_amoderate() — langchain Function Reference

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

Function python LangChainCore Runnables calls 1 called by 3

Entity Profile

LangChainCore→ Runnables→ _amoderate() — langchain Function Reference

Dependency Diagram

graph TD
  d71322b2_e390_f20d_bda8_c8361be856d9["_amoderate()"]
  48713c67_3a9a_ec9e_ec74_46e6955f07bd["OpenAIModerationMiddleware"]
  d71322b2_e390_f20d_bda8_c8361be856d9 -->|defined in| 48713c67_3a9a_ec9e_ec74_46e6955f07bd
  7ab5affa_5898_4089_2b48_c4caa16d99a2["_amoderate_output()"]
  7ab5affa_5898_4089_2b48_c4caa16d99a2 -->|calls| d71322b2_e390_f20d_bda8_c8361be856d9
  f8bee86c_3f1e_1e20_7cac_e6c507e856d6["_amoderate_tool_messages()"]
  f8bee86c_3f1e_1e20_7cac_e6c507e856d6 -->|calls| d71322b2_e390_f20d_bda8_c8361be856d9
  3b0af14d_fc17_a4ff_f519_e197161877e5["_amoderate_user_message()"]
  3b0af14d_fc17_a4ff_f519_e197161877e5 -->|calls| d71322b2_e390_f20d_bda8_c8361be856d9
  596a20ec_ee47_dd52_c0d3_647a9beaa5ca["_build_async_client()"]
  d71322b2_e390_f20d_bda8_c8361be856d9 -->|calls| 596a20ec_ee47_dd52_c0d3_647a9beaa5ca
  style d71322b2_e390_f20d_bda8_c8361be856d9 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/openai/langchain_openai/middleware/openai_moderation.py lines 424–430

    async def _amoderate(self, text: str) -> Moderation:
        if self._async_client is None:
            self._async_client = self._build_async_client()
        response = await self._async_client.moderations.create(
            model=self.model, input=text
        )
        return response.results[0]