Skip to main content

Adding moderation

This shows how to add in moderation (or other safeguards) around your LLM application.

%pip install --upgrade --quiet  langchain langchain-openai
from langchain.chains import OpenAIModerationChain
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import OpenAI
moderate = OpenAIModerationChain()
model = OpenAI()
prompt = ChatPromptTemplate.from_messages([("system", "repeat after me: {input}")])
chain = prompt | model
chain.invoke({"input": "you are stupid"})
'\n\nYou are stupid.'
moderated_chain = chain | moderate
moderated_chain.invoke({"input": "you are stupid"})
{'input': '\n\nYou are stupid',
'output': "Text was found that violates OpenAI's content policy."}