_chat_stream_with_aggregation() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 1 called by 1

Entity Profile

LangChainCore→ LanguageModelBase→ _chat_stream_with_aggregation() — langchain Function Reference

Dependency Diagram

graph TD
  a9bec111_57fc_1b0b_ba6f_432ebeb29556["_chat_stream_with_aggregation()"]
  19e4be00_71fb_5390_6768_f6e6158f49b4["ChatOllama"]
  a9bec111_57fc_1b0b_ba6f_432ebeb29556 -->|defined in| 19e4be00_71fb_5390_6768_f6e6158f49b4
  907cc29e_96a8_c0ba_194e_95ac0fa628fb["_generate()"]
  907cc29e_96a8_c0ba_194e_95ac0fa628fb -->|calls| a9bec111_57fc_1b0b_ba6f_432ebeb29556
  3b4a8d88_e271_d530_a2cc_d47df386a668["_iterate_over_stream()"]
  a9bec111_57fc_1b0b_ba6f_432ebeb29556 -->|calls| 3b4a8d88_e271_d530_a2cc_d47df386a668
  style a9bec111_57fc_1b0b_ba6f_432ebeb29556 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/ollama/langchain_ollama/chat_models.py lines 959–983

    def _chat_stream_with_aggregation(
        self,
        messages: list[BaseMessage],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        verbose: bool = False,  # noqa: FBT002
        **kwargs: Any,
    ) -> ChatGenerationChunk:
        final_chunk = None
        for chunk in self._iterate_over_stream(messages, stop, **kwargs):
            if final_chunk is None:
                final_chunk = chunk
            else:
                final_chunk += chunk
            if run_manager:
                run_manager.on_llm_new_token(
                    chunk.text,
                    chunk=chunk,
                    verbose=verbose,
                )
        if final_chunk is None:
            msg = "No data received from Ollama stream."
            raise ValueError(msg)

        return final_chunk