LangChainの文章要約を行うコードを読む (2) - Map Reduce

_load_map_reduce_chain(llm, verbose=verbose, **kwargs)

def _load_map_reduce_chain(
    llm: BaseLanguageModel,
    map_prompt: BasePromptTemplate = map_reduce_prompt.PROMPT,
    combine_prompt: BasePromptTemplate = map_reduce_prompt.PROMPT,
    combine_document_variable_name: str = "text",
    map_reduce_document_variable_name: str = "text",
    collapse_prompt: Optional[BasePromptTemplate] = None,
    reduce_llm: Optional[BaseLanguageModel] = None,
    collapse_llm: Optional[BaseLanguageModel] = None,
    verbose: Optional[bool] = None,
    token_max: int = 3000,
    callbacks: Callbacks = None,
    *,
    collapse_max_retries: Optional[int] = None,
    **kwargs: Any,
) -> MapReduceDocumentsChain:
    map_chain = LLMChain(
        llm=llm,
        prompt=map_prompt,
        verbose=verbose,  # type: ignore[arg-type]
        callbacks=callbacks,  # type: ignore[arg-type]
    )
    _reduce_llm = reduce_llm or llm
    reduce_chain = LLMChain(
        llm=_reduce_llm,
        prompt=combine_prompt,
        verbose=verbose,  # type: ignore[arg-type]
        callbacks=callbacks,  # type: ignore[arg-type]
    )
    # TODO: document prompt
    combine_documents_chain = StuffDocumentsChain(
        llm_chain=reduce_chain,
        document_variable_name=combine_document_variable_name,
        verbose=verbose,  # type: ignore[arg-type]
        callbacks=callbacks,
    )
    if collapse_prompt is None:
        collapse_chain = None
        if collapse_llm is not None:
            raise ValueError(
                "collapse_llm provided, but collapse_prompt was not: please "
                "provide one or stop providing collapse_llm."
            )
    else:
        _collapse_llm = collapse_llm or llm
        collapse_chain = StuffDocumentsChain(
            llm_chain=LLMChain(
                llm=_collapse_llm,
                prompt=collapse_prompt,
                verbose=verbose,  # type: ignore[arg-type]
                callbacks=callbacks,
            ),
            document_variable_name=combine_document_variable_name,
        )
    reduce_documents_chain = ReduceDocumentsChain(
        combine_documents_chain=combine_documents_chain,
        collapse_documents_chain=collapse_chain,
        token_max=token_max,
        verbose=verbose,  # type: ignore[arg-type]
        callbacks=callbacks,
        collapse_max_retries=collapse_max_retries,
    )
    return MapReduceDocumentsChain(
        llm_chain=map_chain,
        reduce_documents_chain=reduce_documents_chain,
        document_variable_name=map_reduce_document_variable_name,
        verbose=verbose,  # type: ignore[arg-type]
        callbacks=callbacks,
        **kwargs,
    )

class ReduceDocumentsChain(BaseCombineDocumentsChain):
    """Combine documents by recursively reducing them.

    This involves

    - combine_documents_chain

    - collapse_documents_chain

    `combine_documents_chain` is ALWAYS provided. This is final chain that is called.
    We pass all previous results to this chain, and the output of this chain is
    returned as a final result.

    `collapse_documents_chain` is used if the documents passed in are too many to all
    be passed to `combine_documents_chain` in one go. In this case,
    `collapse_documents_chain` is called recursively on as big of groups of documents
    as are allowed.

    Example:
        .. code-block:: python

            from langchain.chains import (
                StuffDocumentsChain, LLMChain, ReduceDocumentsChain
            )
            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)
            combine_documents_chain = StuffDocumentsChain(
                llm_chain=llm_chain,
                document_prompt=document_prompt,
                document_variable_name=document_variable_name
            )
            chain = ReduceDocumentsChain(
                combine_documents_chain=combine_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=llm, prompt=prompt)
            collapse_documents_chain = StuffDocumentsChain(
                llm_chain=llm_chain,
                document_prompt=document_prompt,
                document_variable_name=document_variable_name
            )
            chain = ReduceDocumentsChain(
                combine_documents_chain=combine_documents_chain,
                collapse_documents_chain=collapse_documents_chain,
            )
    """

    combine_documents_chain: BaseCombineDocumentsChain
    """Final chain to call to combine documents.
    This is typically a StuffDocumentsChain."""
    collapse_documents_chain: Optional[BaseCombineDocumentsChain] = None
    """Chain to use to collapse documents if needed until they can all fit.
    If None, will use the combine_documents_chain.
    This is typically a StuffDocumentsChain."""
    token_max: int = 3000
    """The maximum number of tokens to group documents into. For example, if
    set to 3000 then documents will be grouped into chunks of no greater than
    3000 tokens before trying to combine them into a smaller chunk."""
    collapse_max_retries: Optional[int] = None
    """The maximum number of retries to collapse documents to fit token_max.
    If None, it will keep trying to collapse documents to fit token_max.
    Otherwise, after it reaches the max number, it will throw an error"""

    ...

