_construct_scratchpad() — langchain Function Reference

Architecture documentation for the _construct_scratchpad() function in base.py from the langchain codebase.

Function python AgentOrchestration ActionLogic

Entity Profile

AgentOrchestration→ ActionLogic→ _construct_scratchpad() — langchain Function Reference

Dependency Diagram

graph TD
  3a5094fa_f1ec_4d12_ae46_7af52ecae3e1["_construct_scratchpad()"]
  37dfdb3a_fc75_8e43_a082_e000915175c2["ConversationalChatAgent"]
  3a5094fa_f1ec_4d12_ae46_7af52ecae3e1 -->|defined in| 37dfdb3a_fc75_8e43_a082_e000915175c2
  style 3a5094fa_f1ec_4d12_ae46_7af52ecae3e1 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/conversational_chat/base.py lines 120–132

    def _construct_scratchpad(
        self,
        intermediate_steps: list[tuple[AgentAction, str]],
    ) -> list[BaseMessage]:
        """Construct the scratchpad that lets the agent continue its thought process."""
        thoughts: list[BaseMessage] = []
        for action, observation in intermediate_steps:
            thoughts.append(AIMessage(content=action.log))
            human_message = HumanMessage(
                content=self.template_tool_response.format(observation=observation),
            )
            thoughts.append(human_message)
        return thoughts