Ng_/ddlmZddlZddlmZmZmZmZmZm Z m Z m Z ddl m Z ddlmZddlmZddlmZerddlmZ dddZGddeZdS)) annotationsN) TYPE_CHECKINGAnyDictIterableListOptionalTupleType)Document) Embeddings) get_from_env) VectorStore)ClientclientOptional[Client]url Optional[str]api_keyreturnrc ddl}n#t$rtdwxYw|sN|ptdd} |ptdd}n#t$rYnwxYw|||}n4t ||jst dt| |n$#t $r}t d |d}~wwxYw|S) Nrz^Could not import meilisearch python package. Please install it with `pip install meilisearch`.rMEILI_HTTP_ADDRrMEILI_MASTER_KEY)rrz8client should be an instance of meilisearch.Client, got z"Failed to connect to Meilisearch: ) meilisearch ImportErrorr Exceptionr isinstance ValueErrortypeversion)rrrres h/var/www/html/ai-engine/env/lib/python3.11/site-packages/langchain_community/vectorstores/meilisearch.py_create_clientr#sU       @      ;\%):;; Li9K!L!LGG    D ##W#==  2 3 3  "<< " "   C CCCAaAABBBC Ms1!A AA)B>> CCCc eZdZdZ d3ddd4dZ d5d6d!Z d7d8d)Z d7d9d+Z d:d;d-Z d7d Meilisearcha`Meilisearch` vector store. To use this, you need to have `meilisearch` python package installed, and a running Meilisearch instance. To learn more about Meilisearch Python, refer to the in-depth Meilisearch Python documentation: https://meilisearch.github.io/meilisearch-python/. See the following documentation for how to run a Meilisearch instance: https://www.meilisearch.com/docs/learn/getting_started/quick_start. Example: .. code-block:: python from langchain_community.vectorstores import Meilisearch from langchain_community.embeddings.openai import OpenAIEmbeddings import meilisearch # api_key is optional; provide it if your meilisearch instance requires it client = meilisearch.Client(url='http://127.0.0.1:7700', api_key='***') embeddings = OpenAIEmbeddings() embedders = { "theEmbedderName": { "source": "userProvided", "dimensions": "1536" } } vectorstore = Meilisearch( embedding=embeddings, embedders=embedders, client=client, index_name='langchain_demo', text_key='text') Nlangchain-demotextmetadata) embedders embeddingr rrrrr index_namestrtext_key metadata_keyr)Optional[Dict[str, Any]]ct|||}||_||_||_||_||_||_|jt|j ||_ dS)z#Initialize with Meilisearch client.rrrN) r#_client _index_name _embedding _text_key _metadata_key _embeddersindexr,update_embedders_embedders_settings) selfr*rrrr+r-r.r)s r"__init__zMeilisearch.__init__Rs v3HHH %#!)##'<#5#5  ! !$ $  9 % %    defaulttexts Iterable[str] metadatasOptional[List[dict]]idsOptional[List[str]] embedder_namekwargsrr List[str]c t|}g}| d|D}| d|D}|j|}t|D]K\}} ||} ||} | | |j<||} |d| d|| i|j| iL|jt|j  ||S)a!Run more texts through the embedding and add them to the vector store. Args: texts (Iterable[str]): Iterable of strings/text to add to the vectorstore. embedder_name: Name of the embedder. Defaults to "default". metadatas (Optional[List[dict]]): Optional list of metadata. Defaults to None. ids Optional[List[str]]: Optional list of IDs. Defaults to None. Returns: List[str]: List of IDs of the texts added to the vectorstore. Nc>g|]}tjjS)uuiduuid4hex.0_s r" z)Meilisearch.add_texts..s!3334:<<#333r=cg|]}iSrJrJrNs r"rQz)Meilisearch.add_texts..s++++++r=id_vectors) listr4embed_documents enumerater5appendr6r2r8r,r3 add_documents) r;r?rArCrErFdocsembedding_vectorsir'rSr(r*s r" add_textszMeilisearch.add_textsks*U  ;33U333C  ++U+++I O;;EBB ''  GAtQB |H'+HT^ $)!,I KK"M!3Y ?)