    @property
    def _collapse_chain(self) -> BaseCombineDocumentsChain:
        if self.collapse_documents_chain is not None:
            return self.collapse_documents_chain
        else:
            return self.combine_documents_chain

    def combine_docs(
        self,
        docs: List[Document],
        token_max: Optional[int] = None,
        callbacks: Callbacks = None,
        **kwargs: Any,
    ) -> Tuple[str, dict]:
        """Combine multiple documents recursively.

        Args:
            docs: List of documents to combine, assumed that each one is less than
                `token_max`.
            token_max: Recursively creates groups of documents less than this number
                of tokens.
            callbacks: Callbacks to be passed through
            **kwargs: additional parameters to be passed to LLM calls (like other
                input variables besides the documents)

        Returns:
            The first element returned is the single string output. The second
            element returned is a dictionary of other keys to return.
        """
        result_docs, extra_return_dict = self._collapse(
            docs, token_max=token_max, callbacks=callbacks, **kwargs
        )
        return self.combine_documents_chain.combine_docs(
            docs=result_docs, callbacks=callbacks, **kwargs
        )

    def _collapse(
        self,
        docs: List[Document],
        token_max: Optional[int] = None,
        callbacks: Callbacks = None,
        **kwargs: Any,
    ) -> Tuple[List[Document], dict]:
        result_docs = docs
        length_func = self.combine_documents_chain.prompt_length
        num_tokens = length_func(result_docs, **kwargs)

        def _collapse_docs_func(docs: List[Document], **kwargs: Any) -> str:
            return self._collapse_chain.run(
                input_documents=docs, callbacks=callbacks, **kwargs
            )

        _token_max = token_max or self.token_max
        retries: int = 0
        while num_tokens is not None and num_tokens > _token_max:
            new_result_doc_list = split_list_of_docs(
                result_docs, length_func, _token_max, **kwargs
            )
            result_docs = []
            for docs in new_result_doc_list:
                new_doc = collapse_docs(docs, _collapse_docs_func, **kwargs)
                result_docs.append(new_doc)
            num_tokens = length_func(result_docs, **kwargs)
            retries += 1
            if self.collapse_max_retries and retries == self.collapse_max_retries:
                raise ValueError(
                    f"Exceed {self.collapse_max_retries} tries to \
                        collapse document to {_token_max} tokens."
                )
        return result_docs, {}

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:
        .. code-block:: python

            from langchain.chains import (
                StuffDocumentsChain,
                LLMChain,
                ReduceDocumentsChain,
                MapReduceDocumentsChain,
            )
            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)
            # We now define how to combine these summaries
            reduce_prompt = PromptTemplate.from_template(
                "Combine these summaries: {context}"
            )
            reduce_llm_chain = LLMChain(llm=llm, 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=llm, 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."""

    ...
    def combine_docs(
        self,
        docs: List[Document],
        token_max: Optional[int] = None,
        callbacks: Callbacks = None,
        **kwargs: Any,
    ) -> Tuple[str, dict]:
        """Combine documents in a map reduce manner.

        Combine by mapping first chain over all documents, then reducing the results.
        This reducing can be done recursively if needed (if there are many documents).
        """
        map_results = self.llm_chain.apply(
            # FYI - this is parallelized and so it is fast.
            [{self.document_variable_name: d.page_content, **kwargs} for d in docs],
            callbacks=callbacks,
        )
        question_result_key = self.llm_chain.output_key
        result_docs = [
            Document(page_content=r[question_result_key], metadata=docs[i].metadata)
            # This uses metadata from the docs, and the textual results from `results`
            for i, r in enumerate(map_results)
        ]
        result, extra_return_dict = self.reduce_documents_chain.combine_docs(
            result_docs, token_max=token_max, callbacks=callbacks, **kwargs
        )
        if self.return_intermediate_steps:
            intermediate_steps = [r[question_result_key] for r in map_results]
            extra_return_dict["intermediate_steps"] = intermediate_steps
        return result, extra_return_dict