map_rerank.py — langchain Source File

Source Code

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

from __future__ import annotations

from collections.abc import Sequence
from typing import Any, cast

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 Self, override

from langchain_classic.chains.combine_documents.base import BaseCombineDocumentsChain
from langchain_classic.chains.llm import LLMChain
from langchain_classic.output_parsers.regex import RegexParser


@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_rerank_docs_chain/"
    ),
)
class MapRerankDocumentsChain(BaseCombineDocumentsChain):
    r"""Combining documents by mapping a chain over them, then reranking results.

    This algorithm calls an LLMChain on each input document. The LLMChain is expected
    to have an OutputParser that parses the result into both an answer (`answer_key`)
    and a score (`rank_key`). The answer with the highest score is then returned.

    Example:
        ```python
        from langchain_classic.chains import MapRerankDocumentsChain, LLMChain
        from langchain_core.prompts import PromptTemplate
        from langchain_openai import OpenAI
        from langchain_classic.output_parsers.regex import RegexParser

        document_variable_name = "context"
        model = OpenAI()
        # The prompt here should take as an input variable the
        # `document_variable_name`
        # The actual prompt will need to be a lot more complex, this is just
        # an example.
        prompt_template = (
            "Use the following context to tell me the chemical formula "
            "for water. Output both your answer and a score of how confident "
            "you are. Context: {context}"
        )
        output_parser = RegexParser(
            regex=r"(.*?)\nScore: (.*)",
            output_keys=["answer", "score"],
        )
        prompt = PromptTemplate(
            template=prompt_template,
// ... (186 more lines)