_generate() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 1

Entity Profile

LangChainCore→ LanguageModelBase→ _generate() — langchain Function Reference

Dependency Diagram

graph TD
  907cc29e_96a8_c0ba_194e_95ac0fa628fb["_generate()"]
  19e4be00_71fb_5390_6768_f6e6158f49b4["ChatOllama"]
  907cc29e_96a8_c0ba_194e_95ac0fa628fb -->|defined in| 19e4be00_71fb_5390_6768_f6e6158f49b4
  a9bec111_57fc_1b0b_ba6f_432ebeb29556["_chat_stream_with_aggregation()"]
  907cc29e_96a8_c0ba_194e_95ac0fa628fb -->|calls| a9bec111_57fc_1b0b_ba6f_432ebeb29556
  style 907cc29e_96a8_c0ba_194e_95ac0fa628fb fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/ollama/langchain_ollama/chat_models.py lines 1026–1048

    def _generate(
        self,
        messages: list[BaseMessage],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> ChatResult:
        final_chunk = self._chat_stream_with_aggregation(
            messages, stop, run_manager, verbose=self.verbose, **kwargs
        )
        generation_info = final_chunk.generation_info
        chat_generation = ChatGeneration(
            message=AIMessage(
                content=final_chunk.text,
                usage_metadata=cast(
                    "AIMessageChunk", final_chunk.message
                ).usage_metadata,
                tool_calls=cast("AIMessageChunk", final_chunk.message).tool_calls,
                additional_kwargs=final_chunk.message.additional_kwargs,
            ),
            generation_info=generation_info,
        )
        return ChatResult(generations=[chat_generation])