hJ-6dZddlmZmZddlmZddlmZddlm Z ddl m Z ddl m Z mZddlmZmZdd lmZmZdd lmZmZmZdd lmZmZmZmZmZdd lm Z d d eedde dedee deede!de!dee"e!efeffdZ#edddGddeZ$y )z7Chain that combines documents by stuffing into context.)AnyOptional) deprecated) Callbacks)Document)LanguageModelLike)BaseOutputParserStrOutputParser)BasePromptTemplateformat_document)RunnableRunnablePassthrough) ConfigDictFieldmodel_validator)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: .. 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:\n\n{context}")] ) llm = ChatOpenAI(model="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>jfd|DS)Nc36K|]}t|ywN)r ).0doc_document_prompts f/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/langchain/chains/combine_documents/stuff.py zDcreate_stuff_documents_chain..format_docs..Ts!'  C!1 2' s)join)r r&rrs r' format_docsz1create_stuff_documents_chain..format_docsSs)!&&' 45'   format_inputs)run_namestuff_documents_chain)rrr dictstrrassign with_config) rrrrrr_output_parserr*r&s `` @r'create_stuff_documents_chainr5snV34&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/Bc |j|fi|}|jjjdi|}|jj |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. 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""!!$1&1,T^^,,KyKFKKROOKs5A>Acy)Nr.r/)rQs r' _chain_typezStuffDocumentsChain._chain_types&r+r#) __name__ __module__ __qualname____doc__r__annotations__rrr r1rr model_configr classmethodr0rrMpropertylistrOrr[rintr_rtuplerdrgri __classcell__)rTs@r'r:r:cs#J$*/7+O'SI$$? $L (#$2/DI// X#$46$x.6C6HSM6. $I8nII I sDy  I0 $P8nPP P sDy  P*'S''r+r:)%rmtypingrrlangchain_core._apirlangchain_core.callbacksrlangchain_core.documentsrlangchain_core.language_modelsrlangchain_core.output_parsersr r langchain_core.promptsr r langchain_core.runnablesr rpydanticrrr'langchain.chains.combine_documents.baserrrrrlangchain.chains.llmrr1r0r5r:r/r+r'rs= *.-<KFB77*15488"/H4 H4 H4,- H4 01 H4  H4 H4d38nc!"H4V   X t'3t't'r+