Ah-&SrSSKJrJr SSKJr SSKJr SSKJ r SSK J r SSK J r SSKJrJr SS KJrJrJr SS KJr SS KJr S \4S jr"SS\5rS \\ 4Sjr"SS\5rg)z'Vectorstore stubs for the indexing api.)AnyOptional) BaseLoader)Document) Embeddings)BaseLanguageModel) VectorStore)RecursiveCharacterTextSplitter TextSplitter) BaseModel ConfigDictField)RetrievalQAWithSourcesChain) RetrievalQAreturnc[SSS9$)z=Return the default text splitter used for chunking documents.ir) chunk_size chunk_overlap)r U/var/www/html/shao/venv/lib/python3.13/site-packages/langchain/indexes/vectorstore.py_get_default_text_splitterrs )T KKrc "\rSrSr%Sr\\S'\"SSS9rSS\ S \ \ S \ \ \ \ 4S \ S \ 4 S jjrSS\ S \ \ S \ \ \ \ 4S \ S \ 4 SjjrSS\ S \ \ S \ \ \ \ 4S \ S \ 4 SjjrSS\ S \ \ S \ \ \ \ 4S \ S \ 4 SjjrSrg)VectorStoreIndexWrapperz-Wrapper around a vectorstore for easy access. vectorstoreTforbidarbitrary_types_allowedextraNquestionllmretriever_kwargskwargsrc Uc Sn[U5eU=(d 0n[R"U4SURR"S0UD60UD6nUR UR U05UR$)a]Query the vectorstore using the provided LLM. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: The result string from the RetrievalQA chain. This API has been changed to require an LLM. Please provide an llm to use for querying the vectorstore. For example, from langchain_openai import OpenAI llm = OpenAI(temperature=0) retrieverr)NotImplementedErrorrfrom_chain_typer as_retrieverinvoke input_key output_keyselfr!r"r#r$msgchains rqueryVectorStoreIndexWrapper.query s$ ;. &c* *+1r++  &&33G6FG   ||U__h789I9IJJrc # Uc Sn[U5eU=(d 0n[R"U4SURR"S0UD60UD6nUR UR U05IShvN UR$N7f)ayAsynchronously query the vectorstore using the provided LLM. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: The asynchronous result string from the RetrievalQA chain. Nr&r'r)r(rr)rr*ainvoker,r-r.s raqueryVectorStoreIndexWrapper.aqueryCs$ ;. &c* *+1r++  &&33G6FG   mmU__h$?@@%BRBRSS@sA/B1B2Bc Uc Sn[U5eU=(d 0n[R"U4SURR"S0UD60UD6nUR UR U05$)a|Query the vectorstore and retrieve the answer along with sources. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: A dictionary containing the answer and source documents. r&r'r)r(rr)rr*r+ question_keyr.s rquery_with_sources*VectorStoreIndexWrapper.query_with_sourcesfs$ ;. &c* *+1r+;;  &&33G6FG   ||U//:;;rc # Uc Sn[U5eU=(d 0n[R"U4SURR"S0UD60UD6nUR UR U05IShvN $N7f)aAsynchronously query the vectorstore and retrieve the answer and sources. Args: question: The question or prompt to query. llm: The language model to use. Must not be None. retriever_kwargs: Optional keyword arguments for the retriever. **kwargs: Additional keyword arguments forwarded to the chain. Returns: A dictionary containing the answer and source documents. Nr&r'r)r(rr)rr*r5r9r.s raquery_with_sources+VectorStoreIndexWrapper.aquery_with_sourcess$ ;. &c* *+1r+;;  &&33G6FG   ]]E$6$6#ABBBBsA/A81A62A8r)NN)__name__ __module__ __qualname____firstlineno____doc__r __annotations__r model_configstrrrdictrr2r6r:r=__static_attributes__rrrrrsv7 $L,059 !K!K' (!K#4S>2 !K  !K !KL,059 !T!T' (!T#4S>2 !T  !T !TL,059 !<!<' (!<#4S>2 !<  !<  !2 !C  !C  !C!Crrc|SSKnSSKJn UR SSS9 U$![anSn[U5UeSnAff=f)zGet the InMemoryVectorStore.rN)InMemoryVectorStorezBPlease install langchain-community to use the InMemoryVectorStore.zUsing InMemoryVectorStore as the default vectorstore.This memory store won't persist data. You should explicitlyspecify a vectorstore when using VectorstoreIndexCreator) stacklevel)warnings)langchain_community.vectorstores.inmemoryrJ ImportErrorwarn)rMrJer0s r_get_in_memory_vectorstorerRsW&Q MM C   &R#A%&s ;6;c\rSrSr%Sr\"\S9r\\ \ S'\ \ S'\"\ S9r \\ S'\"\S9r\\ S'\"SS S 9rS \\S \4S jrS \\S \4SjrS\\S \4SjrS\\S \4SjrSrg)VectorstoreIndexCreatorzLogic for creating indexes.)default_factoryvectorstore_cls embedding text_splittervectorstore_kwargsTrrloadersrcx/nUH"nURUR55 M$ URU5$)zCreate a vectorstore index from a list of loaders. Args: loaders: A list of `BaseLoader` instances to load documents. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. )extendloadfrom_documents)r/r[docsloaders r from_loaders$VectorstoreIndexCreator.from_loaderss6F KK &""4((rc # /nUH,nURUR5Vs/sShvN oDPM URU5IShvN $N" Os snfsn5 M[N7f)zAsynchronously create a vectorstore index from a list of loaders. Args: loaders: A list of `BaseLoader` instances to load documents. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. N)r] alazy_loadafrom_documents)r/r[r`radocs r afrom_loaders%VectorstoreIndexCreator.afrom_loaderssVF KKf.?.?.ABBs))$///CB C/sA%A$A A AA A A$ A" A$A A A$ documentscURRU5nURR"UUR40UR D6n[ US9$)zCreate a vectorstore index from a list of documents. Args: documents: A list of `Document` objects. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. r)rYsplit_documentsrWr_rXrZrr/rjsub_docsrs rr_&VectorstoreIndexCreator.from_documentssW%%55i@**99  NN %% ';??rc# URRU5nURR"UUR40UR D6IShvN n[ US9$N 7f)zAsynchronously create a vectorstore index from a list of documents. Args: documents: A list of `Document` objects. Returns: A `VectorStoreIndexWrapper` containing the constructed vectorstore. Nrl)rYrmrWrfrXrZrrns rrf'VectorstoreIndexCreator.afrom_documentssd%%55i@ 00@@  NN %%  ';??  sAA#A!A#rN)r?r@rArBrCrrRrWtyper rDrrrYr rGrZr rElistrrrbrhrr_rfrHrrrrTrTs%).2*OT+&"'8R"SM<S$T:: $L )D$4 )9P ) 04 +; 0@W 0@X@;R@"@>@ !@rrTN)rCtypingrrlangchain_core.document_loadersrlangchain_core.documentsrlangchain_core.embeddingsrlangchain_core.language_modelsrlangchain_core.vectorstoresr langchain_text_splittersr r pydanticr r r*langchain.chains.qa_with_sources.retrievalr"langchain.chains.retrieval_qa.baserrrrsrRrTrrrrsi- 6-0<3Q11R:LLL TCiTCnD$5$N@iN@r