Generating a customer response

Multi-Modal Systems with the OpenAI API

James Chapman

Curriculum Manager, DataCamp

Reminder

print(corrected_text)

Corrected text (highlighted)

Case study plan

Customer message moderation

Generating a response

Response moderation

Case study steps

Customer message moderation

from openai import OpenAI

client = OpenAI(api_key="ENTER YOUR KEY HERE")


response = client.moderations.create(
    model="text-moderation-latest",
    input=corrected_text
)


# Extract scores and convert to dictionary
scores = response.results[0].category_scores.model_dump()

Customer message moderation

print(scores)

{'harassment': 1.0383088920207229e-05,
  ...
 'hate': 6.848756015642721e-07,
  ...
 'violence': 6.475193367805332e-05,
 ...}

Customer message moderation

# Extract violence score
violence_score = scores['violence']


# Check if violence score is above 0.7
if violence_score > 0.7:
    print("Content flagged for violence!")
else:
    print("Content is safe from violence.")

Content is safe from violence.

Generating a response

print(FAQs)

Q: How can I upgrade my subscription?
A: You can upgrade your plan anytime in your account settings under 'Billing'. 
...

print(content_overview)

Content Type: Career Track // Title: Associate AI Engineer for Developers // 
...

Generating a response

A prompt with role specified

Generating a response

Passing resources to the prompt

Generating a response

Full prompt

Generating a response

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": instruction_prompt},
        {"role": "user", "content": corrected_text}
    ],
    max_completion_tokens=400
)

Generating a response

# Extract chatbot response
chatbot_reply = response.choices[0].message.content

Chatbot reply highlighted

Response moderation

response = client.moderations.create(
    model="text-moderation-latest",
    input=chatbot_reply))

scores = response.results[0].category_scores.model_dump()

Response moderation

# Check if any scores exceed 0.7
if all(score > 0.7 for score in scores.values()):
    print("AI Response flagged for moderation!")
    chatbot_reply = """I'm sorry, but I can't provide a response to that request.
    Please contact [email protected] for further assistance."""
else:
    print("AI Response is safe.")

AI Response is safe.

Recap

Case study steps with checkmarks

Let's practice!

Multi-Modal Systems with the OpenAI API