tj]$dZddlmZddlmZddlmZddlmZddl m Z ddl m Z m Z ddlmZdd lmZmZmZdd lmZdd lmZddZeddddGddeZdS)zLCombine documents by doing a first pass and then refining on more documents.) annotations)Any) deprecated) Callbacks)Document)BasePromptTemplateformat_documentPromptTemplate) ConfigDictFieldmodel_validator)BaseCombineDocumentsChain)LLMChainreturnr c&tdgdS)N page_contentz{page_content})input_variablestemplater o/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_classic/chains/combine_documents/refine.py_get_default_document_promptrs >*:EU V V VVrz0.3.1z2.0.0zlangchain.agents.create_agentzuBuild new RAG flows with `create_agent` and a retrieval tool. See https://docs.langchain.com/oss/python/langchain/rag)sinceremoval alternativeaddendumcteZdZUdZded< ded< ded< ded< eeZd ed < d Zd ed < e d-fd Z e ddZ e ded.dZe ded.dZ d/d0d"Z d/d0d#Zd1d&Zd2d*Zd3d+Ze d4d,ZxZS)5RefineDocumentsChainaCombine 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: ```python from langchain_classic.chains import RefineDocumentsChain, LLMChain from langchain_core.prompts import PromptTemplate from langchain_openai 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" model = 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=model, 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=model, 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_factoryrdocument_promptFboolreturn_intermediate_stepsr list[str]cHtj}|jrg|d}|S)zExpect input key.intermediate_steps)super output_keysr()self _output_keys __class__s rr-z RefineDocumentsChain.output_keysas3ww*  ) A@\@+?@LrTforbid)arbitrary_types_allowedextrabefore)modevaluesdictrc*d|vr|d|d<|d=|S)zFor backwards compatibility.return_refine_stepsr(r)clsr6s rget_return_intermediate_stepsz2RefineDocumentsChain.get_return_intermediate_stepsns. !F * *289N2OF. /,- rc d|vrd}t||djj}d|vr0t|dkr |d|d<n8d}t||d|vrd|dd|}t||S) z4Get default document variable name, if not provided.r z"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)r:r6msgllm_chain_variabless r"get_default_document_variable_namez7RefineDocumentsChain.get_default_document_variable_namews f , ,6CS// !$%89@P #6 1 1&''1,,3Fq3I/009!oo% , -5H H HQ&1I*JQQ;NQQ S// ! rNdocslist[Document] callbacksrkwargstuple[str, dict]c |j|fi|}|jjdd|i|}|g}|ddD]G}|||}i||}|jjdd|i|}||H|||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. rFr=Nr)_construct_initial_inputsr predict_construct_refine_inputsr!append_construct_result r.rDrFrGinputsres refine_stepsdoc base_inputss r combine_docsz!RefineDocumentsChain.combine_docss$0/????,d$,KKyKFKKu 8 % %C77SAAK. .v.F/$'/NN)NvNNC    $ $ $ $%%lC888rc8K|j|fi|}|jjdd|i|d{V}|g}|ddD]M}|||}i||}|jjdd|i|d{V}||N|||S)aCombine 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. rFNr=r)rJr apredictrLr!rMrNrOs r acombine_docsz"RefineDocumentsChain.acombine_docss$0/????3D*3RRiR6RRRRRRRRu 8 % %C77SAAK. .v.F6-6UUUfUUUUUUUUC    $ $ $ $%%lC888rrRrQc&|jrd|i}ni}||fS)Nr+)r()r.rRrQextra_return_dicts rrNz&RefineDocumentsChain._construct_results-  ) #!5| D   " %%%rrSrdict[str, Any]cH|jt||j|j|iSN)r#r r&r$)r.rSrQs rrLz-RefineDocumentsChain._construct_refine_inputss)  'd>R)S)S  &  rc d|dji|djfd|jjD}|j|jjdi|i}i||S)Nrrc"i|] }|| Srr).0k base_infos r zBRefineDocumentsChain._construct_initial_inputs..sWWWQIaLWWWrr)rupdatemetadatar&rr#format)r.rDrG document_inforTrbs @rrJz.RefineDocumentsChain._construct_initial_inputss $T!W%9: a)***WWWW$2F2VWWW  ')D)=)D)U)U})U)U )+(((rcdS)Nrefine_documents_chainr)r.s r _chain_typez RefineDocumentsChain._chain_types''r)rr))r6r7rrr])rDrErFrrGrrrH)rRr)rQr"rrH)rSrrQr"rr[)rDrErGrrr[)rr")__name__ __module__ __qualname____doc____annotations__r rr&r(propertyr-r model_configr classmethodr;rCrUrXrNrLrJrj __classcell__)r0s@rrrs--^ /)QL*/%4+++OS&+++++? X: $L _(###[$#_(###[$#6 $99999> $999998&&&&    ) ) ) )(((X(((((rrN)rr )rn __future__rtypingrlangchain_core._apirlangchain_core.callbacksrlangchain_core.documentsrlangchain_core.promptsrr langchain_core.prompts.promptr pydanticr r r/langchain_classic.chains.combine_documents.baserlangchain_classic.chains.llmrrrrrrr~sdRR""""""******......------FFFFFFFF8888887777777777211111WWWW   / > D(D(D(D(D(4D(D(D(D(D(r