_load_refine_chain() — langchain Function Reference

Architecture documentation for the _load_refine_chain() function in chain.py from the langchain codebase.

Function python AgentOrchestration ClassicChains

Entity Profile

AgentOrchestration→ ClassicChains→ _load_refine_chain() — langchain Function Reference

Dependency Diagram

graph TD
  397d4e62_619b_1e8c_8dce_1572b19dc058["_load_refine_chain()"]
  efa3839a_04cc_4e5d_7ba0_06993a200d6c["chain.py"]
  397d4e62_619b_1e8c_8dce_1572b19dc058 -->|defined in| efa3839a_04cc_4e5d_7ba0_06993a200d6c
  style 397d4e62_619b_1e8c_8dce_1572b19dc058 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/summarize/chain.py lines 172–193

def _load_refine_chain(
    llm: BaseLanguageModel,
    *,
    question_prompt: BasePromptTemplate = refine_prompts.PROMPT,
    refine_prompt: BasePromptTemplate = refine_prompts.REFINE_PROMPT,
    document_variable_name: str = "text",
    initial_response_name: str = "existing_answer",
    refine_llm: BaseLanguageModel | None = None,
    verbose: bool | None = None,
    **kwargs: Any,
) -> RefineDocumentsChain:
    initial_chain = LLMChain(llm=llm, prompt=question_prompt, verbose=verbose)
    _refine_llm = refine_llm or llm
    refine_chain = LLMChain(llm=_refine_llm, prompt=refine_prompt, verbose=verbose)
    return RefineDocumentsChain(
        initial_llm_chain=initial_chain,
        refine_llm_chain=refine_chain,
        document_variable_name=document_variable_name,
        initial_response_name=initial_response_name,
        verbose=verbose,
        **kwargs,
    )