a bg_/@sddlmZddlZddlmZmZmZmZmZm Z m Z m Z ddl m Z ddlmZddlmZddlmZer|ddlmZdd d d d d d dZGdddeZdS)) annotationsN) TYPE_CHECKINGAnyDictIterableListOptionalTupleType)Document) Embeddings) get_from_env) VectorStore)ClientOptional[Client] Optional[str]r)clienturlapi_keyreturnc Csz ddl}Wnty&tdYn0|sp|p8tdd}z|pHtdd}Wnty^Yn0|j||d}nt||jstdt|z |Wn2ty}ztd |WYd}~n d}~00|S) Nrz^Could not import meilisearch python package. Please install it with `pip install meilisearch`.rZMEILI_HTTP_ADDRrZMEILI_MASTER_KEY)rrz8client should be an instance of meilisearch.Client, got z"Failed to connect to Meilisearch: ) meilisearch ImportErrorr Exceptionr isinstance ValueErrortypeversion)rrrrerz/var/www/html/cobodadashboardai.evdpl.com/venv/lib/python3.9/site-packages/langchain_community/vectorstores/meilisearch.py_create_clients0      $r c@seZdZdZd.ddddd d d d d d d d dZd/dddd dddddZd0d ddd dddddZd1d ddd dddd d!Zd2d"d dd ddd#d$d%Zd3d"ddd ddd&d'd(Z e ddddddddidf d)ddddd d d dd d d*d ddd+d,d-Z dS)4 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) embeddersr rrstrzOptional[Dict[str, Any]]) embeddingrrr index_nametext_key metadata_keyr%c CsPt|||d}||_||_||_||_||_||_|jt|j ||_ dS)z#Initialize with Meilisearch client.rrrN) r _client _index_name _embedding _text_key _metadata_keyZ _embeddersindexr&Zupdate_embeddersZ_embedders_settings) selfr'rrrr(r)r*r%rrr__init__Rs zMeilisearch.__init__defaultz Iterable[str]zOptional[List[dict]]zOptional[List[str]]rz List[str])texts metadatasids embedder_namekwargsrc Kst|}g}|dur"dd|D}|dur8dd|D}|j|}t|D]J\}} ||} ||} | | |j<||} |d| d|| i|j| iqL|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. NcSsg|]}tjqSr)uuiduuid4hex.0_rrr z)Meilisearch.add_texts..cSsg|]}iqSrrr=rrrr@rAidZ_vectors) listr.Zembed_documents enumerater/appendr0r,r1r&r-Z add_documents) r2r5r6r7r8r9docsZembedding_vectorsir#rBr$r'rrr add_textsks(    zMeilisearch.add_textsintzOptional[Dict[str, str]]zList[Document])querykfilterr8r9rcKs"|j|||||d}dd|DS)aReturn meilisearch documents most similar to the query. Args: query (str): Query text for which to find similar documents. embedder_name: Name of the embedder to be used. Defaults to "default". k (int): Number of documents to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Document]: List of Documents most similar to the query text and score for each. )rKr8rLrMr9cSsg|] \}}|qSrrr>docr?rrrr@rAz1Meilisearch.similarity_search..)similarity_search_with_score)r2rKrLrMr8r9Zdocs_and_scoresrrrsimilarity_searchszMeilisearch.similarity_searchzList[Tuple[Document, float]]cKs$|j|}|j|||||d}|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'r8rLrMr9)r.Z embed_query'similarity_search_by_vector_with_scores)r2rKrLrMr8r9Z_queryrFrrrrPs z(Meilisearch.similarity_search_with_scorez List[float])r'r8rLrMr9rc Ksg}|jt|jd|d|d||dd}|dD]B}||j} |j| vr8| |j} |d} |t | | d| fq8|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?)Z semanticRatioZembedderT)ZvectorZhybridlimitrMZshowRankingScorehitsZ _rankingScore)Z page_contentr$) r,r1r&r-searchr0r/poprEr ) r2r'r8rLrMr9rFresultsresultr$r#Zsemantic_scorerrrrSs&    z3Meilisearch.similarity_search_by_vector_with_scores)r'rLrMr8r9rcKs"|j|||||d}dd|DS)rTrRcSsg|] \}}|qSrrrNrrrr@!rAz;Meilisearch.similarity_search_by_vector..)rS)r2r'rLrMr8r9rFrrrsimilarity_search_by_vectorsz'Meilisearch.similarity_search_by_vectorzType[Meilisearch]zDict[str, Any])clsr5r'r6rrrr(r7r)r*r%r8r9rc Ks8t|||d}||| ||d}|j|| ||| | d|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, ) r+)r'r%rr()r5r8r6r7r)r*)r rH)r]r5r'r6rrrr(r7r)r*r%r8r9Z vectorstorerrr from_texts#s +zMeilisearch.from_texts)NNNr"r#r$)NNr4)rINr4)rINr4)r4rIN)rINr4) __name__ __module__ __qualname____doc__r3rHrQrPrSr\ classmethodr^rrrrr!.sT&  3!#/r!)NNN) __future__rr:typingrrrrrrr r Zlangchain_core.documentsr Zlangchain_core.embeddingsr Zlangchain_core.utilsr Zlangchain_core.vectorstoresrrrr r!rrrrs (