stuff.py — langchain Source File

Source Code

"""Chain that combines documents by stuffing into context."""

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.language_models import LanguageModelLike
from langchain_core.output_parsers import BaseOutputParser, StrOutputParser
from langchain_core.prompts import BasePromptTemplate, format_document
from langchain_core.runnables import Runnable, RunnablePassthrough
from pydantic import ConfigDict, Field, model_validator
from typing_extensions import override

from langchain_classic.chains.combine_documents.base import (
    DEFAULT_DOCUMENT_PROMPT,
    DEFAULT_DOCUMENT_SEPARATOR,
    DOCUMENTS_KEY,
    BaseCombineDocumentsChain,
    _validate_prompt,
)
from langchain_classic.chains.llm import LLMChain


def create_stuff_documents_chain(
    llm: LanguageModelLike,
    prompt: BasePromptTemplate,
    *,
    output_parser: BaseOutputParser | None = None,
    document_prompt: BasePromptTemplate | None = None,
    document_separator: str = DEFAULT_DOCUMENT_SEPARATOR,
    document_variable_name: str = DOCUMENTS_KEY,
) -> Runnable[dict[str, Any], Any]:
    r"""Create 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:
        ```python
        # pip install -U langchain langchain-openai

// ... (232 more lines)