_resolve_model_id() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 4 called by 1

Entity Profile

LangChainCore→ LanguageModelBase→ _resolve_model_id() — langchain Function Reference

Dependency Diagram

graph TD
  22e01022_d885_0ce1_205d_61a25556c8f8["_resolve_model_id()"]
  8cf0d6c0_abf8_3ee2_fd00_8bfc8c02058a["ChatHuggingFace"]
  22e01022_d885_0ce1_205d_61a25556c8f8 -->|defined in| 8cf0d6c0_abf8_3ee2_fd00_8bfc8c02058a
  8ac960fc_fbc0_6865_20cb_72e7b4885586["__init__()"]
  8ac960fc_fbc0_6865_20cb_72e7b4885586 -->|calls| 22e01022_d885_0ce1_205d_61a25556c8f8
  2230a40c_6f71_52d5_fb7c_c75e81b6a18e["_is_huggingface_hub()"]
  22e01022_d885_0ce1_205d_61a25556c8f8 -->|calls| 2230a40c_6f71_52d5_fb7c_c75e81b6a18e
  e8659305_1c54_8f00_e4ea_e2e11763c89f["_is_huggingface_textgen_inference()"]
  22e01022_d885_0ce1_205d_61a25556c8f8 -->|calls| e8659305_1c54_8f00_e4ea_e2e11763c89f
  2d69e762_e417_3944_d08b_9ec4de6e3bbe["_is_huggingface_pipeline()"]
  22e01022_d885_0ce1_205d_61a25556c8f8 -->|calls| 2d69e762_e417_3944_d08b_9ec4de6e3bbe
  2b662de8_c3da_0d48_1bc1_b88b1d6c6022["_is_huggingface_endpoint()"]
  22e01022_d885_0ce1_205d_61a25556c8f8 -->|calls| 2b662de8_c3da_0d48_1bc1_b88b1d6c6022
  style 22e01022_d885_0ce1_205d_61a25556c8f8 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py lines 994–1030

    def _resolve_model_id(self) -> None:
        """Resolve the model_id from the LLM's inference_server_url."""
        from huggingface_hub import list_inference_endpoints  # type: ignore[import]

        if _is_huggingface_hub(self.llm) or (
            hasattr(self.llm, "repo_id") and self.llm.repo_id
        ):
            self.model_id = self.llm.repo_id
            return
        if _is_huggingface_textgen_inference(self.llm):
            endpoint_url: str | None = self.llm.inference_server_url
        if _is_huggingface_pipeline(self.llm):
            from transformers import AutoTokenizer  # type: ignore[import]

            self.model_id = self.model_id or self.llm.model_id
            self.tokenizer = (
                AutoTokenizer.from_pretrained(self.model_id)
                if self.tokenizer is None
                else self.tokenizer
            )
            return
        if _is_huggingface_endpoint(self.llm):
            self.model_id = self.llm.repo_id or self.llm.model
            return
        endpoint_url = self.llm.endpoint_url
        available_endpoints = list_inference_endpoints("*")
        for endpoint in available_endpoints:
            if endpoint.url == endpoint_url:
                self.model_id = endpoint.repository

        if not self.model_id:
            msg = (
                "Failed to resolve model_id:"
                f"Could not find model id for inference server: {endpoint_url}"
                "Make sure that your Hugging Face token has access to the endpoint."
            )
            raise ValueError(msg)