prep_prompts() — langchain Function Reference

Architecture documentation for the prep_prompts() function in llm.py from the langchain codebase.

Function python AgentOrchestration ClassicChains called by 1

Entity Profile

AgentOrchestration→ ClassicChains→ prep_prompts() — langchain Function Reference

Dependency Diagram

graph TD
  ac9c4aef_a496_a26f_96a9_e9cc5be4c22d["prep_prompts()"]
  ccf50fe1_4990_cf19_1e2d_25efe83f53c5["LLMChain"]
  ac9c4aef_a496_a26f_96a9_e9cc5be4c22d -->|defined in| ccf50fe1_4990_cf19_1e2d_25efe83f53c5
  377cb47d_aeea_738a_00c1_527af33d920e["generate()"]
  377cb47d_aeea_738a_00c1_527af33d920e -->|calls| ac9c4aef_a496_a26f_96a9_e9cc5be4c22d
  style ac9c4aef_a496_a26f_96a9_e9cc5be4c22d fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/llm.py lines 174–197

    def prep_prompts(
        self,
        input_list: list[dict[str, Any]],
        run_manager: CallbackManagerForChainRun | None = None,
    ) -> tuple[list[PromptValue], list[str] | None]:
        """Prepare prompts from inputs."""
        stop = None
        if len(input_list) == 0:
            return [], stop
        if "stop" in input_list[0]:
            stop = input_list[0]["stop"]
        prompts = []
        for inputs in input_list:
            selected_inputs = {k: inputs[k] for k in self.prompt.input_variables}
            prompt = self.prompt.format_prompt(**selected_inputs)
            _colored_text = get_colored_text(prompt.to_string(), "green")
            _text = "Prompt after formatting:\n" + _colored_text
            if run_manager:
                run_manager.on_text(_text, end="\n", verbose=self.verbose)
            if "stop" in inputs and inputs["stop"] != stop:
                msg = "If `stop` is present in any inputs, should be present in all."
                raise ValueError(msg)
            prompts.append(prompt)
        return prompts, stop