generate() — langchain Function Reference

Architecture documentation for the generate() function in llm.py from the langchain codebase.

Function python AgentOrchestration ClassicChains calls 1 called by 2

Entity Profile

AgentOrchestration→ ClassicChains→ generate() — langchain Function Reference

Dependency Diagram

graph TD
  377cb47d_aeea_738a_00c1_527af33d920e["generate()"]
  ccf50fe1_4990_cf19_1e2d_25efe83f53c5["LLMChain"]
  377cb47d_aeea_738a_00c1_527af33d920e -->|defined in| ccf50fe1_4990_cf19_1e2d_25efe83f53c5
  85bfcf5c_48e7_0dba_6c8e_553c4c40a5ea["_call()"]
  85bfcf5c_48e7_0dba_6c8e_553c4c40a5ea -->|calls| 377cb47d_aeea_738a_00c1_527af33d920e
  be1cf4da_b223_486d_abea_864bf732bbc6["apply()"]
  be1cf4da_b223_486d_abea_864bf732bbc6 -->|calls| 377cb47d_aeea_738a_00c1_527af33d920e
  ac9c4aef_a496_a26f_96a9_e9cc5be4c22d["prep_prompts()"]
  377cb47d_aeea_738a_00c1_527af33d920e -->|calls| ac9c4aef_a496_a26f_96a9_e9cc5be4c22d
  style 377cb47d_aeea_738a_00c1_527af33d920e fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/llm.py lines 120–145

    def generate(
        self,
        input_list: list[dict[str, Any]],
        run_manager: CallbackManagerForChainRun | None = None,
    ) -> LLMResult:
        """Generate LLM result from inputs."""
        prompts, stop = self.prep_prompts(input_list, run_manager=run_manager)
        callbacks = run_manager.get_child() if run_manager else None
        if isinstance(self.llm, BaseLanguageModel):
            return self.llm.generate_prompt(
                prompts,
                stop,
                callbacks=callbacks,
                **self.llm_kwargs,
            )
        results = self.llm.bind(stop=stop, **self.llm_kwargs).batch(
            cast("list", prompts),
            {"callbacks": callbacks},
        )
        generations: list[list[Generation]] = []
        for res in results:
            if isinstance(res, BaseMessage):
                generations.append([ChatGeneration(message=res)])
            else:
                generations.append([Generation(text=res)])
        return LLMResult(generations=generations)