3fi;->dZddlmZddlmZddlmZddlmZddl m Z ddl m Z m Z ddlmZmZdd lmZmZdd lmZmZmZdd lmZdd lmZmZmZmZmZdd l m!Z!ddeedde dede dzdedzde"de"dee#e"efeffdZ$edddGddeZ%y)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||xst|xs t}dtdtffd }t j di|ijd|z|z|zjdS)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}) ``` inputsrc>jfd|DS)Nc36K|]}t|ywN)r ).0doc_document_prompts n/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_classic/chains/combine_documents/stuff.py zDcreate_stuff_documents_chain..format_docs..Ys!'  C!1 2' s)join)r r&rrs r' format_docsz1create_stuff_documents_chain..format_docsXs)!&&' 45'   format_inputs)run_namestuff_documents_chain)rrr dictstrr assign with_config) rrrrrr_output_parserr*r&s `` @r'create_stuff_documents_chainr5svV34&A*A"7o&7N D S  ""K&zStuffDocumentsChain.s 7r+)default_factoryrrz rTforbid)arbitrary_types_allowedextrabefore)modevaluesrc|djj}d|vr%t|dk(r |d|d<|Sd}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)clsrDllm_chain_variablesmsgs r'"get_default_document_variable_namez6StuffDocumentsChain.get_default_document_variable_names%[188HH #6 1&'1,3Fq3I/0 3!o% , -5H H)&1I*J)KL;;N:OQ S/ ! r+c|jjDcgc]}||jk7s|}}t||zScc}wr#)r; input_keysrsuper)selfk extra_keys __class__s r'rOzStuffDocumentsChain.input_keyssM~~00 A9T9T4TA  w!J.. s AAdocskwargsc <|Dcgc]}t||j}}|jDcic]*\}}||jjj vr||,}}}|j j|||j<|Scc}wcc}}w)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 ) r ritemsr;rrGrr)r)rQrUrVr% doc_stringsrRvr s r' _get_inputszStuffDocumentsChain._get_inputss NRRcsD,@,@AR R  1DNN))999 qD  /3.E.E.J.J;.Wt**+ S s B/BNc |j|fi|}|jjjdi|}|jj |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/)r[r;rformat_get_num_tokens)rQrUrVr rs r' prompt_lengthz!StuffDocumentsChain.prompt_lengthsO "!!$1&1-&&--77~~--f55r+ callbacksc h|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. r`r/)r[r;predictrQrUr`rVr s r' combine_docsz StuffDocumentsChain.combine_docss?""!!$1&1%t~~%%D DVDbHHr+cK|j|fi|}|jjdd|i|d{ifS7w)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. r`Nr/)r[r;apredictrcs r' acombine_docsz!StuffDocumentsChain.acombine_docs sI""!!$1&1,T^^,,KyKFKKROOKs5A>Acy)Nr.r/)rQs r' _chain_typezStuffDocumentsChain._chain_type!s&r+r#) __name__ __module__ __qualname____doc__r__annotations__rrr r1rr model_configr classmethodr0rrMpropertyrlistrOrr[intr_rtuplerdrgri __classcell__)rTs@r'r:r:hs D$*/7+O'SI$$? $L (#$2 /DI// X#$46$x.6C6C$J6. $I8nII I sDy  I0 $P8nPP P sDy  P*'S''r+r:)&rmtypingrlangchain_core._apirlangchain_core.callbacksrlangchain_core.documentsrlangchain_core.language_modelsrlangchain_core.output_parsersrr langchain_core.promptsr r langchain_core.runnablesr r pydanticrrrtyping_extensionsr/langchain_classic.chains.combine_documents.baserrrrrlangchain_classic.chains.llmrr1r0r5r:r/r+r'rs=*.-<KFB77&2.2158"/L4 L4 L4$d* L4 ($. L4  L4 L4d38nc!"L4^   X r'3r'r'r+