@h8SrSSKJr SSKJrJrJrJr SSKJ r SSK J r SSK J r SSKJr SSKJr "S S \5r"S S \5rSS jrSSjrSSjr\ "SSSS9"SS\55rg)z=Combine many documents together by recursively reducing them.) annotations)AnyCallableOptionalProtocol) deprecated) Callbacks)Document) ConfigDict)BaseCombineDocumentsChainc"\rSrSrSrSSjrSrg)CombineDocsProtocol&Interface for the combine_docs method.c g)rNselfdocskwargss a/var/www/html/shao/venv/lib/python3.13/site-packages/langchain/chains/combine_documents/reduce.py__call__CombineDocsProtocol.__call__srNrlist[Document]rrreturnstr__name__ __module__ __qualname____firstlineno____doc__r__static_attributes__rrrrrs 05rrc"\rSrSrSrSSjrSrg)AsyncCombineDocsProtocolrc # g7f)z,Async interface for the combine_docs method.Nrrs rr!AsyncCombineDocsProtocol.__call__ssrNrrrrrr'r's 0;rr'c /n/nUHYnURU5 U"U40UD6nXr:dM$[U5S:Xa Sn[U5eURUSS5 USSnM[ URU5 U$)aSplit Documents into subsets that each meet a cumulative length constraint. Args: docs: The full list of Documents. length_func: Function for computing the cumulative length of a set of Documents. token_max: The maximum cumulative length of any subset of Documents. **kwargs: Arbitrary additional keyword params to pass to each call of the length_func. Returns: A List[List[Document]]. zLA single document was longer than the context length, we cannot handle this.N)appendlen ValueError) r length_func token_maxrnew_result_doc_list_sub_result_docsdoc _num_tokensmsgs rsplit_list_of_docsr8s$$!"2=f=  "#$).!o%  & &'7'< =/4 /0 rc JU"U40UD6nUSRR5VVs0sHupEU[U5_M nnnUSSHInURR5H(upEXF;aXd==SU3- ss'M[U5Xd'M* MK [X6S9$s snnf)Execute a collapse function on a set of documents and merge their metadatas. Args: docs: A list of Documents to combine. combine_document_func: A function that takes in a list of Documents and optionally addition keyword parameters and combines them into a single string. **kwargs: Arbitrary additional keyword params to pass to the combine_document_func. Returns: A single Document with the output of combine_document_func for the page content and the combined metadata's of all the input documents. All metadata values are strings, and where there are overlapping keys across documents the values are joined by ", ". rr,N,  page_contentmetadatar>itemsrr rcombine_document_funcrresultkvcombined_metadatar5s r collapse_docsrGAs*#4 26 2F/3Aw/?/?/E/E/GH/GtqCF/GHABxLL&&(DA%!$"QC0$'*1v!$ )  DDIsBcf# U"U40UD6IShvN nUSRR5VVs0sHupEU[U5_M nnnUSSHInURR5H(upEXF;aXd==SU3- ss'M[U5Xd'M* MK [X6S9$Ns snnf7f)r:Nrr,r;r<r?rAs racollapse_docsrIas*)88 8F/3Aw/?/?/E/E/GH/GtqCF/GHABxLL&&(DA%!$"QC0$'*1v!$ )  DD9Hs! B1B)$B1B+ AB1+B1z0.3.1z1.0zThis class is deprecated. Please see the migration guide here for a recommended replacement: https://python.langchain.com/docs/versions/migrating_chains/map_reduce_chain/)sinceremovalmessagec\rSrSr%SrS\S'SrS\S'SrS \S 'SrS \S '\ "S SS9r \ SSj5r SSSjjr SSSjjrSSSjjrSSSjjr\ SSj5rSrg)ReduceDocumentsChaina Combine documents by recursively reducing them. This involves - combine_documents_chain - collapse_documents_chain `combine_documents_chain` is ALWAYS provided. This is final chain that is called. We pass all previous results to this chain, and the output of this chain is returned as a final result. `collapse_documents_chain` is used if the documents passed in are too many to all be passed to `combine_documents_chain` in one go. In this case, `collapse_documents_chain` is called recursively on as big of groups of documents as are allowed. Example: .. code-block:: python from langchain.chains import ( StuffDocumentsChain, LLMChain, ReduceDocumentsChain ) from langchain_core.prompts import PromptTemplate from langchain_community.llms import OpenAI # This controls how each document will be formatted. Specifically, # it will be passed to `format_document` - see that function for more # details. document_prompt = PromptTemplate( input_variables=["page_content"], template="{page_content}" ) document_variable_name = "context" llm = OpenAI() # The prompt here