_stream() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase called by 2

Entity Profile

LangChainCore→ LanguageModelBase→ _stream() — langchain Function Reference

Dependency Diagram

graph TD
  512ea4c4_540d_4115_afbf_5f3b5fca19ec["_stream()"]
  48aa29b8_65e7_522f_a445_a441eeb6baff["BaseChatModel"]
  512ea4c4_540d_4115_afbf_5f3b5fca19ec -->|defined in| 48aa29b8_65e7_522f_a445_a441eeb6baff
  2c835c4d_6d4b_1dc6_028c_27710e69a32a["stream()"]
  2c835c4d_6d4b_1dc6_028c_27710e69a32a -->|calls| 512ea4c4_540d_4115_afbf_5f3b5fca19ec
  7f734836_7715_c31c_80ea_e14410d37d70["_generate_with_cache()"]
  7f734836_7715_c31c_80ea_e14410d37d70 -->|calls| 512ea4c4_540d_4115_afbf_5f3b5fca19ec
  style 512ea4c4_540d_4115_afbf_5f3b5fca19ec fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/language_models/chat_models.py lines 1435–1453

    def _stream(
        self,
        messages: list[BaseMessage],
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> Iterator[ChatGenerationChunk]:
        """Stream the output of the model.

        Args:
            messages: The messages to generate from.
            stop: Optional list of stop words to use when generating.
            run_manager: Optional callback manager to use for this call.
            **kwargs: Additional keyword arguments to pass to the model.

        Yields:
            The chat generation chunks.
        """
        raise NotImplementedError