+X     3t/0011??EEE r=querykintfilterOptional[Dict[str, str]]List[Document]c N||||||}d|DS)aReturn meilisearch documents most similar to the query. Args: query (str): Query text for which to find similar documents. embedder_name: Name of the embedder to be used. Defaults to "default". k (int): Number of documents to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Document]: List of Documents most similar to the query text and score for each. )r_rEr`rbrFcg|]\}}|SrJrJrOdocrPs r"rQz1Meilisearch.similarity_search..s222Q222r=)similarity_search_with_score)r;r_r`rbrErFdocs_and_scoress r"similarity_searchzMeilisearch.similarity_searchsC*;;' <  32/2222r=List[Tuple[Document, float]]c n|j|}||||||}|S)a%Return meilisearch documents most similar to the query, along with scores. Args: query (str): Query text for which to find similar documents. embedder_name: Name of the embedder to be used. Defaults to "default". k (int): Number of documents to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Document]: List of Documents most similar to the query text and score for each. r*rEr`rbrF)r4 embed_query'similarity_search_by_vector_with_scores)r;r_r`rbrErF_queryrZs r"riz(Meilisearch.similarity_search_with_scoresI*,,U33;;' <   r= List[float]c ng}|jt|jd|d|d||dd}|dD]`}||j} |j| vrH| |j} |d} |t| | | fa|S) #Return meilisearch documents most similar to embedding vector. Args: embedding (List[float]): Embedding to look up similar documents. embedder_name: Name of the embedder to be used. Defaults to "default". k (int): Number of documents to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Document]: List of Documents most similar to the query vector and score for each. g?) semanticRatioembedderT)vectorhybridlimitrbshowRankingScorehits _rankingScore) page_contentr() r2r8r,r3searchr6r5poprXr ) r;r*rEr`rbrFrZresultsresultr(r'semantic_scores r"rpz3Meilisearch.similarity_search_by_vector_with_scoress*,$$S)9%:%:;;BB #,/]KK $(      fo  Fd01H~))||DN33!'!8 4(CCC^T r=c N||||||}d|DS)rtrncg|]\}}|SrJrJrgs r"rQz;Meilisearch.similarity_search_by_vector..!s'''Q'''r=)rp)r;r*r`rbrErFrZs r"similarity_search_by_vectorz'Meilisearch.similarity_search_by_vectorsC*;;' <  ('$''''r=clsType[Meilisearch]Dict[str, Any]c  ~t|||}||| ||}||| ||| | |S)aConstruct Meilisearch wrapper from raw documents. This is a user-friendly interface that: 1. Embeds documents. 2. Adds the documents to a provided Meilisearch index. This is intended to be a quick way to get started. Example: .. code-block:: python from langchain_community.vectorstores import Meilisearch from langchain_community.embeddings import OpenAIEmbeddings import meilisearch # The environment should be the one specified next to the API key # in your Meilisearch console client = meilisearch.Client(url='http://127.0.0.1:7700', api_key='***') embedding = OpenAIEmbeddings() embedders: Embedders index setting. embedder_name: Name of the embedder. Defaults to "default". docsearch = Meilisearch.from_texts( client=client, embedding=embedding, ) r1)r*r)rr+)r?rErArCr-r.)r#r])rr?r*rArrrr+rCr-r.r)rErF vectorstores r" from_textszMeilisearch.from_texts#stV v3HHHc!    '%    r=)NNNr&r'r()r*r rrrrrrr+r,r-r,r.r,r)r/)NNr>) r?r@rArBrCrDrErrFrrrG)r^Nr>) r_r,r`rarbrcrErrFrrrd) r_r,r`rarbrcrErrFrrrl)r>r^N) r*rrrErr`rarbr/rFrrrl) r*rrr`rarbrcrErrFrrrd)rrr?rGr*r rArBrrrrrrr+r,rCrDr-rr.rr)rrErrFrrr%) __name__ __module__ __qualname____doc__r<r]rkrirpr classmethodrrJr=r"r%r%.sX!!L$(!!%*&&/3&&&&&&8+/#''0 .....f+/'0 33333B+/'0 F(1+/ *****^+/'0 (((((< +/#'!!%*#'"(&0$&'0::::[:::r=r%)NNN)rrrrrrrr) __future__rrKtypingrrrrrr r r langchain_core.documentsr langchain_core.embeddingsr langchain_core.utilsrlangchain_core.vectorstoresrrrr#r%rJr=r"rs """""" RRRRRRRRRRRRRRRRRRRR------000000------333333#"""""" $!>ppppp+pppppr=