a bgZ@sddlmZddlZddlZddlmZmZddlmZm Z m Z m Z m Z m Z mZddlmZddlmZddlmZerddlmZddlmZeZeGd d d ZGd d d eZdS) ) annotationsN)asdict dataclass) TYPE_CHECKINGAnyDictIterableListOptionalTupleDocument) Embeddings) VectorStore)DocumentCollectionc@s:eZdZUdZded<ded<ded<ded <d ed <d S) CollectionConfigaConfiguration for a `Zep Collection`. If the collection does not exist, it will be created. Attributes: name (str): The name of the collection. description (Optional[str]): An optional description of the collection. metadata (Optional[Dict[str, Any]]): Optional metadata for the collection. embedding_dimensions (int): The number of dimensions for the embeddings in the collection. This should match the Zep server configuration if auto-embed is true. is_auto_embedded (bool): A flag indicating whether the collection is automatically embedded by Zep. strname Optional[str] descriptionOptional[Dict[str, Any]]metadataintembedding_dimensionsboolis_auto_embeddedN)__name__ __module__ __qualname____doc____annotations__r!r!r/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_community/vectorstores/zep.pyrs rc s2eZdZdZddddddddddd fd d Zedd d dZdd ddZdd ddZdTdddddddZ dUdddddddd Z dVddddddd!d"Z dWddd$d%dd&d'd(d)Z dXddd$d%dd&d'd*d+Z dYdd%d$dd&d-d.d/ZdZdd%d$dd0d-d1d2Zd[dd%d$dd0d-d3d4Zd\dd%d$dd0d-d5d6Zd]dd%d$dd&d-d7d8Zd^d9d%d$dd&d:d;d<Zd_d9d%d$dd&d:d=d>Zd`dd%d%dAd$dd&dBdCdDZdadd%d%dAd$dd&dBdEdFZdbd9d%d%dAd$dd&dGdHdIZdcd9d%d%dAd$dd&dGdJdKZedddddMdddddddN dOdPZdeddddQdRdSZZS)fZepVectorStorea`Zep` vector store. It provides methods for adding texts or documents to the store, searching for similar documents, and deleting documents. Search scores are calculated using cosine similarity normalized to [0, 1]. Args: api_url (str): The URL of the Zep API. collection_name (str): The name of the collection in the Zep store. api_key (Optional[str]): The API key for the Zep API. config (Optional[CollectionConfig]): The configuration for the collection. Required if the collection does not already exist. embedding (Optional[Embeddings]): Optional embedding function to use to embed the texts. Required if the collection is not auto-embedded. Napi_keyconfig embeddingrrzOptional[CollectionConfig]zOptional[Embeddings]None)collection_nameapi_urlr%r&r'returncst|stdzddlm}Wnty@tdYn0|||d|_||_|rn|j|jkrn|j|_||_ | |_ ||_ dS)Nzs$    zZepVectorStore.__init__)r+cCs|jS)z/Access the query embedding object if available.)r6)r7r!r!r" embeddingsaszZepVectorStore.embeddingsrcCsTddlm}z|jj|j}Wn.|yNtd|jd|}Yn0|S)z; Load the collection from the Zep backend. r) NotFoundErrorz Collection z$ not found. Creating new collection.) r0r;r2documentZget_collectionr)loggerinfo_create_collection)r7r; collectionr!r!r"r4fs   zZepVectorStore._load_collectioncCs,|jstd|jjjfit|j}|S)z= Create a new collection in the Zep backend. zCCollection config must be specified when creating a new collection.)r3r/r2r<Zadd_collectionr)r7r@r!r!r"r?vs z!ZepVectorStore._create_collectionz Iterable[str]zOptional[List[Dict[Any, Any]]]zOptional[List[str]]zList[ZepDocument])texts metadatas document_idsr+c Csddlm}d}|jr8|jjr8|jdurtjdddnV|jdur|jt|}|jr|jj t |dkrt d|jj dt |dng}t |D]B\}}| |||r||nd|r||nd|r||nddq|S) Nrr z{The collection is set to auto-embed and an embedding function is present. Ignoring the embedding function.) stacklevelzkThe embedding