should take as an input variable the # `document_variable_name` prompt = PromptTemplate.from_template( "Summarize this content: {context}" ) llm_chain = LLMChain(llm=llm, prompt=prompt) combine_documents_chain = StuffDocumentsChain( llm_chain=llm_chain, document_prompt=document_prompt, document_variable_name=document_variable_name ) chain = ReduceDocumentsChain( combine_documents_chain=combine_documents_chain, ) # If we wanted to, we could also pass in collapse_documents_chain # which is specifically aimed at collapsing documents BEFORE # the final call. prompt = PromptTemplate.from_template( "Collapse this content: {context}" ) llm_chain = LLMChain(llm=llm, prompt=prompt) collapse_documents_chain = StuffDocumentsChain( llm_chain=llm_chain, document_prompt=document_prompt, document_variable_name=document_variable_name ) chain = ReduceDocumentsChain( combine_documents_chain=combine_documents_chain, collapse_documents_chain=collapse_documents_chain, ) r combine_documents_chainNz#Optional[BaseCombineDocumentsChain]collapse_documents_chaini intr2 Optional[int]collapse_max_retriesTforbid)arbitrary_types_allowedextracLURb UR$UR$)N)rQrPrs r_collapse_chain$ReduceDocumentsChain._collapse_chains&  ( ( 400 0+++rc pUR"U4UUS.UD6upVURR"SUUS.UD6$)a%Combine multiple documents recursively. Args: docs: List of documents to combine, assumed that each one is less than `token_max`. token_max: Recursively creates groups of documents less than this number of tokens. callbacks: Callbacks to be passed through **kwargs: additional parameters to be passed to LLM calls (like other input variables besides the documents) Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. r2 callbacksrr^r) _collapserP combine_docsrrr2r^r result_docsextra_return_dicts rra!ReduceDocumentsChain.combine_docss],*. * *  * & ++88    rc# UR"U4UUS.UD6IShvN upVURR"SUUS.UD6IShvN $N-N7f)a+Async combine multiple documents recursively. Args: docs: List of documents to combine, assumed that each one is less than `token_max`. token_max: Recursively creates groups of documents less than this number of tokens. callbacks: Callbacks to be passed through **kwargs: additional parameters to be passed to LLM calls (like other input variables besides the documents) Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. r]Nr_r) _acollapserP acombine_docsrbs rrh"ReduceDocumentsChain.acombine_docs st,04 0 0  0 * & 11??     *  s!AA (AA A Ac ^^UnTRRnU"U40UD6nSUU4SjjnU=(d TRn Sn UbXy:a[UUU 40UD6n U V s/sHn [ X40UD6PM nn U"U40UD6nU S- n TR (a.U TR :XaSTR SU S3n [ U 5eUbXy:aMU04$s sn f)NcB>TRR"SUTS.UD6$N)input_documentsr^r)rZrunrrr^rs r_collapse_docs_func;ReduceDocumentsChain._collapse.._collapse_docs_func8s1''++ $# rrr,Exceed 7 tries to collapse document to  tokens.r)rP prompt_lengthr2r8rGrTr0rrr2r^rrcr1 num_tokensrp _token_maxretriesr3docs_r7s` ` rr`ReduceDocumentsChain._collapse-s 22@@  77   0$.. $)@"4# # 10EeCFC0 %[;F;J qLG((W8Q8Q-Q 9 9:;..8\C o%!$)@"BsCc^^# UnTRRnU"U40UD6nSUU4SjjnU=(d TRn Sn UbXy:a[UUU 40UD6n U V s/sHn [ X40UD6IShvN PM nn U"U40UD6nU S- n TR (a.U TR :XaSTR SU S3n [ U 5eUbXy:aMU04$Nes sn f7f)Nc^># TRR"SUTS.UD6IShvN $N7frl)rZarunros rrp._collapse_docs_func_s>--22 $# s #-+-rr,rrrsrtr)rPrur2r8rIrTr0rvs` ` rrgReduceDocumentsChain._acollapseTs' 22@@  77   0$.. $)@"4# # 10E%UJ6JJJ0 %[;F;J qLG((W8Q8Q-Q 9 9:;..8\C o%!$)@"BKs1AC! C4C 5C=AC!C!CC!cg)Nreduce_documents_chainrrYs r _chain_type ReduceDocumentsChain._chain_type{s'rr)rr )NN) rrr2rSr^r rrrztuple[str, dict]) rrr2rSr^r rrrztuple[list[Document], dict])rr)r r!r"r#r$__annotations__rQr2rTr model_configpropertyrZrarhr`rgrr%rrrrNrNs~AF760DHAH0IsG+/-.J $L ,,$(#    !        J$(#    !        J$(# %%!% %  % % %T$(# %%!% %  % % %N((rrNN) rrr1rr2rRrrrzlist[list[Document]])rrrBrrrrr )rrrBr'rrrr )r$ __future__rtypingrrrrlangchain_core._apirlangchain_core.callbacksr langchain_core.documentsr pydanticr 'langchain.chains.combine_documents.baser rr'r8rGrIrNrrrrsC"44*.-M5(5;x;! !!! !  !HE E.EE E@E E3EE E@   X s(4s(s(r