o Zh/@sddlmZddlZddlmZmZmZmZmZm Z m Z m Z ddl m Z ddlmZddlmZddlmZer>ddlmZ   ddddZGdddeZdS)) annotationsN) TYPE_CHECKINGAnyDictIterableListOptionalTupleType)Document) Embeddings) get_from_env) VectorStore)ClientclientOptional[Client]url Optional[str]api_keyreturnrc Cszddl}Wn tytdw|s6|ptdd}z |p"tdd}Wn ty-Ynw|j||d}nt||jsEtdt|z|W|Sty_}ztd |d}~ww) 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)rrrrerc/var/www/html/lang_env/lib/python3.10/site-packages/langchain_community/vectorstores/meilisearch.py_create_clients4      r c @seZdZdZ      d:ddd;ddZ   dd?d+d,Z $  d>d@d.d/Z  $ dAdBd1d2Z $  d>dCd3d4Z e ddddddddidf dDd8d9Z dS)E 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]]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__Qs zMeilisearch.__init__defaulttexts Iterable[str] metadatasOptional[List[dict]]idsOptional[List[str]] embedder_namekwargsrr List[str]c Kst|}g}|durdd|D}|durdd|D}|j|}t|D]%\}} ||} ||} | | |j<||} |d| d|| i|j| iq&|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 sz)Meilisearch.add_texts..cSsg|]}iqSrrrBrrrrEsidZ_vectors) listr/Zembed_documents enumerater0appendr1r-r2r(r.Z add_documents) r3r6r8r:r<r=docsZembedding_vectorsir#rFr$r&rrr add_textsjs(    zMeilisearch.add_textsquerykintfilterOptional[Dict[str, str]]List[Document]cK"|j|||||d}dd|DS)aReturn meilisearch documents most similar to the query. Args: query (str): Query text for which to find similar documents. embedder_name: Name of the embedder to be used. Defaults to "default". k (int): Number of documents to return. Defaults to 4. filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None. Returns: List[Document]: List of Documents most similar to the query text and score for each. )rNr<rOrQr=cSg|]\}}|qSrrrCdocrDrrrrEz1Meilisearch.similarity_search..)similarity_search_with_score)r3rNrOrQr<r=Zdocs_and_scoresrrrsimilarity_searchzMeilisearch.similarity_searchList[Tuple[Document, float]]cKs$|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&r<rOrQr=)r/Z embed_query'similarity_search_by_vector_with_scores)r3rNrOrQr<r=Z_queryrJrrrrYs z(Meilisearch.similarity_search_with_score List[float]c Ksg}|jt|jd|d|d||dd}|dD]!}||j} |j| vr=| |j} |d} |t | | d| fq|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)ZvectorZhybridlimitrQZshowRankingScorehitsZ _rankingScore)Z page_contentr$) r-r2r(r.searchr1r0poprIr ) r3r&r<rOrQr=rJresultsresultr$r#Zsemantic_scorerrrr^s,    z3Meilisearch.similarity_search_by_vector_with_scorescKrT)r`r]cSrUrrrVrrrrE#rXz;Meilisearch.similarity_search_by_vector..)r^)r3r&rOrQr<r=rJrrrsimilarity_search_by_vectorr[z'Meilisearch.similarity_search_by_vectorclsType[Meilisearch]Dict[str, Any]c 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')r6r<r8r:r)r*)r rL)rir6r&r8rrrr'r:r)r*r%r<r=Z vectorstorerrr from_texts%s +zMeilisearch.from_texts)NNNr"r#r$)r&r rrrrrrr'r(r)r(r*r(r%r+)NNr5) r6r7r8r9r:r;r<rr=rrr>)rMNr5) rNr(rOrPrQrRr<rr=rrrS) rNr(rOrPrQrRr<rr=rrr\)r5rMN) r&r_r<rrOrPrQr+r=rrr\) r&r_rOrPrQrRr<rr=rrrS)rirjr6r>r&r r8r9rrrrrrr'r(r:r;r)rr*rr%rkr<rr=rrr!) __name__ __module__ __qualname____doc__r4rLrZrYr^rh classmethodrlrrrrr!-sV&  3 ! # 2 r!)NNN)rrrrrrrr) __future__rr?typingrrrrrrr r Zlangchain_core.documentsr Zlangchain_core.embeddingsr Zlangchain_core.utilsr Zlangchain_core.vectorstoresrrrr r!rrrrs (