_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
  089db75e_7a28_1e2e_04d8_793957a7a281["_load_refine_chain()"]
  7bff8b59_614d_4352_11dd_db15fa7a7056["chain.py"]
  089db75e_7a28_1e2e_04d8_793957a7a281 -->|defined in| 7bff8b59_614d_4352_11dd_db15fa7a7056
  style 089db75e_7a28_1e2e_04d8_793957a7a281 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/question_answering/chain.py lines 186–229

def _load_refine_chain(
    llm: BaseLanguageModel,
    *,
    question_prompt: BasePromptTemplate | None = None,
    refine_prompt: BasePromptTemplate | None = None,
    document_variable_name: str = "context_str",
    initial_response_name: str = "existing_answer",
    refine_llm: BaseLanguageModel | None = None,
    verbose: bool | None = None,
    callback_manager: BaseCallbackManager | None = None,
    callbacks: Callbacks = None,
    **kwargs: Any,
) -> RefineDocumentsChain:
    _question_prompt = (
        question_prompt or refine_prompts.QUESTION_PROMPT_SELECTOR.get_prompt(llm)
    )
    _refine_prompt = refine_prompt or refine_prompts.REFINE_PROMPT_SELECTOR.get_prompt(
        llm,
    )
    initial_chain = LLMChain(
        llm=llm,
        prompt=_question_prompt,
        verbose=verbose,
        callback_manager=callback_manager,
        callbacks=callbacks,
    )
    _refine_llm = refine_llm or llm
    refine_chain = LLMChain(
        llm=_refine_llm,
        prompt=_refine_prompt,
        verbose=verbose,
        callback_manager=callback_manager,
        callbacks=callbacks,
    )
    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,
        callback_manager=callback_manager,
        callbacks=callbacks,
        **kwargs,
    )