_load_refine_chain() — langchain Function Reference

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

Function python AgentOrchestration ClassicChains

Entity Profile

AgentOrchestration→ ClassicChains→ _load_refine_chain() — langchain Function Reference

Dependency Diagram

graph TD
  34eb332a_78d4_043f_afca_775c1e31ee0c["_load_refine_chain()"]
  bca47bc4_997d_4fc4_b050_2e6593c54792["loading.py"]
  34eb332a_78d4_043f_afca_775c1e31ee0c -->|defined in| bca47bc4_997d_4fc4_b050_2e6593c54792
  style 34eb332a_78d4_043f_afca_775c1e31ee0c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/qa_with_sources/loading.py lines 141–164

def _load_refine_chain(
    llm: BaseLanguageModel,
    *,
    question_prompt: BasePromptTemplate = refine_prompts.DEFAULT_TEXT_QA_PROMPT,
    refine_prompt: BasePromptTemplate = refine_prompts.DEFAULT_REFINE_PROMPT,
    document_prompt: BasePromptTemplate = refine_prompts.EXAMPLE_PROMPT,
    document_variable_name: str = "context_str",
    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,
        document_prompt=document_prompt,
        verbose=verbose,
        **kwargs,
    )