o JjgO7@sdZddlmZddlmZmZmZmZmZm Z ddl m Z ddl m Z ddlmZddlmZddlmZGd d d eZGd d d eZd&ddZd'ddZd(ddZe dd d!d"Gd#d$d$eZd%S))z=Combine many documents together by recursively reducing them.) annotations)AnyCallableListOptionalProtocolTuple) deprecated) Callbacks)Document) ConfigDict)BaseCombineDocumentsChainc@eZdZdZd dd Zd S) CombineDocsProtocol&Interface for the combine_docs method.docsList[Document]kwargsrreturnstrcKdS)rNselfrrrra/var/www/html/zoom/venv/lib/python3.10/site-packages/langchain/chains/combine_documents/reduce.py__call__szCombineDocsProtocol.__call__Nrrrrrr__name__ __module__ __qualname____doc__rrrrrrrc@r) AsyncCombineDocsProtocolrrrrrrrcsdS)z,Async interface for the combine_docs method.Nrrrrrrsz!AsyncCombineDocsProtocol.__call__Nrrrrrrr#r"r#rr length_funcr token_maxintrrrList[List[Document]]cKstg}g}|D],}||||fi|}||kr2t|dkr#td||dd|dd}q|||S)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)rr$r%rnew_result_doc_list_sub_result_docsdoc _num_tokensrrrsplit_list_of_docss    r1combine_document_funcr cKs||fi|}dd|djD}|ddD]"}|jD]\}}||vr5||d|7<q!t|||<q!qt||dS)Execute a collapse function on a set of documents and merge their metadatas. Args: docs: A list of Documents to combine. combine_document_func: A function that takes in a list of Documents and optionally addition keyword parameters and combines them into a single string. **kwargs: Arbitrary additional keyword params to pass to the combine_document_func. Returns: A single Document with the output of combine_document_func for the page content and the combined metadata's of all the input documents. All metadata values are strings, and where there are overlapping keys across documents the values are joined by ", ". cSi|] \}}|t|qSrr.0kvrrr Sz!collapse_docs..rr(N,  page_contentmetadatar?itemsrr rr2rresultcombined_metadatar/r8r9rrr collapse_docs=s rEcs||fi|IdH}dd|djD}|ddD]"}|jD]\}}||vr9||d|7<q%t|||<q%qt||dS)r3NcSr4rr5r6rrrr:sr;z"acollapse_docs..rr(r<r=r@rBrrracollapse_docs]s rFz0.3.1z1.0zThis class is deprecated. Please see the migration guide here for a recommended replacement: https://python.langchain.com/docs/versions/migrating_chains/map_reduce_chain/)sinceremovalmessagec@seZdZUdZded< dZded< dZded < dZd ed < ed d dZ e d%ddZ  d&d'ddZ  d&d'ddZ  d&d(ddZ  d&d(d d!Ze d)d#d$ZdS)*ReduceDocumentsChainay 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 r&r% Optional[int]collapse_max_retriesTforbid)arbitrary_types_allowedextrarcCs|jdur|jS|jS)N)rLrKrrrr_collapse_chains z$ReduceDocumentsChain._collapse_chainrr callbacksr rrTuple[str, dict]cKs4|j|f||d|\}}|jjd||d|S)aCombine multiple documents recursively. Args: docs: List of documents to combine, assumed that each one is less than `token_max`. token_max: Recursively creates groups of documents less than this number of tokens. callbacks: Callbacks to be passed through **kwargs: additional parameters to be passed to LLM calls (like other input variables besides the documents) Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. r%rTrrTNr) _collapserK combine_docsrrr%rTr result_docsextra_return_dictrrrrYs z!ReduceDocumentsChain.combine_docscsB|j|f||d|IdH\}}|jjd||d|IdHS)aAsync combine multiple documents recursively. Args: docs: List of documents to combine, assumed that each one is less than `token_max`. token_max: Recursively creates groups of documents less than this number of tokens. callbacks: Callbacks to be passed through **kwargs: additional parameters to be passed to LLM calls (like other input variables besides the documents) Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. rVNrWr) _acollapserK acombine_docsrZrrrr^s z"ReduceDocumentsChain.acombine_docsTuple[List[Document], dict]c  s|}jj}||fi|}dfdd }|pj} d } |durl|| krlt||| fi|} g}| D]}t||fi|} || q3||fi|}| d 7} jrd| jkrdtd jd | d |durl|| ks%|ifS)Nrrrrrrcsjjd|d|SN)input_documentsrTr)rSrunrrrTrrr_collapse_docs_func+s z;ReduceDocumentsChain._collapse.._collapse_docs_funcrr(Exceed 7 tries to collapse document to  tokens.r)rK prompt_lengthr%r1rEr*rNr, rrr%rTrr[r$ num_tokensre _token_maxretriesr-new_docrrdrrX s4   zReduceDocumentsChain._collapsec s|}jj}||fi|}dfdd }|pj} d } |durp|| krpt||| fi|} g}| D]}t||fi|IdH} || q4||fi|}| d 7} jrh| jkrhtd jd | d |durp|| ks&|ifS)Nrrrrrrcs jjd|d|IdHSr`)rSarunrcrdrrreNs  z._collapse_docs_funcrr(rfrgrhr)rKrir%r1rFr*rNr,rjrrdrr]Cs6   zReduceDocumentsChain._acollapsercCr)Nreduce_documents_chainrrRrrr _chain_typefsz ReduceDocumentsChain._chain_type)rr )NN) rrr%rMrTr rrrrU) rrr%rMrTr rrrr_)rr)rrr r!__annotations__rLr%rNr model_configpropertyrSrYr^rXr]rqrrrrrJ}s<  C          & #rJN) rrr$rr%r&rrrr')rrr2rrrrr )rrr2r#rrrr )r! __future__rtypingrrrrrrlangchain_core._apir langchain_core.callbacksr langchain_core.documentsr pydanticr 'langchain.chains.combine_documents.baser rr#r1rErFrJrrrrs&