dimensions of the collection and the embedding function do not match. Collection dimensions: z, Embedding dimensions: )contentrZ document_idr')zep_python.documentr r5rr6warningswarnZembed_documentslistrlenr/ enumerateappend) r7rArBrC ZepDocumentr: documentsidr!r!r"_generate_documents_to_adds>     z)ZepVectorStore._generate_documents_to_addzOptional[List[Dict[str, Any]]]rz List[str])rArBrCkwargsr+cKs,|jstd||||}|j|}|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. document_ids: Optional list of document ids associated with the texts. kwargs: vectorstore specific parameters Returns: List of ids from adding the texts into the vectorstore. Return docs most similar to query using specified search type. similarityr[rmmrsearch_type of ? not allowed. Expected search_type to be 'similarity' or 'mmr'.N)similarity_searchmax_marginal_relevance_searchr/r7rYrZrr[rSr!r!r"searchs  zZepVectorStore.searchcs`|dkr&|j|f||d|IdHS|dkrL|j|f||d|IdHStd|ddS)r\r]r^Nr_r`ra)asimilarity_searchamax_marginal_relevance_searchr/rdr!r!r"asearchs&    zZepVectorStore.asearch)rYr[rrSr+cKs&|j|f||d|}dd|DS)"Return docs most similar to query.r^cSsg|] \}}|qSr!r!.0doc_r!r!r" z4ZepVectorStore.similarity_search..(_similarity_search_with_relevance_scoresr7rYr[rrSresultsr!r!r"rbs z ZepVectorStore.similarity_searchzList[Tuple[Document, float]]cKs|j|f||d|S)z$Run similarity search with distance.r^rq)r7rYr[rrSr!r!r"similarity_search_with_scores z+ZepVectorStore.similarity_search_with_scorecKsl|jstd|jjsD|jrD|j|}|jjf|||d|}n|jj|f||d|}dd|DS)a Default similarity search with relevance scores. Modify if necessary in subclass. Return docs and relevance scores in the range [0, 1]. 0 is dissimilar, 1 is most similar. Args: query: input text k: Number of Documents to return. Defaults to 4. metadata: Optional, metadata filter **kwargs: kwargs to be passed to similarity search. Should include: score_threshold: Optional, a floating point value between 0 to 1 and filter the resulting set of retrieved docs Returns: List of Tuples of (doc, similarity_score) rTr'limitrrwrcSs&g|]}t|j|jd|jpdfqSZ page_contentrgr rFrZscorerlrmr!r!r"roKszKZepVectorStore._similarity_search_with_relevance_scores..)r5r/rr6 embed_queryrer7rYr[rrS query_vectorrtr!r!r"rr"s* z7ZepVectorStore._similarity_search_with_relevance_scorescsx|jstd|jjsJ|jrJ|j|}|jjf|||d|IdH}n |jj|f||d|IdH}dd|DS)rjrTrvNrxcSs&g|]}t|j|jd|jpdfqSryr{r|r!r!r"ronszKZepVectorStore.asimilarity_search_with_relevance_scores..)r5r/rr6r}rhr~r!r!r"(asimilarity_search_with_relevance_scoresVs*   z7ZepVectorStore.asimilarity_search_with_relevance_scorescs,|j||fd|i|IdH}dd|DS)rjrNcSsg|] \}}|qSr!r!rkr!r!r"rorpz5ZepVectorStore.asimilarity_search..)rrsr!r!r"rfys  z!ZepVectorStore.asimilarity_searchz List[float])r'r[rrSr+cKs6|jstd|jjf|||d|}dd|DS)aFReturn 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: Optional, metadata filter Returns: List of Documents most similar to the query vector. rTrvcSsg|]}t|j|jdqSrzr rFrr|r!r!r"ros z>ZepVectorStore.similarity_search_by_vector..r5r/rer7r'r[rrSrtr!r!r"similarity_search_by_vectorsz*ZepVectorStore.similarity_search_by_vectorcs6|jstd|jjf|||d|}dd|DS)z-Return docs most similar to embedding vector.rTrvcSsg|]}t|j|jdqSrrr|r!r!r"ros z?ZepVectorStore.asimilarity_search_by_vector..rrr!r!r"asimilarity_search_by_vectorsz+ZepVectorStore.asimilarity_search_by_vector?float)rYr[fetch_k lambda_multrrSr+c Ksx|jstd|jjsH|jrH|j|}|jjf|||d|d|}n"|jj|f||d|d|\}}dd|DS)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. Zep determines this automatically and this parameter is ignored. 