o Jjg(@s dZddlmZmZddlmZmZmZmZm Z m Z ddl m Z ddl mZmZddlmZddlmZmZddlmZdd lmZdd lmZmZdd lmZmZdd lm Z d Z!dZ"e#dZ$dede%ddfddZ&Gddde eZ'e ddddGddde Z(dS)z.Base interface for chains combining documents.)ABCabstractmethod)AnyDictListOptionalTupleType) deprecated)AsyncCallbackManagerForChainRunCallbackManagerForChainRun)Document)BasePromptTemplatePromptTemplate)RunnableConfig) create_model)RecursiveCharacterTextSplitter TextSplitter) BaseModelField)Chainz contextz{page_content}promptdocument_variable_namereturnNcCs$||jvrtd|d|jdS)NzPrompt must accept z= as an input variable. Received prompt with input variables: )input_variables ValueError)rrr_/var/www/html/zoom/venv/lib/python3.10/site-packages/langchain/chains/combine_documents/base.py_validate_prompts rc @s`eZdZUdZdZeed<dZeed< ddee de e fd d Z ddee de e fd d Z edeefd dZedeefddZdeededeefddZedeededeeeffddZedeededeeeffddZ ddeeeefdeedeeeffddZ ddeeeefdeedeeeffddZdS) BaseCombineDocumentsChainaWBase interface for chains combining documents. Subclasses of this chain deal with combining documents in a variety of ways. This base class exists to add some uniformity in the interface these types of chains should expose. Namely, they expect an input key related to the documents to use (default `input_documents`), and then also expose a method to calculate the length of a prompt from documents (useful for outside callers to use to determine whether it's safe to pass a list of documents into this chain or whether that will be longer than the context length). input_documents input_key output_text output_keyNconfigrcCst di|jttdfiS)NCombineDocumentsInput)r&)rr"rr selfr%rrrget_input_schema0s z*BaseCombineDocumentsChain.get_input_schemacCt di|jtdfiS)NCombineDocumentsOutput)r+)rr$strr'rrrget_output_schema8  z+BaseCombineDocumentsChain.get_output_schemacC|jgSz2Expect input key. :meta private: r"r(rrr input_keys@z$BaseCombineDocumentsChain.input_keyscCr/z3Return output key. :meta private: )r$r2rrr output_keysHr4z%BaseCombineDocumentsChain.output_keysdocskwargscKdS)aVReturn the prompt length given the documents passed in. This can be used by a caller to determine whether passing in a list of documents would exceed a certain prompt length. This useful when trying to ensure that the size of a prompt remains below a certain context limit. Args: docs: List[Document], a list of documents to use to calculate the total prompt length. Returns: Returns None if the method does not depend on the prompt length, otherwise the length of the prompt in tokens. Nrr(r7r8rrr prompt_lengthPsz'BaseCombineDocumentsChain.prompt_lengthcKr9aCombine documents into a single string. Args: docs: List[Document], the documents to combine **kwargs: Other parameters to use in combining documents, often other inputs to the prompt. Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. Nrr:rrr combine_docsbsz&BaseCombineDocumentsChain.combine_docscsdSr<rr:rrr acombine_docspsz'BaseCombineDocumentsChain.acombine_docsinputs run_managercsX|pt}|j}fdd|D}j|fd|i|\}}||j<|S)3Prepare inputs, call combine docs, prepare outputs.c i|] \}}|jkr||qSrr1.0kvr2rr  z3BaseCombineDocumentsChain._call.. callbacks)r get_noop_managerr"itemsr= get_childr$r(r?r@ _run_managerr7 other_keysoutputextra_return_dictrr2r_calls   zBaseCombineDocumentsChain._callcs`|pt}|j}fdd|D}j|fd|i|IdH\}}||j<|S)rAcrBrr1rCr2rrrGrHz4BaseCombineDocumentsChain._acall..rIN)r rJr"rKr>rLr$rMrr2r_acalls   z BaseCombineDocumentsChain._acallN) __name__ __module__ __qualname____doc__r"r,__annotations__r$rrr rr)r-propertyrr3r6r rintr;rrdictr=r>rr rRr rSrrrrr !s^     $      r z0.2.7zexample in API reference with more detail: https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.base.AnalyzeDocumentChain.htmlz1.0)since alternativeremovalc @seZdZUdZdZeed<eedZ e ed<e ed<e de efdd Ze de efd d Z dd eedeefddZ dd eedeefddZ ddeeefdeedeeeffddZd S)AnalyzeDocumentChainaChain that splits documents, then analyzes it in pieces. This chain is parameterized by a TextSplitter and a CombineDocumentsChain. This chain takes a single document as input, and then splits it up into chunks and then passes those chucks to the CombineDocumentsChain. This class is deprecated. See below for alternative implementations which supports async and streaming modes of operation. If the underlying combine documents chain takes one ``input_documents`` argument (e.g., chains generated by ``load_summarize_chain``): .. code-block:: python split_text = lambda x: text_splitter.create_documents([x]) summarize_document_chain = split_text | chain If the underlying chain takes additional arguments (e.g., ``load_qa_chain``, which takes an additional ``question`` argument), we can use the following: .. code-block:: python from operator import itemgetter from langchain_core.runnables import RunnableLambda, RunnableParallel split_text = RunnableLambda( lambda x: text_splitter.create_documents([x]) ) summarize_document_chain = RunnableParallel( question=itemgetter("question"), input_documents=itemgetter("input_document") | split_text, ) | chain.pick("output_text") To additionally return the input parameters, as ``AnalyzeDocumentChain`` does, we can wrap this construction with ``RunnablePassthrough``: .. code-block:: python from operator import itemgetter from langchain_core.runnables import ( RunnableLambda, RunnableParallel, RunnablePassthrough, ) split_text = RunnableLambda( lambda x: text_splitter.create_documents([x]) ) summarize_document_chain = RunnablePassthrough.assign( output_text=RunnableParallel( question=itemgetter("question"), input_documents=itemgetter("input_document") | split_text, ) | chain.pick("output_text") ) input_documentr")default_factory text_splittercombine_docs_chainrcCr/r0r1r2rrrr3r4zAnalyzeDocumentChain.input_keyscCs|jjSr5)rdr6r2rrrr6r4z AnalyzeDocumentChain.output_keysNr%cCr*)Nr`)r`)rr"r,r'rrrr)r.z%AnalyzeDocumentChain.get_input_schemacCs |j|SrT)rdr-r'rrrr-s z&AnalyzeDocumentChain.get_output_schemar?r@csZ|pt}|j}j|g}fdd|D}||jj<j|d|dS)z=Split document into chunks and pass to CombineDocumentsChain.crBrr1rCr2rrrGrHz.AnalyzeDocumentChain._call..T)return_only_outputsrI)r rJr"rccreate_documentsrKrdrL)r(r?r@rNdocumentr7rOrr2rrRs    zAnalyzeDocumentChain._callrT)rUrVrWrXr"r,rYrrrcrr rZrr3r6rrr rr)r-rr rRrrrrr`s:  9     r`))rXabcrrtypingrrrrrr langchain_core._apir langchain_core.callbacksr r langchain_core.documentsr langchain_core.promptsrrlangchain_core.runnables.configrlangchain_core.runnables.utilsrlangchain_text_splittersrrpydanticrrlangchain.chains.baserDEFAULT_DOCUMENT_SEPARATOR DOCUMENTS_KEY from_templateDEFAULT_DOCUMENT_PROMPTr,rr r`rrrrs0