_call() — langchain Function Reference

Architecture documentation for the _call() function in llms.py from the langchain codebase.

Function python LangChainCore LanguageModelBase calls 3

Entity Profile

LangChainCore→ LanguageModelBase→ _call() — langchain Function Reference

Dependency Diagram

graph TD
  e1e4f815_3e2a_75f8_675e_9a5e7f0f868a["_call()"]
  c95a497f_938f_2be9_842e_087a0766cf00["AnthropicLLM"]
  e1e4f815_3e2a_75f8_675e_9a5e7f0f868a -->|defined in| c95a497f_938f_2be9_842e_087a0766cf00
  cb1cae7d_4a5d_cfbf_994a_88075fe175e2["_stream()"]
  e1e4f815_3e2a_75f8_675e_9a5e7f0f868a -->|calls| cb1cae7d_4a5d_cfbf_994a_88075fe175e2
  5b0cfa0b_130d_960a_411e_cc97a2c28a93["_get_anthropic_stop()"]
  e1e4f815_3e2a_75f8_675e_9a5e7f0f868a -->|calls| 5b0cfa0b_130d_960a_411e_cc97a2c28a93
  04edfbcc_f913_d95a_6261_c2a81f9f570e["_format_messages()"]
  e1e4f815_3e2a_75f8_675e_9a5e7f0f868a -->|calls| 04edfbcc_f913_d95a_6261_c2a81f9f570e
  style e1e4f815_3e2a_75f8_675e_9a5e7f0f868a fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/langchain_anthropic/llms.py lines 249–296

    def _call(
        self,
        prompt: str,
        stop: list[str] | None = None,
        run_manager: CallbackManagerForLLMRun | None = None,
        **kwargs: Any,
    ) -> str:
        r"""Call out to Anthropic's completion endpoint.

        Args:
            prompt: The prompt to pass into the model.
            stop: Optional list of stop words to use when generating.
            run_manager: Optional callback manager for LLM run.
            kwargs: Additional keyword arguments to pass to the model.

        Returns:
            The string generated by the model.

        Example:
            ```python
            prompt = "What are the biggest risks facing humanity?"
            prompt = f"\n\nHuman: {prompt}\n\nAssistant:"
            response = model.invoke(prompt)
            ```
        """
        if self.streaming:
            completion = ""
            for chunk in self._stream(
                prompt=prompt,
                stop=stop,
                run_manager=run_manager,
                **kwargs,
            ):
                completion += chunk.text
            return completion

        stop = self._get_anthropic_stop(stop)
        params = {**self._default_params, **kwargs}

        # Remove parameters not supported by Messages API
        params = {k: v for k, v in params.items() if k != "max_tokens_to_sample"}

        response = self.client.messages.create(
            messages=self._format_messages(prompt),
            stop_sequences=stop if stop else None,
            **params,
        )
        return response.content[0].text