_generate() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 1

Entity Profile

LangChainCore→ LanguageModelBase→ _generate() — langchain Function Reference

Dependency Diagram

graph TD
  ba978ac5_9b81_aa68_4fc3_ce3b4b3d5bba["_generate()"]
  6220540a_4afa_4d39_cdb6_bb2f4e26fe5f["OllamaLLM"]
  ba978ac5_9b81_aa68_4fc3_ce3b4b3d5bba -->|defined in| 6220540a_4afa_4d39_cdb6_bb2f4e26fe5f
  485962b7_8158_7fa1_e16f_5af052f86e09["_stream_with_aggregation()"]
  ba978ac5_9b81_aa68_4fc3_ce3b4b3d5bba -->|calls| 485962b7_8158_7fa1_e16f_5af052f86e09
  style ba978ac5_9b81_aa68_4fc3_ce3b4b3d5bba fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/ollama/langchain_ollama/llms.py lines 451–468

    def _generate(
        self,
        prompts: list[str],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> LLMResult:
        generations = []
        for prompt in prompts:
            final_chunk = self._stream_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]