_amoderate_inputs() — langchain Function Reference

Architecture documentation for the _amoderate_inputs() function in openai_moderation.py from the langchain codebase.

Function python LangChainCore ApiManagement calls 2 called by 1

Entity Profile

LangChainCore→ ApiManagement→ _amoderate_inputs() — langchain Function Reference

Dependency Diagram

graph TD
  e4877997_5734_a30d_80bc_a99942eef494["_amoderate_inputs()"]
  48713c67_3a9a_ec9e_ec74_46e6955f07bd["OpenAIModerationMiddleware"]
  e4877997_5734_a30d_80bc_a99942eef494 -->|defined in| 48713c67_3a9a_ec9e_ec74_46e6955f07bd
  dba8c922_0033_80d5_1547_3a5900e4ba64["abefore_model()"]
  dba8c922_0033_80d5_1547_3a5900e4ba64 -->|calls| e4877997_5734_a30d_80bc_a99942eef494
  f8bee86c_3f1e_1e20_7cac_e6c507e856d6["_amoderate_tool_messages()"]
  e4877997_5734_a30d_80bc_a99942eef494 -->|calls| f8bee86c_3f1e_1e20_7cac_e6c507e856d6
  3b0af14d_fc17_a4ff_f519_e197161877e5["_amoderate_user_message()"]
  e4877997_5734_a30d_80bc_a99942eef494 -->|calls| 3b0af14d_fc17_a4ff_f519_e197161877e5
  style e4877997_5734_a30d_80bc_a99942eef494 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/langchain_openai/middleware/openai_moderation.py lines 205–230

    async def _amoderate_inputs(
        self, messages: Sequence[BaseMessage]
    ) -> dict[str, Any] | None:
        working = list(messages)
        modified = False

        if self.check_tool_results:
            action = await self._amoderate_tool_messages(working)
            if action:
                if "jump_to" in action:
                    return action
                working = cast("list[BaseMessage]", action["messages"])
                modified = True

        if self.check_input:
            action = await self._amoderate_user_message(working)
            if action:
                if "jump_to" in action:
                    return action
                working = cast("list[BaseMessage]", action["messages"])
                modified = True

        if modified:
            return {"messages": working}

        return None