jK ddlmZddlZddlZddlmZmZmZmZm Z m Z m Z m Z ddl mZddlZddlmZddlmZddlmZddlmZdd lmZerddlZdd Z d dd Zdd Zdd ZedddGddeZ y)) annotationsN) TYPE_CHECKINGAnyCallableDictIterableListOptionalTuple)uuid4) deprecated)Document) Embeddings) VectorStore)maximal_marginal_relevancec||dgdgdS)Ntext)namedataType)class properties) index_nametext_keys s/var/www/html/Fitness-lenito-AI-main/venv/lib/python3.12/site-packages/langchain_community/vectorstores/weaviate.py_default_schemars#!#H   c 2 ddl}|xstjj d}|xstjj d}|r|j j |nd}|jd||d|S#t$r tdwxYw)Nr_Could not import weaviate python package. Please install it with `pip install weaviate-client` WEAVIATE_URLWEAVIATE_API_KEY)api_key)urlauth_client_secretr)weaviate ImportErrorosenvirongetauth AuthApiKeyClient)r#r"kwargsr%r*s r_create_weaviate_clientr.)s    //C;(:;G8?8== # #G # 4TD 8?? Fst Fv FF   C   s BBc>dddtj|zz z S)N)npexp)vals r_default_score_normalizerr4;s qAs O$ $$rcZt|tjr|jS|SN) isinstancedatetime isoformat)values r_json_serializabler;?s$%**+  Lrz0.3.18z1.0z&langchain_weaviate.WeaviateVectorStore)sinceremovalalternative_importc eZdZdZddedf ddZeddZddZ d ddZ d ddZ d dd Z d dd Z d dd Z d dd Z d dd Ze dddddddded ddZdd dZy)!Weaviatea`Weaviate` vector store. To use, you should have the ``weaviate-client`` python package installed. Example: .. code-block:: python import weaviate from langchain_community.vectorstores import Weaviate client = weaviate.Client(url=os.environ["WEAVIATE_URL"], ...) weaviate = Weaviate(client, index_name, text_key) NTcL ddl}t||jst dt |||_||_||_||_ |jg|_ ||_ ||_ ||jj|yy#t$r tdwxYw)z Initialize with Weaviate client.rNz_Could not import weaviate python package. Please install it with `pip install weaviate-client`.z5client should be an instance of weaviate.Client, got )r%r&r7r, ValueErrortype_client _index_name _embedding _text_key _query_attrsrelevance_score_fn_by_textextend) selfclientrr embedding attributesrIby_textr%s r__init__zWeaviate.__init__Zs   &(//2GV ~V  %#!!^^,"4  !    $ $Z 0 "! H  s BB#c|jSr6)rFrLs r embeddingszWeaviate.embeddings|s rc>|jr |jStSr6)rIr4rSs r_select_relevance_score_fnz#Weaviate._select_relevance_score_fns'&&  # # + rc pddlm}g}d}|jr6t|ts t |}|jj |}|j j5}t|D]\}} |j| i} |)||jD]\} } t| | | <|t} d|vr |d|} n d|vr|d|} |j| |j| |r||nd|jd|j!|  ddd|S#1swY|SxYw)z4Upload texts with metadata (properties) to Weaviate.rget_valid_uuidNuuidsidstenant) data_object class_nameuuidvectorr\) weaviate.utilrYrFr7listembed_documentsrDbatch enumeraterGitemsr;r add_data_objectrEr)append)rLtexts metadatasr-rYr[rTrdirdata_propertieskeyr3_ids r add_textszWeaviate.add_textss7 126 ??eT*U 88?J \\  5$U+4#'>>4"8($-aL$6$6$8S/A#/F,%9%UW-f$ /!,Cf_ -*C%% /#//,6:a=D!::h/ & 3/, 2 3 2 s #B=D++D5c |jr|j||fi|S|j td|jj |}|j ||fi|S)Return docs most similar to query. Args: query: Text to look up documents similar to. k: Number of Documents to return. Defaults to 4. Returns: List of Documents most similar to the query. zC_embedding cannot be None for similarity_search when _by_text=False)rJsimilarity_search_by_textrFrB embed_querysimilarity_search_by_vector)rLquerykr-rNs rsimilarity_searchzWeaviate.similarity_searchsq ==1411%EfE E& %33E:I3433IqKFK Krc  d|gi}|jdr|jd|d<|jjj|j|j}|jdr |j |jd}|jdr |j |jd}|jdr |j|jd}|j|j|j}d|vrtd|dg}|d d |jD]9}|j|j} |jt| | ;|S) rqconceptssearch_distance certainty where_filterr\ additionalerrorsError during query: dataGet page_contentmetadata)r)rDrurErH with_where with_tenantwith_additionalwith_near_text with_limitdorBpoprGrhr) rLrurvr-content query_objresultdocsresrs rrrz"Weaviate.similarity_search_by_texts\$.w"7 ::' (#)::.?#@GK LL&&**4+;+;T=N=NO ::n %!,,VZZ-GHI ::h !--fjj.BCI ::l #!11&**\2JKI))'2==a@CCE v 3F84D3EFG G&>%()9)9:C774>>*D KKdSA B; rc d|i}|jjj|j|j}|jdr |j |jd}|jdr |j |jd}|jdr |j|jd}|j|j|j}d|vrtd|dg}|dd|jD]9}|j|j} |jt| | ;|S) z:Look up similar documents by embedding vector in Weaviate.r`r|r\r}r~rrrr)rDrur)rErHrrrwith_near_vectorrrrBrrGrhr) rLrNrvr-r`rrrrrs rrtz$Weaviate.similarity_search_by_vectors9I&LL&&**4+;+;T=N=NO ::n %!,,VZZ-GHI ::h !