map_reduce.py — langchain Source File

Source Code

"""Combining documents by mapping a chain over them first, then combining results."""

from __future__ import annotations

from typing import Any

from langchain_core._api import deprecated
from langchain_core.callbacks import Callbacks
from langchain_core.documents import Document
from langchain_core.runnables.config import RunnableConfig
from langchain_core.utils.pydantic import create_model
from pydantic import BaseModel, ConfigDict, model_validator
from typing_extensions import override

from langchain_classic.chains.combine_documents.base import BaseCombineDocumentsChain
from langchain_classic.chains.combine_documents.reduce import ReduceDocumentsChain
from langchain_classic.chains.llm import LLMChain


@deprecated(
    since="0.3.1",
    removal="1.0",
    message=(
        "This class is deprecated. Please see the migration guide here for "
        "a recommended replacement: "
        "https://python.langchain.com/docs/versions/migrating_chains/map_reduce_chain/"
    ),
)
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)
// ... (235 more lines)