蘺h*4dZddlmZmZmZmZmZddlmZddl m Z ddl m Z m Z ddlmZmZddlmZmZmZddlmZmZdd lmZdd lmZmZmZmZmZdd l m!Z!d d ed de dedee deede"deee"efeff dZ#GddeZ$d S)z7Chain that combines documents by stuffing into context.)AnyDictListOptionalTuple)Document)LanguageModelLike)BaseOutputParserStrOutputParser)BasePromptTemplateformat_document)ExtraFieldroot_validator)RunnableRunnablePassthrough) Callbacks)DEFAULT_DOCUMENT_PROMPTDEFAULT_DOCUMENT_SEPARATOR DOCUMENTS_KEYBaseCombineDocumentsChain_validate_prompt)LLMChainN) output_parserdocument_promptdocument_separatorllmpromptrrrreturnct||pt|p t}dtdtffd }t jdit|id|z|z|zdS)aCreate a chain for passing a list of Documents to a model. Args: llm: Language model. prompt: Prompt template. Must contain input variable "context", which will be used for passing in the formatted documents. output_parser: Output parser. Defaults to StrOutputParser. document_prompt: Prompt used for formatting each document into a string. Input variables can be "page_content" or any metadata keys that are in all documents. "page_content" will automatically retrieve the `Document.page_content`, and all other inputs variables will be automatically retrieved from the `Document.metadata` dictionary. Default to a prompt that only contains `Document.page_content`. document_separator: String separator to use between formatted document strings. Returns: An LCEL Runnable. The input is a dictionary that must have a "context" key that maps to a List[Document], and any other input variables expected in the prompt. The Runnable return type depends on output_parser used. Example: .. code-block:: python # pip install -U langchain langchain-community from langchain_community.chat_models import ChatOpenAI from langchain_core.documents import Document from langchain_core.prompts import ChatPromptTemplate from langchain.chains.combine_documents import create_stuff_documents_chain prompt = ChatPromptTemplate.from_messages( [("system", "What are everyone's favorite colors: {context}")] ) llm = ChatOpenAI(model_name="gpt-3.5-turbo") chain = create_stuff_documents_chain(llm, prompt) docs = [ Document(page_content="Jesse loves red but not yellow"), Document(page_content = "Jamal loves green but not as much as he loves orange") ] chain.invoke({"context": docs}) inputsrc\fd|tDS)Nc38K|]}t|VdSN)r ).0doc_document_prompts p/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/langchain/chains/combine_documents/stuff.py zDcreate_stuff_documents_chain..format_docs..Os?' ' 7:OC!1 2 2' ' ' ' ' ' )joinr)r!r'rs r( format_docsz1create_stuff_documents_chain..format_docsNsF!&&' ' ' ' >D]>S' ' '    r* format_inputs)run_namestuff_documents_chain) rrr dictstrrassignr with_config)rrrrr_output_parserr,r's ` @r(create_stuff_documents_chainr6shV&A*A"7o&7&7N D S       "BBm[%ABBNN$ O           k2k334r*c eZdZUdZeed< edZeed< e ed< dZ e ed< Gd d Z e d d e de fdZedee ffd ZdeededefdZdeededeefdZ ddeedededee effdZ ddeedededee effdZede fdZxZS)StuffDocumentsChaina-Chain that combines documents by stuffing into context. This chain takes a list of documents and first combines them into a single string. It does this by formatting each document into a string with the `document_prompt` and then joining them together with `document_separator`. It then adds that new string to the inputs with the variable name set by `document_variable_name`. Those inputs are then passed to the `llm_chain`. Example: .. code-block:: python from langchain.chains import StuffDocumentsChain, 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}" ) llm_chain = LLMChain(llm=llm, prompt=prompt) chain = StuffDocumentsChain( llm_chain=llm_chain, document_prompt=document_prompt, document_variable_name=document_variable_name ) llm_chainctSr$)rr0r*r(zStuffDocumentsChain.s 7r*)default_factoryrdocument_variable_namez rc$eZdZdZejZdZdS)StuffDocumentsChain.Configz'Configuration for this pydantic object.TN)__name__ __module__ __qualname____doc__rforbidextraarbitrary_types_allowedr0r*r(Configr?s#55 "&r*rGT)prevaluesrc|djj}d|vr.t|dkr |d|d<n4td|d|vrtd|dd||S)zGet default document variable name, if not provided. If only one variable is present in the llm_chain.prompt, we can infer that the formatted documents should be passed in with this variable name. r9r=rzQdocument_variable_name must be provided if there are multiple llm_chain_variableszdocument_variable_name z- was not found in llm_chain input_variables: )rinput_variableslen ValueError)clsrIllm_chain_variabless r("get_default_document_variable_namez6StuffDocumentsChain.get_default_document_variable_names%[18H #6 1 1&''1,,3Fq3I/00 3 ./7JJJ Uf5M.NUU?RUU r*cbfdjjD}tj|zS)Nc*g|]}|jk |Sr0)r=)r%kselfs r( z2StuffDocumentsChain.input_keys..s-   A9T4T4TA4T4T4Tr*)r9 input_keyssuper)rU extra_keys __class__s` r(rWzStuffDocumentsChain.input_keyssE    ~0   ww!J..r*docskwargsc fd|D}fd|D}j||j<|S)aConstruct inputs from kwargs and docs. Format and then join all the documents together into one input with name `self.document_variable_name`. Also pluck any additional variables from **kwargs. Args: docs: List of documents to format and then join into single input **kwargs: additional inputs to chain, will pluck any other required arguments from here. Returns: dictionary of inputs to LLMChain c:g|]}t|jSr0)r r)r%r&rUs r(rVz3StuffDocumentsChain._get_inputs..s&RRRcsD,@AARRRr*cBi|]\}}|jjjv||Sr0)r9rrL)r%rTvrUs r( z3StuffDocumentsChain._get_inputs..s<   1DN)999 q999r*)itemsrr+r=)rUr[r\ doc_stringsr!s` r( _get_inputszStuffDocumentsChain._get_inputsst SRRRTRRR          /3.E.J.J;.W.Wt*+ r*c |j|fi|}|jjjdi|}|j|S)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. r0)rdr9rformat_get_num_tokens)rUr[r\r!rs r( prompt_lengthz!StuffDocumentsChain.prompt_lengthsQ "!$11&11-&-7777~--f555r*N callbacksc J|j|fi|}|jjdd|i|ifS)aStuff all documents into one prompt and pass to LLM. Args: docs: List of documents to join together into one variable callbacks: Optional callbacks to pass along **kwargs: additional parameters to use to get inputs to LLMChain. Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. rir0)rdr9predictrUr[rir\r!s r( combine_docsz StuffDocumentsChain.combine_docssC"!$11&11%t~%DD DVDDbHHr*cZK|j|fi|}|jjdd|i|d{VifS)aAsync stuff all documents into one prompt and pass to LLM. Args: docs: List of documents to join together into one variable callbacks: Optional callbacks to pass along **kwargs: additional parameters to use to get inputs to LLMChain. Returns: The first element returned is the single string output. The second element returned is a dictionary of other keys to return. riNr0)rdr9apredictrls r( acombine_docsz!StuffDocumentsChain.acombine_docssY"!$11&11,T^,KKyKFKKKKKKKKROOr*cdS)Nr/r0)rUs r( _chain_typezStuffDocumentsChain._chain_types&&r*r$)r@rArBrCr__annotations__rrr r2rrGrrrQpropertyrrWrrr1rdrintrhrrrmrprr __classcell__)rZs@r(r8r8]sa##J$*/%77+++O'SI$$$$?'''''''' ^0/DI/////X/ X#$46$x.6C6HSM6666*<@IINI/8IKNI sDy IIII&<@PPNP/8PKNP sDy PPPP$'S'''X'''''r*r8)%rCtypingrrrrrlangchain_core.documentsrlangchain_core.language_modelsr langchain_core.output_parsersr r langchain_core.promptsr r langchain_core.pydantic_v1rrrlangchain_core.runnablesrrlangchain.callbacks.managerr'langchain.chains.combine_documents.baserrrrrlangchain.chains.llmrr2r6r8r0r*r(rs==33333333333333------<<<<<<KKKKKKKKFFFFFFFFCCCCCCCCCCBBBBBBBB111111*)))))15488 D4D4D4 D4 D4,- D4 01 D4  D4d38nc!"D4D4D4D4Nm'm'm'm'm'3m'm'm'm'm'r*