Moderating the customer call
To ensure quality and safety, you'll now moderate the processed customer message. This step helps identify and flag potentially inappropriate content such as harassment.
The corrected transcript from the previous exercise is available as corrected_text.
This exercise is part of the course
Multi-Modal Systems with the OpenAI API
Exercise instructions
- Create a moderation request using the
text-moderation-latestmodel withcorrected_textas input. - Extract response's category scores and convert them to a dictionary using
.model_dump(). - Extract the harassment score from the
scoresdictionary and check if it is greater than0.8.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
client = OpenAI(api_key="")
# Send the moderation request
response = ____
# Extract scores and convert to dictionary
scores = ____
# Extract harassment score
harassment_score = ____
if ____:
print("Content flagged for harassment!")
else:
print("Content is safe from harassment.")