from_llm() — langchain Function Reference

Architecture documentation for the from_llm() function in chain_filter.py from the langchain codebase.

Function python LangChainCore MessageInterface calls 1

Entity Profile

LangChainCore→ MessageInterface→ from_llm() — langchain Function Reference

Dependency Diagram

graph TD
  fabf73af_d79e_d974_a75d_4ae7d496f6fe["from_llm()"]
  c18417f6_2ef7_e19d_e7f5_79027ef3dd22["LLMChainFilter"]
  fabf73af_d79e_d974_a75d_4ae7d496f6fe -->|defined in| c18417f6_2ef7_e19d_e7f5_79027ef3dd22
  3bb64d93_abb2_004b_0389_814a82fbb490["_get_default_chain_prompt()"]
  fabf73af_d79e_d974_a75d_4ae7d496f6fe -->|calls| 3bb64d93_abb2_004b_0389_814a82fbb490
  style fabf73af_d79e_d974_a75d_4ae7d496f6fe fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/retrievers/document_compressors/chain_filter.py lines 113–135

    def from_llm(
        cls,
        llm: BaseLanguageModel,
        prompt: BasePromptTemplate | None = None,
        **kwargs: Any,
    ) -> "LLMChainFilter":
        """Create a LLMChainFilter from a language model.

        Args:
            llm: The language model to use for filtering.
            prompt: The prompt to use for the filter.
            kwargs: Additional arguments to pass to the constructor.

        Returns:
            A LLMChainFilter that uses the given language model.
        """
        _prompt = prompt if prompt is not None else _get_default_chain_prompt()
        if _prompt.output_parser is not None:
            parser = _prompt.output_parser
        else:
            parser = StrOutputParser()
        llm_chain = _prompt | llm | parser
        return cls(llm_chain=llm_chain, **kwargs)