--fjj.BCI ::l #!11&**\2JKI++F3>>qADDF v 3F84D3EFG G&>%()9)9:C774>>*D KKdSA B; rc |j|jj|}n td|j|f|||d|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. Returns: List of Documents selected by maximal marginal relevance. zCmax_marginal_relevance_search requires a suitable Embeddings object)rvfetch_k lambda_mult)rFrsrB'max_marginal_relevance_search_by_vector)rLrurvrrr-rNs rmax_marginal_relevance_searchz&Weaviate.max_marginal_relevance_searchs`2 ?? &33E:IU %()9)9:C774>>*DFF3}-h7HE  " "H$$Mu#U V;rrF)rM weaviate_urlweaviate_api_key batch_sizerrrPrIc  ddlm} |xs t||}|r|jj ||xsdt j}t|| }|jj|s|jj||r|j|nd}|rt|djnd}d| vr| jd}n/t!t#|Dcgc]}| t }}|j5}t%|D]U\}}| |i}|#||jD] }|||||<||}|||d }||||d <|j&d i|W|j)ddd|||| f||| | d | S#t$r}td|d}~wwxYwcc}w#1swY;xYw) avConstruct Weaviate wrapper from raw documents. This is a user-friendly interface that: 1. Embeds documents. 2. Creates a new index for the embeddings in the Weaviate instance. 3. Adds the documents to the newly created Weaviate index. This is intended to be a quick way to get started. Args: texts: Texts to add to vector store. embedding: Text embedding model to use. metadatas: Metadata associated with each text. client: weaviate.Client to use. weaviate_url: The Weaviate URL. If using Weaviate Cloud Services get it from the ``Details`` tab. Can be passed in as a named param or by setting the environment variable ``WEAVIATE_URL``. Should not be specified if client is provided. weaviate_api_key: The Weaviate API key. If enabled and using Weaviate Cloud Services, get it from ``Details`` tab. Can be passed in as a named param or by setting the environment variable ``WEAVIATE_API_KEY``. Should not be specified if client is provided. batch_size: Size of batch operations. index_name: Index name. text_key: Key to use for uploading/retrieving text to/from vectorstore. by_text: Whether to search by text or by embedding. relevance_score_fn: Function for converting whatever distance function the vector store uses to a relevance score, which is a normalized similarity score (0 means dissimilar, 1 means similar). kwargs: Additional named parameters to pass to ``Weaviate.__init__()``. Example: .. code-block:: python from langchain_community.embeddings import OpenAIEmbeddings from langchain_community.vectorstores import Weaviate embeddings = OpenAIEmbeddings() weaviate = Weaviate.from_texts( texts, embeddings, weaviate_url="http://localhost:8080" ) rrXrN)r#r")r LangChain_rZ)r_r]r^r`)rNrOrIrPr)rarYr&r.rd configurer hexrschemaexists create_classrcrbkeysrrangelenrergflush)clsrirNrjrMrrrrrrPrIr-rYerrTrOrZ_rdrkrrlrmrnparamss r from_textszWeaviate.from_textss@  4 2$   LL " "j " 9=Z }#=  X6}}##J/ MM & &v .9BY..u5 2;T)A,++-.  f JJw'E6;CJ6GH6G^EG,6GEH \\U$U+4d#((|002/8|C/@, 3Ah #2", )'1!}F8$%%%//-,0 KKM36      !1    q G  6I \s*F&5GA4G& G/ F;;GGc x| td|D](}|jjj|*y)zUDelete by vector IDs. Args: ids: List of ids to delete. NzNo ids provided to delete.)r_)rBrDr]delete)rLr[r-ids rrzWeaviate.delete s< ;9: :B LL $ $ + + + 4r)rMrrstrrrrNOptional[Embeddings]rOOptional[List[str]]rI"Optional[Callable[[float], float]]rPbool)returnr)rzCallable[[float], float]r6)riz Iterable[str]rjOptional[List[dict]]r-rr List[str]))rurrvintr-rrList[Document])rN List[float]rvrr-rrr)rg?) rurrvrrrrfloatr-rrr) rNrrvrrrrrr-rrr)rurrvrr-rrzList[Tuple[Document, float]])rirrNrrjrrMzOptional[weaviate.Client]r Optional[str]rrrz Optional[int]rrrrrPrrIrr-rrr@)r[rr-rrNone)__name__ __module__ __qualname____doc__r4rQpropertyrTrVrorwrrrtrrr classmethodrrrrrr@r@Es (+/*. & 1 1 1 1 ( 1 ( 1  1 1D +/))() )  )X$%LL L03L L0$% 03 @01$),rs"    *-03M !G G GG G$%   ? L5{L5  L5r