o Zhm#@sddlmZddlZddlZddlmZmZmZmZm Z ddl m Z ddl m Z ddlmZddlmZeeZGdd d eZdS) ) annotationsN)AnyIterableListOptionalTuple)Document) Embeddings) VectorStore)DistanceStrategyc@seZdZdZejfd=dd Zed>d d Zd?ddZ d@ddZ dAdBdd Z   !dCdDd'd(Z !dEdFd+d,Z d-gfdGd3d4Zd-gd5dHd6d7Zd-gfdId8d9Ze dAdJd;d<ZdS)KKDBAIaT`KDB.AI` vector store. See https://kdb.ai. To use, you should have the `kdbai_client` python package installed. Args: table: kdbai_client.Table object to use as storage, embedding: Any embedding function implementing `langchain.embeddings.base.Embeddings` interface, distance_strategy: One option from DistanceStrategy.EUCLIDEAN_DISTANCE, DistanceStrategy.DOT_PRODUCT or DistanceStrategy.COSINE. See the example [notebook](https://github.com/KxSystems/langchain/blob/KDB.AI/docs/docs/integrations/vectorstores/kdbai.ipynb). tabler embeddingr distance_strategyOptional[DistanceStrategy]cCs:zddl}Wn tytdw||_||_||_dS)Nrz`Could not import kdbai_client python package. Please install it with `pip install kdbai_client`.) kdbai_client ImportError_table _embeddingr)selfr rrrr]/var/www/html/lang_env/lib/python3.10/site-packages/langchain_community/vectorstores/kdbai.py__init__!s   zKDBAI.__init__returnOptional[Embeddings]cCst|jtr |jSdSN) isinstancerr rrrr embeddings4s zKDBAI.embeddingstexts Iterable[str]List[List[float]]cs.tjtrjt|Sfdd|DS)Ncsg|]}|qSr)r.0trrr =z*KDBAI._embed_documents..)rrr embed_documentslist)rrrrr_embed_documents:s zKDBAI._embed_documentstextstr List[float]cCs"t|jtr |j|S||Sr)rrr Z embed_query)rr*rrr _embed_query?s   zKDBAI._embed_queryN List[str]idsOptional[List[str]]metadata Optional[Any]NonecszddlWn tytdwzddl}Wn ty#tdw|j|}|}||d<dd|D|d<fdd|D|d <|durS|j||gd d }|jj|d d dS)NrzRCould not import numpy python package. Please install it with `pip install numpy`.TCould not import pandas python package. Please install it with `pip install pandas`.idcSsg|]}|dqS)zutf-8)encoder"rrrr%]r&z!KDBAI._insert..r*csg|] }j|ddqS)Zfloat32)Zdtype)array)r#enprrr%^sr)ZaxisF)warn) numpyrpandasrr' DataFrameconcatrinsert)rrr/r1pdZembedsdfrr9r_insertDs,     z KDBAI._insert metadatasOptional[List[dict]] batch_sizeintkwargscKszddl}Wn tytdwt|}d}|dur*t||jr%|}n||}g}t|d|d} t| D]C} | |} | d|} || | } |rU|| | }n ddtt| D}|durp|j| | jdd}nd}| | ||||}q:|S) aRun more texts through the embeddings and add to the vectorstore. Args: texts (Iterable[str]): Texts to add to the vectorstore. metadatas (Optional[List[dict]]): List of metadata corresponding to each chunk of text. ids (Optional[List[str]]): List of IDs corresponding to each chunk of text. batch_size (Optional[int]): Size of batch of chunks of text to insert at once. Returns: List[str]: List of IDs of the added texts. rNr4r;cSsg|]}ttqSr)r+uuiduuid4)r#_rrrr%sz#KDBAI.add_texts..T)Zdrop) r>rr(rr?lenrangeZilocZ reset_indexrD)rrrFr/rHrJrBZmetadfZout_idsZnbatchesiistartZiendbatchZ batch_idsZ batch_metarrr add_textscs8        zKDBAI.add_texts documentsList[Document]cKsVzddl}Wn tytdwdd|D}|dd|D}|j|||dS)aHRun more documents through the embeddings and add to the vectorstore. Args: documents (List[Document]: Documents to add to the vectorstore. batch_size (Optional[int]): Size of batch of documents to insert at once. Returns: List[str]: List of IDs of the added texts. rNr4cSg|]}|jqSr) page_contentr#xrrrr%z'KDBAI.add_documents..cSrVr)r1rXrrrr%rZ)r1rH)r>rr?rS)rrTrHrJrBrr1rrr add_documentss  zKDBAI.add_documentsr;querykfilterOptional[List]List[Tuple[Document, float]]cKs|j||f||d|S)anRun similarity search with distance from a query string. Args: query (str): Query string. k (Optional[int]): number of neighbors to retrieve. filter (Optional[List]): KDB.AI metadata filter clause: https://code.kx.com/kdbai/use/filter.html Returns: List[Document]: List of similar documents. r]r^)&similarity_search_by_vector_with_scorer-)rr\r]r^rJrrrsimilarity_search_with_scoresz"KDBAI.similarity_search_with_scorerac Ksd|vr |d}|jjd |g||d|}g}t|tr#|d}n|S|jddD]}|d}|d} |t|dd |Dd | fq+|S) aReturn documents most similar to embedding, along with scores. Args: embedding (List[float]): query vector. k (Optional[int]): number of neighbors to retrieve. filter (Optional[List]): KDB.AI metadata filter clause: https://code.kx.com/kdbai/use/filter.html Returns: List[Document]: List of similar documents. n)Zvectorsrdr^rrecords)Zorientr*Z __nn_distancecSsi|] \}}|dkr||qS)r*r)r#r]vrrr sz@KDBAI.similarity_search_by_vector_with_score..)rWr1Nr) poprsearchrr(to_dictappendritems) rrr]r^rJmatchesdocsrowr*Zscorerrrrbs&      z,KDBAI.similarity_search_by_vector_with_scorecKs&|j|f||d|}dd|DS)a`Run similarity search from a query string. Args: query (str): Query string. k (Optional[int]): number of neighbors to retrieve. filter (Optional[List]): KDB.AI metadata filter clause: https://code.kx.com/kdbai/use/filter.html Returns: List[Document]: List of similar documents. racSsg|]\}}|qSrr)r#docrMrrrr%sz+KDBAI.similarity_search..)rc)rr\r]r^rJZdocs_and_scoresrrrsimilarity_searchszKDBAI.similarity_searchclscKstd)zNot implemented.) Exception)rrrrrFrJrrr from_textss zKDBAI.from_texts)r rrr rr)rr)rr rr!)r*r+rr,r)rr.r/r0r1r2rr3)NNrE) rr rFrGr/r0rHrIrJrrr.)rE)rTrUrHrIrJrrr.) r\r+r]rIr^r_rJrrr`) rr,r]rIr^r_rJrrr`) r\r+r]rIr^r_rJrrrU) rrrrr.rr rFrGrJrrr)__name__ __module__ __qualname____doc__r ZEUCLIDEAN_DISTANCErpropertyrr)r-rDrSr[rcrbrq classmethodrtrrrrr s8     " 8  + r ) __future__rloggingrKtypingrrrrrZlangchain_core.documentsrZlangchain_core.embeddingsr Zlangchain_core.vectorstoresr Z&langchain_community.vectorstores.utilsr getLoggerruloggerr rrrrs