_call() — langchain Function Reference

Architecture documentation for the _call() function in base.py from the langchain codebase.

Function python AgentOrchestration ClassicChains

Entity Profile

AgentOrchestration→ ClassicChains→ _call() — langchain Function Reference

Dependency Diagram

graph TD
  90aa30a1_894c_0c7f_2f26_64e1e1157b85["_call()"]
  94675137_e239_b0ed_4295_d86f72dadd0c["LLMSummarizationCheckerChain"]
  90aa30a1_894c_0c7f_2f26_64e1e1157b85 -->|defined in| 94675137_e239_b0ed_4295_d86f72dadd0c
  style 90aa30a1_894c_0c7f_2f26_64e1e1157b85 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/llm_summarization_checker/base.py lines 147–177

    def _call(
        self,
        inputs: dict[str, Any],
        run_manager: CallbackManagerForChainRun | None = None,
    ) -> dict[str, str]:
        _run_manager = run_manager or CallbackManagerForChainRun.get_noop_manager()
        all_true = False
        count = 0
        output = None
        original_input = inputs[self.input_key]
        chain_input = original_input
        while not all_true and count < self.max_checks:
            output = self.sequential_chain(
                {"summary": chain_input},
                callbacks=_run_manager.get_child(),
            )
            count += 1

            if output["all_true"].strip() == "True":
                break

            if self.verbose:
                logger.info(output["revised_summary"])

            chain_input = output["revised_summary"]

        if not output:
            msg = "No output from chain"
            raise ValueError(msg)

        return {self.output_key: output["revised_summary"].strip()}