from_llm() — langchain Function Reference

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

Function python LangChainCore ApiManagement calls 1

Entity Profile

LangChainCore→ ApiManagement→ from_llm() — langchain Function Reference

Dependency Diagram

graph TD
  3ded29e8_4b66_b09b_5821_98f6a1d72ec1["from_llm()"]
  d6c70f63_58ba_abd9_fdbd_d94844756192["LLMChainExtractor"]
  3ded29e8_4b66_b09b_5821_98f6a1d72ec1 -->|defined in| d6c70f63_58ba_abd9_fdbd_d94844756192
  d0fa9aff_4084_869a_579a_5f2349477ea4["_get_default_chain_prompt()"]
  3ded29e8_4b66_b09b_5821_98f6a1d72ec1 -->|calls| d0fa9aff_4084_869a_579a_5f2349477ea4
  style 3ded29e8_4b66_b09b_5821_98f6a1d72ec1 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/retrievers/document_compressors/chain_extract.py lines 111–126

    def from_llm(
        cls,
        llm: BaseLanguageModel,
        prompt: PromptTemplate | None = None,
        get_input: Callable[[str, Document], str] | None = None,
        llm_chain_kwargs: dict | None = None,  # noqa: ARG003
    ) -> LLMChainExtractor:
        """Initialize from LLM."""
        _prompt = prompt if prompt is not None else _get_default_chain_prompt()
        _get_input = get_input if get_input is not None else default_get_input
        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, get_input=_get_input)