_create_chat_result() — langchain Function Reference

Architecture documentation for the _create_chat_result() function in chat_models.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
  c5fc57f8_7702_2a2f_411d_d1ed1dae6cb1["_create_chat_result()"]
  1a5cd25a_9420_c6b2_ec8d_2b53c6427514["ChatFireworks"]
  c5fc57f8_7702_2a2f_411d_d1ed1dae6cb1 -->|defined in| 1a5cd25a_9420_c6b2_ec8d_2b53c6427514
  12942fee_5eb3_0410_27b1_0d94ecd994a1["_generate()"]
  12942fee_5eb3_0410_27b1_0d94ecd994a1 -->|calls| c5fc57f8_7702_2a2f_411d_d1ed1dae6cb1
  55737e4f_058c_81d8_55a7_4c05e4e31524["_agenerate()"]
  55737e4f_058c_81d8_55a7_4c05e4e31524 -->|calls| c5fc57f8_7702_2a2f_411d_d1ed1dae6cb1
  2d3513e4_e3e4_8c27_2865_6eb2193506c3["_convert_dict_to_message()"]
  c5fc57f8_7702_2a2f_411d_d1ed1dae6cb1 -->|calls| 2d3513e4_e3e4_8c27_2865_6eb2193506c3
  style c5fc57f8_7702_2a2f_411d_d1ed1dae6cb1 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/fireworks/langchain_fireworks/chat_models.py lines 550–577

    def _create_chat_result(self, response: dict | BaseModel) -> ChatResult:
        generations = []
        if not isinstance(response, dict):
            response = response.model_dump()
        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),
                }
                message.response_metadata["model_provider"] = "fireworks"
                message.response_metadata["model_name"] = self.model_name
            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,
            "system_fingerprint": response.get("system_fingerprint", ""),
        }
        return ChatResult(generations=generations, llm_output=llm_output)