dhOSrSSKrSSKJrJrJrJr SSKJr SSK J r SSK J r SSK Jr SSKJr SS KJr "S S \5rS \S \S\4Sjrg)zMilvus RetrieverN)AnyDictListOptional)CallbackManagerForRetrieverRun)Document) Embeddings) BaseRetriever)model_validator)Milvusc \rSrSr%Sr\\S'Sr\\S'Sr \ \ \\ 4\S'Sr \ \ \\ 4\S'S r\\S 'Sr\ \\S '\\S '\\S '\"SS9\S\ S\ 4Sj55rSS\\S\ \\SS4SjjrS\S\S\ S\\4SjrSrg)MilvusRetrieveraMilvus API retriever. See detailed instructions here: https://python.langchain.com/docs/integrations/retrievers/milvus_hybrid_search/ Setup: Install ``langchain-milvus`` and other dependencies: .. code-block:: bash pip install -U pymilvus[model] langchain-milvus Key init args: collection: Milvus Collection Instantiate: .. code-block:: python retriever = MilvusCollectionHybridSearchRetriever(collection=collection) Usage: .. code-block:: python query = "What are the story about ventures?" retriever.invoke(query) .. code-block:: none [Document(page_content="In 'The Lost Expedition' by Caspian Grey...", metadata={'doc_id': '449281835035545843'}), Document(page_content="In 'The Phantom Pilgrim' by Rowan Welles...", metadata={'doc_id': '449281835035545845'}), Document(page_content="In 'The Dreamwalker's Journey' by Lyra Snow..", metadata={'doc_id': '449281835035545846'})] Use within a chain: .. code-block:: python from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import RunnablePassthrough from langchain_openai import ChatOpenAI prompt = ChatPromptTemplate.from_template( """Answer the question based only on the context provided. Context: {context} Question: {question}""" ) llm = ChatOpenAI(model="gpt-3.5-turbo-0125") def format_docs(docs): return "\n\n".join(doc.page_content for doc in docs) chain = ( {"context": retriever | format_docs, "question": RunnablePassthrough()} | prompt | llm | StrOutputParser() ) chain.invoke("What novels has Lila written and what are their contents?") .. code-block:: none "Lila Rose has written 'The Memory Thief,' which follows a charismatic thief..." embedding_functionLangChainCollectioncollection_nameNcollection_propertiesconnection_argsSessionconsistency_level search_paramsstore retrieverbefore)modevaluesreturnc|[USUSUSUSUS5US'USRSUS0S 9US 'U$) z&Create the Milvus store and retriever.rrrrrrparamr) search_kwargsr)r as_retriever)clsrs ]/var/www/html/shao/venv/lib/python3.13/site-packages/langchain_community/retrievers/milvus.pycreate_retriever MilvusRetriever.create_retriever`ss! ' ( $ % * + $ % & '  w%Wo::"F?$;<; { texts metadatasc:URRX5 g)zAdd text to the Milvus store Args: texts (List[str]): The text metadatas (List[dict]): Metadata dicts, must line up with existing store N)r add_texts)selfr'r(s r#r*MilvusRetriever.add_textsps U.r&query run_managerkwargsc \URR"U4SUR50UD6$)Nr.)rinvoke get_child)r+r-r.r/s r#_get_relevant_documents'MilvusRetriever._get_relevant_documents{s7~~$$  *446 :@  r&)N)__name__ __module__ __qualname____firstlineno____doc__r __annotations__rstrrrrrrrrdictr r r classmethodr$rr*rrr3__static_attributes__r5r&r#rrsBH#"0OS06:8DcN3:04OXd38n-4&s&$(M8D>( M(# d s $ CG /#Y /+3DJ+? /  /    4    h  r&rargsr/rcN[R"S[5 [U0UD6$)zDeprecated MilvusRetreiver. Please use MilvusRetriever ('i' before 'e') instead. Args: *args: **kwargs: Returns: MilvusRetriever zfMilvusRetreiver will be deprecated in the future. Please use MilvusRetriever ('i' before 'e') instead.)warningswarnDeprecationWarningr)r@r/s r#MilvusRetreiverrEs* MM ? D +F ++r&)r:rBtypingrrrrlangchain_core.callbacksrlangchain_core.documentsrlangchain_core.embeddingsr langchain_core.retrieversr pydanticr 'langchain_community.vectorstores.milvusr rrEr5r&r#rMsL,,C-03$: s ms l,3,#,/,r&