format_to_tool_messages() — langchain Function Reference

Architecture documentation for the format_to_tool_messages() function in tools.py from the langchain codebase.

Function python AgentOrchestration ClassicChains calls 1

Entity Profile

AgentOrchestration→ ClassicChains→ format_to_tool_messages() — langchain Function Reference

Dependency Diagram

graph TD
  a9286f07_f4e9_b9c2_3f3a_a1cea3c4479e["format_to_tool_messages()"]
  fe1bd3fc_e601_3b60_c724_5a81dc3b1d29["tools.py"]
  a9286f07_f4e9_b9c2_3f3a_a1cea3c4479e -->|defined in| fe1bd3fc_e601_3b60_c724_5a81dc3b1d29
  beaefb47_cd61_4401_ac33_e9afb4d4b58f["_create_tool_message()"]
  a9286f07_f4e9_b9c2_3f3a_a1cea3c4479e -->|calls| beaefb47_cd61_4401_ac33_e9afb4d4b58f
  style a9286f07_f4e9_b9c2_3f3a_a1cea3c4479e fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/format_scratchpad/tools.py lines 51–73

def format_to_tool_messages(
    intermediate_steps: Sequence[tuple[AgentAction, str]],
) -> list[BaseMessage]:
    """Convert (AgentAction, tool output) tuples into `ToolMessage` objects.

    Args:
        intermediate_steps: Steps the LLM has taken to date, along with observations.

    Returns:
        list of messages to send to the LLM for the next prediction.

    """
    messages = []
    for agent_action, observation in intermediate_steps:
        if isinstance(agent_action, ToolAgentAction):
            new_messages = [
                *list(agent_action.message_log),
                _create_tool_message(agent_action, observation),
            ]
            messages.extend([new for new in new_messages if new not in messages])
        else:
            messages.append(AIMessage(content=agent_action.log))
    return messages