langchain Architecture Docs
Home / Function/ _get_ls_params() — langchain Function Reference

_get_ls_params() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase called by 4

Entity Profile

Dependency Diagram

graph TD
  73e16e99_e480_d8c0_802c_181872401224["_get_ls_params()"]
  48aa29b8_65e7_522f_a445_a441eeb6baff["BaseChatModel"]
  73e16e99_e480_d8c0_802c_181872401224 -->|defined in| 48aa29b8_65e7_522f_a445_a441eeb6baff
  2c835c4d_6d4b_1dc6_028c_27710e69a32a["stream()"]
  2c835c4d_6d4b_1dc6_028c_27710e69a32a -->|calls| 73e16e99_e480_d8c0_802c_181872401224
  9d211053_b2a3_2915_b514_1f332955694a["astream()"]
  9d211053_b2a3_2915_b514_1f332955694a -->|calls| 73e16e99_e480_d8c0_802c_181872401224
  0ef74a8b_6fbe_eae4_e552_b56b1ab32fea["generate()"]
  0ef74a8b_6fbe_eae4_e552_b56b1ab32fea -->|calls| 73e16e99_e480_d8c0_802c_181872401224
  bb15e35a_96ec_beed_4dc7_6fc3602e2d6a["agenerate()"]
  bb15e35a_96ec_beed_4dc7_6fc3602e2d6a -->|calls| 73e16e99_e480_d8c0_802c_181872401224
  style 73e16e99_e480_d8c0_802c_181872401224 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/core/langchain_core/language_models/chat_models.py lines 788–826

    def _get_ls_params(
        self,
        stop: list[str] | None = None,
        **kwargs: Any,
    ) -> LangSmithParams:
        """Get standard params for tracing."""
        # get default provider from class name
        default_provider = self.__class__.__name__
        if default_provider.startswith("Chat"):
            default_provider = default_provider[4:].lower()
        elif default_provider.endswith("Chat"):
            default_provider = default_provider[:-4]
        default_provider = default_provider.lower()

        ls_params = LangSmithParams(ls_provider=default_provider, ls_model_type="chat")
        if stop:
            ls_params["ls_stop"] = stop

        # model
        if "model" in kwargs and isinstance(kwargs["model"], str):
            ls_params["ls_model_name"] = kwargs["model"]
        elif hasattr(self, "model") and isinstance(self.model, str):
            ls_params["ls_model_name"] = self.model
        elif hasattr(self, "model_name") and isinstance(self.model_name, str):
            ls_params["ls_model_name"] = self.model_name

        # temperature
        if "temperature" in kwargs and isinstance(kwargs["temperature"], float):
            ls_params["ls_temperature"] = kwargs["temperature"]
        elif hasattr(self, "temperature") and isinstance(self.temperature, float):
            ls_params["ls_temperature"] = self.temperature

        # max_tokens
        if "max_tokens" in kwargs and isinstance(kwargs["max_tokens"], int):
            ls_params["ls_max_tokens"] = kwargs["max_tokens"]
        elif hasattr(self, "max_tokens") and isinstance(self.max_tokens, int):
            ls_params["ls_max_tokens"] = self.max_tokens

        return ls_params

Domain

Subdomains

Defined In

Called By

Source

Frequently Asked Questions

What does _get_ls_params() do?
_get_ls_params() is a function in the langchain codebase, defined in libs/core/langchain_core/language_models/chat_models.py.
Where is _get_ls_params() defined?
_get_ls_params() is defined in libs/core/langchain_core/language_models/chat_models.py at line 788.
What calls _get_ls_params()?
_get_ls_params() is called by 4 function(s): agenerate, astream, generate, stream.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free