_amoderate_user_message() — langchain Function Reference

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

Function python LangChainCore MessageInterface calls 4 called by 1

Entity Profile

LangChainCore→ MessageInterface→ _amoderate_user_message() — langchain Function Reference

Dependency Diagram

graph TD
  3b0af14d_fc17_a4ff_f519_e197161877e5["_amoderate_user_message()"]
  48713c67_3a9a_ec9e_ec74_46e6955f07bd["OpenAIModerationMiddleware"]
  3b0af14d_fc17_a4ff_f519_e197161877e5 -->|defined in| 48713c67_3a9a_ec9e_ec74_46e6955f07bd
  e4877997_5734_a30d_80bc_a99942eef494["_amoderate_inputs()"]
  e4877997_5734_a30d_80bc_a99942eef494 -->|calls| 3b0af14d_fc17_a4ff_f519_e197161877e5
  1837f115_98c9_8c34_1443_f85d68c85154["_find_last_index()"]
  3b0af14d_fc17_a4ff_f519_e197161877e5 -->|calls| 1837f115_98c9_8c34_1443_f85d68c85154
  f339afc9_dc76_818a_622f_e3da922e8e0c["_extract_text()"]
  3b0af14d_fc17_a4ff_f519_e197161877e5 -->|calls| f339afc9_dc76_818a_622f_e3da922e8e0c
  d71322b2_e390_f20d_bda8_c8361be856d9["_amoderate()"]
  3b0af14d_fc17_a4ff_f519_e197161877e5 -->|calls| d71322b2_e390_f20d_bda8_c8361be856d9
  59081f65_8455_8937_22b3_f7febac7b501["_apply_violation()"]
  3b0af14d_fc17_a4ff_f519_e197161877e5 -->|calls| 59081f65_8455_8937_22b3_f7febac7b501
  style 3b0af14d_fc17_a4ff_f519_e197161877e5 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/langchain_openai/middleware/openai_moderation.py lines 366–384

    async def _amoderate_user_message(
        self, messages: Sequence[BaseMessage]
    ) -> dict[str, Any] | None:
        idx = self._find_last_index(messages, HumanMessage)
        if idx is None:
            return None

        message = messages[idx]
        text = self._extract_text(message)
        if not text:
            return None

        result = await self._amoderate(text)
        if not result.flagged:
            return None

        return self._apply_violation(
            messages, index=idx, stage="input", content=text, result=result
        )