tj-`dZddlmZddlmZddlmZddlmZddl m Z ddl m Z m Z ddlmZmZdd lmZmZdd lmZmZmZdd lmZdd lmZmZmZmZmZdd l m!Z!ddeedde dede dzdedzde"de"dee#e"efeffdZ$eddddGddeZ%dS)z7Chain that combines documents by stuffing into context.)Any) deprecated) Callbacks)Document)LanguageModelLike)BaseOutputParserStrOutputParser)BasePromptTemplateformat_document)RunnableRunnablePassthrough) ConfigDictFieldmodel_validator)override)DEFAULT_DOCUMENT_PROMPTDEFAULT_DOCUMENT_SEPARATOR DOCUMENTS_KEYBaseCombineDocumentsChain_validate_prompt)LLMChainN) output_parserdocument_promptdocument_separatordocument_variable_namellmpromptrrrrreturnct||pt|p t}dtdtffd }t jdi|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"` (override by setting document_variable), 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. document_variable_name: Variable name to use for the formatted documents in the prompt. Defaults to `"context"`. 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: ```python # pip install -U langchain langchain-openai from langchain_openai import ChatOpenAI from langchain_core.documents import Document from langchain_core.prompts import ChatPromptTemplate from langchain_classic.chains.combine_documents import ( create_stuff_documents_chain, ) prompt = ChatPromptTemplate.from_messages( [("system", "What are everyone's favorite colors:\n\n{context}")] ) model = ChatOpenAI(model="gpt-3.5-turbo") chain = create_stuff_documents_chain(model, 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}) ``` inputsrcRfd|DS)Nc38K|]}t|VdSN)r ).0doc_document_prompts n/var/www/html/CA-Chatbot/venv/lib/python3.11/site-packages/langchain_classic/chains/combine_documents/stuff.py zDcreate_stuff_documents_chain..format_docs..YsB' '  C!1 2 2' ' ' ' ' ' )join)r r&rrs r' format_docsz1create_stuff_documents_chain..format_docsXsG!&&' ' ' ' 45' ' '    r) format_inputs)run_namestuff_documents_chain)rrr dictstrr assign with_config) rrrrrr_output_parserr+r&s `` @r'create_stuff_documents_chainr5svV3444&A*A"7o&7&7N D S         "KK&zStuffDocumentsChain.s 7r))default_factoryrrz rTforbid)arbitrary_types_allowedextrabefore)modevaluesrc|djj}d|vr0t|dkr |d|d<n8d}t||d|vrd|dd|}t||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. r<rrzQdocument_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)clsrEllm_chain_variablesmsgs r'"get_default_document_variable_namez6StuffDocumentsChain.get_default_document_variable_names%[18H #6 1 1&''1,,3Fq3I/003!oo% , -5H H HQ&1I*JQQ;NQQ S// ! r)cbfdjjD}tj|zS)Nc*g|]}|jk |Sr/)r)r$kselfs r' z2StuffDocumentsChain.input_keys..s-   A9T4T4TA4T4T4Tr))r< input_keyssuper)rR extra_keys __class__s` r'rTzStuffDocumentsChain.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|jSr/)r r)r$r%rRs r'rSz3StuffDocumentsChain._get_inputs..s&RRRcsD,@AARRRr)cBi|]\}}|jjjv||Sr/)r<rrH)r$rQvrRs r' z3StuffDocumentsChain._get_inputs..s<   1DN)999 q999r))itemsrr*r)rRrXrY doc_stringsr s` r' _get_inputszStuffDocumentsChain._get_inputsst SRRRTRRR          /3.E.J.J;.W.Wt*+ r)Nc |j|fi|}|jjjdi|}|j|S)aReturn 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: a list of documents to use to calculate the total prompt length. **kwargs: additional parameters to use to get inputs to LLMChain. Returns: Returns None if the method does not depend on the prompt length, otherwise the length of the prompt in tokens. r/)rar<rformat_get_num_tokens)rRrXrYr rs r' prompt_lengthz!StuffDocumentsChain.prompt_lengthsQ "!$11&11-&-7777~--f555r) 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. rfr/)rar<predictrRrXrfrYr 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. rfNr/)rar<apredictris r' acombine_docsz!StuffDocumentsChain.acombine_docs sY""!$11&11,T^,KKyKFKKKKKKKKROOr)cdS)Nr.r/)rRs r' _chain_typezStuffDocumentsChain._chain_type!s&&r)r#) __name__ __module__ __qualname____doc__r__annotations__rrr r1rr model_configr classmethodr0rrNpropertyrlistrTrraintrertuplerjrmro __classcell__)rWs@r'r;r;hss  D$*/%77+++O'SI$$$$?: $L _(###[$#2 /DI/////XX/ X#$46$x.6C6C$J6666. $II8nII I sDy  IIII0 $PP8nPP P sDy  PPPP*'S'''X'''''r)r;)&rstypingrlangchain_core._apirlangchain_core.callbacksrlangchain_core.documentsrlangchain_core.language_modelsrlangchain_core.output_parsersrr langchain_core.promptsr r langchain_core.runnablesr r pydanticrrrtyping_extensionsr/langchain_classic.chains.combine_documents.baserrrrrlangchain_classic.chains.llmrr1r0r5r;r/r)r'rs<==******......------<<<<<<KKKKKKKKFFFFFFFFBBBBBBBB7777777777&&&&&&211111.2158"/L4L4L4 L4 L4$d* L4 ($. L4  L4 L4d38nc!"L4L4L4L4^   / > r'r'r'r'r'3r'r'r'r'r'r)