_moderate_output() — langchain Function Reference

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

Function python LangChainCore Runnables calls 4 called by 1

Entity Profile

LangChainCore→ Runnables→ _moderate_output() — langchain Function Reference

Dependency Diagram

graph TD
  171f9009_f0c5_1fb7_2224_0686c89f7a33["_moderate_output()"]
  48713c67_3a9a_ec9e_ec74_46e6955f07bd["OpenAIModerationMiddleware"]
  171f9009_f0c5_1fb7_2224_0686c89f7a33 -->|defined in| 48713c67_3a9a_ec9e_ec74_46e6955f07bd
  d785fd03_0ba8_5b39_5297_f8614287fbc5["after_model()"]
  d785fd03_0ba8_5b39_5297_f8614287fbc5 -->|calls| 171f9009_f0c5_1fb7_2224_0686c89f7a33
  1837f115_98c9_8c34_1443_f85d68c85154["_find_last_index()"]
  171f9009_f0c5_1fb7_2224_0686c89f7a33 -->|calls| 1837f115_98c9_8c34_1443_f85d68c85154
  f339afc9_dc76_818a_622f_e3da922e8e0c["_extract_text()"]
  171f9009_f0c5_1fb7_2224_0686c89f7a33 -->|calls| f339afc9_dc76_818a_622f_e3da922e8e0c
  00b44df2_8039_fbfd_6b56_82201884b43b["_moderate()"]
  171f9009_f0c5_1fb7_2224_0686c89f7a33 -->|calls| 00b44df2_8039_fbfd_6b56_82201884b43b
  59081f65_8455_8937_22b3_f7febac7b501["_apply_violation()"]
  171f9009_f0c5_1fb7_2224_0686c89f7a33 -->|calls| 59081f65_8455_8937_22b3_f7febac7b501
  style 171f9009_f0c5_1fb7_2224_0686c89f7a33 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/langchain_openai/middleware/openai_moderation.py lines 232–250

    def _moderate_output(
        self, messages: Sequence[BaseMessage]
    ) -> dict[str, Any] | None:
        last_ai_idx = self._find_last_index(messages, AIMessage)
        if last_ai_idx is None:
            return None

        ai_message = messages[last_ai_idx]
        text = self._extract_text(ai_message)
        if not text:
            return None

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

        return self._apply_violation(
            messages, index=last_ai_idx, stage="output", content=text, result=result
        )