_agenerate() — langchain Function Reference

Architecture documentation for the _agenerate() function in llms.py from the langchain codebase.

Function python LangChainCore LanguageModelBase calls 1

Entity Profile

LangChainCore→ LanguageModelBase→ _agenerate() — langchain Function Reference

Dependency Diagram

graph TD
  4d13dd97_2efb_7876_bd9a_d6f306eb9901["_agenerate()"]
  6220540a_4afa_4d39_cdb6_bb2f4e26fe5f["OllamaLLM"]
  4d13dd97_2efb_7876_bd9a_d6f306eb9901 -->|defined in| 6220540a_4afa_4d39_cdb6_bb2f4e26fe5f
  24323d78_8a9f_dfa5_957d_6cdf837960b0["_astream_with_aggregation()"]
  4d13dd97_2efb_7876_bd9a_d6f306eb9901 -->|calls| 24323d78_8a9f_dfa5_957d_6cdf837960b0
  style 4d13dd97_2efb_7876_bd9a_d6f306eb9901 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/ollama/langchain_ollama/llms.py lines 470–487

    async def _agenerate(
        self,
        prompts: list[str],
        stop: list[str] | None = None,
        run_manager: AsyncCallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> LLMResult:
        generations = []
        for prompt in prompts:
            final_chunk = await self._astream_with_aggregation(
                prompt,
                stop=stop,
                run_manager=run_manager,
                verbose=self.verbose,
                **kwargs,
            )
            generations.append([final_chunk])
        return LLMResult(generations=generations)  # type: ignore[arg-type]