a ~g$@sdZddlmZddlmZmZmZmZddlm Z ddl m Z ddl m Z ddlmZmZddlmZdd lmZmZmZdd lmZdd lmZd d ddZe ddddGdddeZdS)zLCombine documents by doing a first pass and then refining on more documents.) annotations)AnyDictListTuple) deprecated) Callbacks)Document)BasePromptTemplateformat_documentPromptTemplate) ConfigDictFieldmodel_validator)BaseCombineDocumentsChain)LLMChainr returncCstdgddS)N page_contentz{page_content})input_variablestemplater rrn/var/www/html/emsaiapi.evdpl.com/venv/lib/python3.9/site-packages/langchain/chains/combine_documents/refine.py_get_default_document_promptsrz0.3.1z1.0zThis class is deprecated. Please see the migration guide here for a recommended replacement: https://python.langchain.com/docs/versions/migrating_chains/refine_docs_chain/)sinceremovalmessagecs&eZdZUdZded<ded<ded<ded<eedZd ed <d Zd ed <e ddfdd Z e dddZ e ddedddddZe ddedddddZd4dd dd!d"d#d$Zd5dd dd!d"d%d&Zddd!d'd(d)Zd*dd+d,d-d.Zddd+d/d0d1Ze ddd2d3ZZS)6RefineDocumentsChaina& Combine documents by doing a first pass and then refining on more documents. This algorithm first calls `initial_llm_chain` on the first document, passing that first document in with the variable name `document_variable_name`, and produces a new variable with the variable name `initial_response_name`. Then, it loops over every remaining document. This is called the "refine" step. It calls `refine_llm_chain`, passing in that document with the variable name `document_variable_name` as well as the previous response with the variable name `initial_response_name`. Example: .. code-block:: python from langchain.chains import RefineDocumentsChain, LLMChain 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}" ) initial_llm_chain = LLMChain(llm=llm, prompt=prompt) initial_response_name = "prev_response" # The prompt here should take as an input variable the # `document_variable_name` as well as `initial_response_name` prompt_refine = PromptTemplate.from_template( "Here's your first summary: {prev_response}. " "Now add to it based on the following context: {context}" ) refine_llm_chain = LLMChain(llm=llm, prompt=prompt_refine) chain = RefineDocumentsChain( initial_llm_chain=initial_llm_chain, refine_llm_chain=refine_llm_chain, document_prompt=document_prompt, document_variable_name=document_variable_name, initial_response_name=initial_response_name, ) rinitial_llm_chainrefine_llm_chainstrdocument_variable_nameinitial_response_name)default_factoryr document_promptFboolreturn_intermediate_stepsz List[str]rcstj}|jr|dg}|S)z2Expect input key. :meta private: intermediate_steps)super output_keysr')self _output_keys __class__rrr*ds z RefineDocumentsChain.output_keysTforbid)arbitrary_types_allowedextrabefore)moderr)valuesrcCsd|vr|d|d<|d=|S)zFor backwards compatibility.Zreturn_refine_stepsr'r)clsr4rrrget_return_intermediate_stepsts z2RefineDocumentsChain.get_return_intermediate_stepscCspd|vrtd|djj}d|vrHt|dkr>|d|d<qltdn$|d|vrltd|dd||S) z4Get default document variable name, if not provided.rz"initial_llm_chain must be providedr"rzWdocument_variable_name must be provided if there are multiple llm_chain input_variableszdocument_variable_name z- was not found in llm_chain input_variables: ) ValueErrorpromptrlen)r5r4llm_chain_variablesrrr"get_default_document_variable_name}s     z7RefineDocumentsChain.get_default_document_variable_nameNzList[Document]rzTuple[str, dict])docs callbackskwargsrc Ks|j|fi|}|jjfd|i|}|g}|ddD]<}|||}i||}|jjfd|i|}||q:|||S)aCombine by mapping first chain over all, then stuffing into final chain. Args: docs: List of documents to combine 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>r7N)_construct_initial_inputsrpredict_construct_refine_inputsr append_construct_result r+r=r>r?inputsres refine_stepsdoc base_inputsrrr combine_docss   z!RefineDocumentsChain.combine_docsc s|j|fi|}|jjfd|i|IdH}|g}|ddD]B}|||}i||}|jjfd|i|IdH}||q@|||S)aAsync combine by mapping a first chain over all, then stuffing into a final chain. Args: docs: List of documents to combine 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>Nr7)r@rapredictrBr rCrDrErrr acombine_docss   z"RefineDocumentsChain.acombine_docs)rHrGrcCs|jrd|i}ni}||fS)Nr()r')r+rHrGextra_return_dictrrrrDs z&RefineDocumentsChain._construct_resultr zDict[str, Any])rIrGrcCs|jt||j|j|iS)N)r"r r%r#)r+rIrGrrrrBsz-RefineDocumentsChain._construct_refine_inputs)r=r?rc s\d|dji|djfdd|jjD}|j|jjfi|i}i||}|S)Nrrcsi|]}||qSrr).0k base_inforr zBRefineDocumentsChain._construct_initial_inputs..)rupdatemetadatar%rr"format)r+r=r?Z document_inforJrFrrQrr@s z.RefineDocumentsChain._construct_initial_inputscCsdS)Nrefine_documents_chainr)r+rrr _chain_typesz RefineDocumentsChain._chain_type)N)N)__name__ __module__ __qualname____doc____annotations__rrr%r'propertyr*r model_configr classmethodr6r<rKrMrDrBr@rY __classcell__rrr-rrs< 2   rN)r] __future__rtypingrrrrlangchain_core._apirlangchain_core.callbacksrlangchain_core.documentsr langchain_core.promptsr r langchain_core.prompts.promptr pydanticrrr'langchain.chains.combine_documents.baserlangchain.chains.llmrrrrrrrs"