||Dcgc]}|d  }}|D]}|jD]\} } | |vr t| trd} nHt| t rd} n5t| t rd } n"t| trd } ntd| d|j| | d|j| |jj||\} } | dk7rZ| dk(rtjd|dytjd|d| dtdj| dycc}w)NzEmbeddings list is empty.ridINT)namedataTypetextSTRINGr+ VECTOR_FLOAT)rJrK dimensionsrJFLOATBOOLzUnsupported data type for .) table_fieldsr<iz#Continuing with the existing table zFailed to create collection : r=r>) ValueErrorlenitemsrrintfloatboolappendr$ create_tablerAinforBrCrD)r*r:r+ metadatasdimfieldsfield field_namesmetadatakeyvalued_typerErFs r-_create_collectionzEpsilla._create_collections89 9*Q- u - 2!~S Q   6<=fU5=fK=%"*.."2JCk) !%-!)#E3/!&#E51!(#E40!'(+EcU!)LMMMM3F"CD&&s+#3&$!% 9 9 V!:!  X # c! A*QOP 2:,b)AT@UV 3 3HY4G HII ->s E#Fc |s |j}n||_|r|jj|t|} |jj |}t|dk(rtjdgS|j||||Dcgc]}ttj!} }g} t| D]F\} } | || || d} |"|| j!}|D] \}}|| |< | j#| H|jj%|| \}}|dk7r;tj'd|d |d t)d j+|d | D cgc] } t-| c} S#t $r2|Dcgc]}|jj|ncc}w}}YlwxYwcc}wcc} w) a Embed texts and add them to the database. Args: texts (Iterable[str]): The texts to embed. metadatas (Optional[List[dict]]): Metadata dicts attached to each of the texts. Defaults to None. collection_name (Optional[str]): Which collection to use. Defaults to "langchain_collection". If provided, default collection name will be set as well. drop_old (Optional[bool]): Whether to drop the previous collection and create a new one. Defaults to False. Returns: List of ids of the added texts. rrzNothing to insert, skipping.)r:r+r^rHrLr+)r:recordsr<zFailed to add records to rTr=r>)r'r$drop_dblistr&embed_documentsNotImplementedError embed_queryrVrAdebugrghashuuiduuid4 enumeraterWr[insertrBrCrDr)r*textsr^r4drop_oldkwargsr+x_idsrjindexrHrecordrcrdrerErFs r- add_textszEpsilla.add_textss0"33O$3D !  LL  9U  J))99%@J z?a  LL7 8I &:  ,115atDJJL!51"3IE2e (/F $$U+113"*JC"'F3K#+ NN6 "(!% 3 3&!4!  X #  LL+O+ST L//0CDE E"%&#BB#&&C# JCHI5a$**66q95IJI J2,'s*F$G 9G G "F>=G G c T|s |j}|jj|}|jj |d||\}}|dk7r9t j d|ddtdj|dgdttfd |d S) 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_vectorlimitr<zSearch failed: r=rRr>ric \t|d|Dcic] }|vs|||c}Scc}w)NrL) page_contentrcr )itemrd exclude_keyss r-z+Epsilla.similarity_search..s<X!%f26263#\:QT#Y$s ) ) r?) r'r&ror$queryrArBrCrDrlmap) r*rkr4rxrrErFrs @r-similarity_searchzEpsilla.similarity_searchs"33O''33E: $ 2 2&$% !3!  X #  LL?8I+>*?qA BL//0CDE E3   "   r1c  Rt||||} | j|f|||d| | S)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)r^r4rw)rr~) clsrv embeddingr^r rrr4rwrxinstances r- from_textszEpsilla.from_textssGD69gwO  +    r1c |D cgc]} | j} } |D cgc]} | j} } |j| |f| |||||d|Scc} wcc} w)a"Create 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. )r^r rrr4rw)rrcr) r documentsrr rrr4rwrxdocrvr^s r-from_documentszEpsilla.from_documentsLs{B.77Yc!!Y7-67YcS\\Y 7s~~     +    87s AA)r rr+r r Optional[str]rr)returnzOptional[Embeddings])r4rrNone))rN)r4rr;zOptional[List[str]]rz List[dict]r0)r:rr+rlr^zOptional[list[dict]]rr)NrF) rvz Iterable[str]r^Optional[List[dict]]r4rrwOptional[bool]rxrr List[str])r) rrrrXr4rrxrrList[Document])r Type[Epsilla]rvrrr r^rr rrrrrr4rrwrrxrrr)rrrrrr r rrrrrr4rrwrrxrrr)__name__ __module__ __qualname____doc__r__annotations__rrr.propertyr+r5r8r@rgr~r classmethodrrr1r-rrso8'87&>>)?!3? "  0 1QU""":M" "4TX*J*J+/*J@& &  & 7:& KN& & P +/!;!;)F#(* ***( *  *  **'*!** **X !;!;)F#(- - !- -  -  -  - '- !- -  - - r1r)r __future__rloggingrrtypingrrrrrr langchain_core.documentsr langchain_core.embeddingsr langchain_core.vectorstoresr rr getLoggerrArrr1r-rsD-" EE-03"    g kg r1