_create_chat_result() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase calls 1 called by 2

Entity Profile

LangChainCore→ LanguageModelBase→ _create_chat_result() — langchain Function Reference

Dependency Diagram

graph TD
  65387b9f_2b3b_0088_ea1b_1b80c0d70ec0["_create_chat_result()"]
  8cf0d6c0_abf8_3ee2_fd00_8bfc8c02058a["ChatHuggingFace"]
  65387b9f_2b3b_0088_ea1b_1b80c0d70ec0 -->|defined in| 8cf0d6c0_abf8_3ee2_fd00_8bfc8c02058a
  0e798408_eb45_2a4b_1ddb_579fdb006f07["_generate()"]
  0e798408_eb45_2a4b_1ddb_579fdb006f07 -->|calls| 65387b9f_2b3b_0088_ea1b_1b80c0d70ec0
  f159f0cd_7dad_a4c8_5648_66f72caa1ece["_agenerate()"]
  f159f0cd_7dad_a4c8_5648_66f72caa1ece -->|calls| 65387b9f_2b3b_0088_ea1b_1b80c0d70ec0
  917b18be_e70d_9247_df2c_672c2650d845["_convert_dict_to_message()"]
  65387b9f_2b3b_0088_ea1b_1b80c0d70ec0 -->|calls| 917b18be_e70d_9247_df2c_672c2650d845
  style 65387b9f_2b3b_0088_ea1b_1b80c0d70ec0 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/huggingface/langchain_huggingface/chat_models/huggingface.py lines 697–721

    def _create_chat_result(self, response: dict) -> ChatResult:
        generations = []
        token_usage = response.get("usage", {})
        for res in response["choices"]:
            message = _convert_dict_to_message(res["message"])
            if token_usage and isinstance(message, AIMessage):
                message.usage_metadata = {
                    "input_tokens": token_usage.get("prompt_tokens", 0),
                    "output_tokens": token_usage.get("completion_tokens", 0),
                    "total_tokens": token_usage.get("total_tokens", 0),
                }
            generation_info = {"finish_reason": res.get("finish_reason")}
            if "logprobs" in res:
                generation_info["logprobs"] = res["logprobs"]
            gen = ChatGeneration(
                message=message,
                generation_info=generation_info,
            )
            generations.append(gen)
        llm_output = {
            "token_usage": token_usage,
            "model_name": self.model_id,
            "system_fingerprint": response.get("system_fingerprint", ""),
        }
        return ChatResult(generations=generations, llm_output=llm_output)