AgentScratchPadChatPromptTemplate Class — langchain Architecture

Architecture documentation for the AgentScratchPadChatPromptTemplate class in schema.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  3b77800e_3db1_de7f_9b6f_e6e8fbe62821["AgentScratchPadChatPromptTemplate"]
  6be4a9a5_5fe4_e64f_c374_e63767576bf6["ChatPromptTemplate"]
  3b77800e_3db1_de7f_9b6f_e6e8fbe62821 -->|extends| 6be4a9a5_5fe4_e64f_c374_e63767576bf6
  c5a5326d_2157_aedd_8829_30e2b51eaa85["schema.py"]
  3b77800e_3db1_de7f_9b6f_e6e8fbe62821 -->|defined in| c5a5326d_2157_aedd_8829_30e2b51eaa85
  75d9b58b_6118_0594_208a_eadaff223189["is_lc_serializable()"]
  3b77800e_3db1_de7f_9b6f_e6e8fbe62821 -->|method| 75d9b58b_6118_0594_208a_eadaff223189
  f6368511_662f_8ce7_f851_59c84e319be5["_construct_agent_scratchpad()"]
  3b77800e_3db1_de7f_9b6f_e6e8fbe62821 -->|method| f6368511_662f_8ce7_f851_59c84e319be5
  45750bb7_a2a7_f029_ac95_0be1565df462["_merge_partial_and_user_variables()"]
  3b77800e_3db1_de7f_9b6f_e6e8fbe62821 -->|method| 45750bb7_a2a7_f029_ac95_0be1565df462

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/schema.py lines 8–37

class AgentScratchPadChatPromptTemplate(ChatPromptTemplate):
    """Chat prompt template for the agent scratchpad."""

    @classmethod
    @override
    def is_lc_serializable(cls) -> bool:
        return False

    def _construct_agent_scratchpad(
        self,
        intermediate_steps: list[tuple[AgentAction, str]],
    ) -> str:
        if len(intermediate_steps) == 0:
            return ""
        thoughts = ""
        for action, observation in intermediate_steps:
            thoughts += action.log
            thoughts += f"\nObservation: {observation}\nThought: "
        return (
            f"This was your previous work "
            f"(but I haven't seen any of it! I only see what "
            f"you return as final answer):\n{thoughts}"
        )

    def _merge_partial_and_user_variables(self, **kwargs: Any) -> dict[str, Any]:
        intermediate_steps = kwargs.pop("intermediate_steps")
        kwargs["agent_scratchpad"] = self._construct_agent_scratchpad(
            intermediate_steps,
        )
        return kwargs