_default_params() — langchain Function Reference

Architecture documentation for the _default_params() function in huggingface.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ _default_params() — langchain Function Reference

Dependency Diagram

graph TD
  fbf2affe_add4_5052_bbc2_6b8713a7073c["_default_params()"]
  8cf0d6c0_abf8_3ee2_fd00_8bfc8c02058a["ChatHuggingFace"]
  fbf2affe_add4_5052_bbc2_6b8713a7073c -->|defined in| 8cf0d6c0_abf8_3ee2_fd00_8bfc8c02058a
  style fbf2affe_add4_5052_bbc2_6b8713a7073c fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py lines 1231–1243

    def _default_params(self) -> dict[str, Any]:
        """Get default parameters for calling Hugging Face Inference Providers API."""
        params = {
            "model": self.model_id,
            "stream": self.streaming,
            "n": self.n,
            "temperature": self.temperature,
            "stop": self.stop,
            **(self.model_kwargs if self.model_kwargs else {}),
        }
        if self.max_tokens is not None:
            params["max_tokens"] = self.max_tokens
        return params