chain_filter.py — langchain Source File

Source Code

"""Filter that uses an LLM to drop documents that aren't relevant to the query."""

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

from langchain_core.callbacks import Callbacks
from langchain_core.documents import BaseDocumentCompressor, Document
from langchain_core.language_models import BaseLanguageModel
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import BasePromptTemplate, PromptTemplate
from langchain_core.runnables import Runnable
from langchain_core.runnables.config import RunnableConfig
from pydantic import ConfigDict

from langchain_classic.chains import LLMChain
from langchain_classic.output_parsers.boolean import BooleanOutputParser
from langchain_classic.retrievers.document_compressors.chain_filter_prompt import (
    prompt_template,
)


def _get_default_chain_prompt() -> PromptTemplate:
    return PromptTemplate(
        template=prompt_template,
        input_variables=["question", "context"],
        output_parser=BooleanOutputParser(),
    )


def default_get_input(query: str, doc: Document) -> dict[str, Any]:
    """Return the compression chain input."""
    return {"question": query, "context": doc.page_content}


class LLMChainFilter(BaseDocumentCompressor):
    """Filter that drops documents that aren't relevant to the query."""

    llm_chain: Runnable
    """LLM wrapper to use for filtering documents.
    The chain prompt is expected to have a BooleanOutputParser."""

    get_input: Callable[[str, Document], dict] = default_get_input
    """Callable for constructing the chain input from the query and a Document."""

    model_config = ConfigDict(
        arbitrary_types_allowed=True,
    )

    def compress_documents(
        self,
        documents: Sequence[Document],
        query: str,
        callbacks: Callbacks | None = None,
    ) -> Sequence[Document]:
        """Filter down documents based on their relevance to the query."""
        filtered_docs = []

        config = RunnableConfig(callbacks=callbacks)
        outputs = zip(
            self.llm_chain.batch(
// ... (76 more lines)