MapReduceDocumentsChain Class — langchain Architecture

Source Code

libs/langchain/langchain_classic/chains/combine_documents/map_reduce.py lines 29–294

class MapReduceDocumentsChain(BaseCombineDocumentsChain):
    """Combining documents by mapping a chain over them, then combining results.

    We first call `llm_chain` on each document individually, passing in the
    `page_content` and any other kwargs. This is the `map` step.

    We then process the results of that `map` step in a `reduce` step. This should
    likely be a ReduceDocumentsChain.

    Example:
        ```python
        from langchain_classic.chains import (
            StuffDocumentsChain,
            LLMChain,
            ReduceDocumentsChain,
            MapReduceDocumentsChain,
        )
        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}")
        llm_chain = LLMChain(llm=model, prompt=prompt)
        # We now define how to combine these summaries
        reduce_prompt = PromptTemplate.from_template(
            "Combine these summaries: {context}"
        )
        reduce_llm_chain = LLMChain(llm=model, prompt=reduce_prompt)
        combine_documents_chain = StuffDocumentsChain(
            llm_chain=reduce_llm_chain,
            document_prompt=document_prompt,
            document_variable_name=document_variable_name,
        )
        reduce_documents_chain = ReduceDocumentsChain(
            combine_documents_chain=combine_documents_chain,
        )
        chain = MapReduceDocumentsChain(
            llm_chain=llm_chain,
            reduce_documents_chain=reduce_documents_chain,
        )
        # If we wanted to, we could also pass in collapse_documents_chain
        # which is specifically aimed at collapsing documents BEFORE
        # the final call.
        prompt = PromptTemplate.from_template("Collapse this content: {context}")
        llm_chain = LLMChain(llm=model, prompt=prompt)
        collapse_documents_chain = StuffDocumentsChain(
            llm_chain=llm_chain,
            document_prompt=document_prompt,
            document_variable_name=document_variable_name,
        )
        reduce_documents_chain = ReduceDocumentsChain(
            combine_documents_chain=combine_documents_chain,
            collapse_documents_chain=collapse_documents_chain,
        )
        chain = MapReduceDocumentsChain(
            llm_chain=llm_chain,
            reduce_documents_chain=reduce_documents_chain,
        )
        ```
    """

    llm_chain: LLMChain
    """Chain to apply to each document individually."""
    reduce_documents_chain: BaseCombineDocumentsChain
    """Chain to use to reduce the results of applying `llm_chain` to each doc.
    This typically either a ReduceDocumentChain or StuffDocumentChain."""
    document_variable_name: str
    """The variable name in the llm_chain to put the documents in.
    If only one variable in the llm_chain, this need not be provided."""
    return_intermediate_steps: bool = False
    """Return the results of the map steps in the output."""