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: Optional, metadata to filter the resulting set of retrieved docs Returns: List of Documents selected by maximal marginal relevance. rTr_r'rwrrZ mmr_lambdarwrrZrcSsg|]}t|j|jdqSrrrlrQr!r!r"rorpz@ZepVectorStore.max_marginal_relevance_search..)r5r/rr6r}reZsearch_return_query_vector r7rYr[rrrrSrrtr!r!r"rcs4   z,ZepVectorStore.max_marginal_relevance_searchc s|jstd|jjsN|jrN|j|}|jjf|||d|d|IdH}n(|jj|f||d|d|IdH\}}dd|DS):Return docs selected using the maximal marginal relevance.rTr_rNrcSsg|]}t|j|jdqSrrrr!r!r"rorpzAZepVectorStore.amax_marginal_relevance_search..)r5r/rr6r}rhZasearch_return_query_vectorrr!r!r"rgs4    z-ZepVectorStore.amax_marginal_relevance_search)r'r[rrrrSr+cKs:|jstd|jjf|||d|d|}dd|DS)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. Zep determines this automatically and this parameter is ignored. 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: Optional, metadata to filter the resulting set of retrieved docs Returns: List of Documents selected by maximal marginal relevance. rTr_rcSsg|]}t|j|jdqSrrrr!r!r"roKrpzJZepVectorStore.max_marginal_relevance_search_by_vector..rr7r'r[rrrrSrtr!r!r"'max_marginal_relevance_search_by_vector!s z6ZepVectorStore.max_marginal_relevance_search_by_vectorcs@|jstd|jjf|||d|d|IdH}dd|DS)rrTr_rNcSsg|]}t|j|jdqSrrrr!r!r"roerpzKZepVectorStore.amax_marginal_relevance_search_by_vector..)r5r/rhrr!r!r"(amax_marginal_relevance_search_by_vectorMs  z7ZepVectorStore.amax_marginal_relevance_search_by_vectorzOptional[List[dict]]) rAr'rBr)r*r%r&rSr+c Ks"||||||d} | ||| S)a Class method that returns a ZepVectorStore instance initialized from texts. If the collection does not exist, it will be created. Args: texts (List[str]): The list of texts to add to the vectorstore. embedding (Optional[Embeddings]): Optional embedding function to use to embed the texts. metadatas (Optional[List[Dict[str, Any]]]): Optional list of metadata associated with the texts. collection_name (str): The name of the collection in the Zep store. api_url (str): The URL of the Zep API. api_key (Optional[str]): The API key for the Zep API. config (Optional[CollectionConfig]): The configuration for the collection. kwargs: Additional parameters specific to the vectorstore. Returns: ZepVectorStore: An instance of ZepVectorStore. r$)rV) clsrAr'rBr)r*r%r&rSZvecstorer!r!r" from_textsgs  zZepVectorStore.from_texts)idsrSr+cKsH|dust|dkrtd|jdur.td|D]}|j|q2dS)zDelete by Zep vector UUIDs. Parameters ---------- ids : Optional[List[str]] The UUIDs of the vectors to delete. Raises ------ ValueError If no UUIDs are provided. NrzNo uuids provided to delete.zNo collection name provided.)rKr/r5Zdelete_document)r7rrSur!r!r"deletes  zZepVectorStore.delete)NN)NN)NN)NrX)NrX)riN)riN)riN)riN)riN)riN)riN)rirrN)rirrN)rirrN)rirrN)NNrrNN)N)rrrrr.propertyr:r4r?rRrVrWrerhrbrurrrrfrrrcrgrr classmethodrr __classcell__r!r!r8r"r#,s #-7&%;)/")r#) __future__rloggingrH dataclassesrrtypingrrrrr r r Zlangchain_core.documentsr Zlangchain_core.embeddingsrZlangchain_core.vectorstoresrrGrNr getLoggerr=rr#r!r!r!r"s $