Chat roles and
system messages
WORKING WITH THE OPENAI API
James Chapman
Curriculum Manager, DataCamp
Chat Completions
Single-turn tasks
Text generation
Text transformation
Classification
WORKING WITH THE OPENAI API
Chat Completions
Single-turn tasks
Text generation
Text transformation
Classification
Multi-turn conversations
→ Build on previous prompts and responses
WORKING WITH THE OPENAI API
Roles
System: controls assistant's behavior
User: instruct the assistant
Assistant: response to user instruction
Can also be written by the developer to
provide examples
WORKING WITH THE OPENAI API
Request setup
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": prompt}]
)
WORKING WITH THE OPENAI API
Prompt setup
messages=[{"role": "system",
"content": "You are a Python programming tutor who speaks concisely."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
WORKING WITH THE OPENAI API
Making a request
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "system",
"content": "You are a Python programming tutor who speaks concisely."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
)
print(response.choices[0].message.content)
WORKING WITH THE OPENAI API
The response
Mutable objects can be changed after creation, while immutable objects cannot be
modified once they are created.
WORKING WITH THE OPENAI API
Mitigating misuse
System message: Can include guardrails
Restrictions on model outputs
WORKING WITH THE OPENAI API
Mitigating misuse with system messages
sys_msg = """
You are finance education assistant that helps students study for exams.
If you are asked for specific, real-world financial advice with risk to their
finances, respond with:
I'm sorry, I am not allowed to provide financial advice.
"""
WORKING WITH THE OPENAI API
Mitigating misuse with system messages
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "system",
"content": sys_msg},
{"role": "user",
"content": "Which stocks should I invest in?"}]
)
print(response.choices[0].message.content)
I'm sorry, I am not allowed to provide financial advice.
WORKING WITH THE OPENAI API
Let's practice!
WORKING WITH THE OPENAI API
Utilizing the
assistant role
WORKING WITH THE OPENAI API
James Chapman
Curriculum Manager, DataCamp
Chat completions for single-turn tasks
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "system",
"content": "You are a data science tutor."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
)
System: controls assistant's behavior
User: instruct the assistant
Assistant: response to user instruction
WORKING WITH THE OPENAI API
Providing examples
Steer model in the right direction
Providing assistant messages is a more
structured form of shot-prompting
Example: Python Programming Tutor
Example user questions and answers
WORKING WITH THE OPENAI API
Providing examples
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "system",
"content": "You are a Python programming tutor who speaks concisely."},
{"role": "user",
"content": "How do you define a Python list?"},
{"role": "assistant",
"content": "Lists are defined by enclosing a comma-separated sequence of
objects inside square brackets [ ]."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
)
WORKING WITH THE OPENAI API
The response
print(response.choices[0].message.content)
Mutable objects can be changed after creation (e.g., lists, dictionaries). Immutable objects
cannot be altered once created (e.g., strings, tuples).
Experiment with the number of examples
WORKING WITH THE OPENAI API
System vs. assistant vs. user
System → important template formatting
Output the information in this format:
name | age | occupation
Assistant → example conversations
User → context required for the new input (often single-turn)
Create a job advert for an AI Engineer. Use this job advert as a template:
Job Title: Data Engineer
...
WORKING WITH THE OPENAI API
Let's practice!
WORKING WITH THE OPENAI API
Multi-turn
conversations with
GPT
WORKING WITH THE OPENAI API
James Chapman
Curriculum Manager, DataCamp
Assistant messages
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "system",
"content": "You are a Python programming tutor who speaks concisely."},
{"role": "user",
"content": "How do you define a Python list?"},
{"role": "assistant",
"content": "Lists are defined by enclosing a comma-separated sequence of
objects inside square brackets [ ]."},
{"role": "user",
"content": "What is the difference between mutable and immutable objects?"}]
)
WORKING WITH THE OPENAI API
Building a conversation
WORKING WITH THE OPENAI API
Building a conversation
WORKING WITH THE OPENAI API
Building a conversation
WORKING WITH THE OPENAI API
Building a conversation
WORKING WITH THE OPENAI API
Building a conversation
WORKING WITH THE OPENAI API
Coding a conversation
messages = [{"role": "system",
"content": "You are a data science tutor who provides short, simple explanations."}]
user_qs = ["Why is Python so popular?", "Summarize this in one sentence."]
for q in user_qs:
print("User: ", q)
user_dict = {"role": "user", "content": q}
messages.append(user_dict)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=messages
)
assistant_dict = {"role": "assistant", "content": response.choices[0].message.content}
messages.append(assistant_dict)
print("Assistant: ", response.choices[0].message.content, "\n")
WORKING WITH THE OPENAI API
Conversation with an AI
User: Why is Python so popular?
Assistant: Python is popular for many reasons, including its simplicity,
versatility, and wide range of available libraries. It has a relatively
easy-to-learn syntax that makes it accessible to beginners and experts alike. It
can be used for a variety of tasks, such as data analysis, web development,
scientific computing, and machine learning. Additionally, Python has an active
community of developers who contribute to its development and share their
knowledge through online resources and forums.
User: Summarize this in one sentence.
Assistant: Python is popular due to its simplicity, versatility, wide range of
libraries, and active community of developers.
WORKING WITH THE OPENAI API
Let's practice!
WORKING WITH THE OPENAI API
Congratulations!
WORKING WITH THE OPENAI API
James Chapman
Curriculum Manager, DataCamp
Chapter 1
What the OpenAI API is used for
How to create requests to the Chat
Completions endpoint
client = OpenAI(api_key="<OPENAI_API_TOKEN>")
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "..."}]
)
print(response.choices[0].message.content)
WORKING WITH THE OPENAI API
Chapter 2
response = client.chat.completions.create( max_completion_tokens and temperature
model="gpt-4o-mini",
messages=[{"role": "user", "content": "..."}],
max_completion_tokens=20,
temperature=0.5
)
Q&A
Text transformation
Content generation
Sentiment analysis
Categorization
WORKING WITH THE OPENAI API
Chapter 3
"system"
Steer model outputs
Add guardrails
"assistant"
Structured few-shot prompting
Build a conversation history
WORKING WITH THE OPENAI API
What next?
AI application development:
OpenAI Fundamentals skill track
Developing AI Applications skill track
Associate AI Engineer for Developers career track
Apply your learning in projects:
Planning a Trip to Paris with the OpenAI API
Enriching Stock Market Data using the OpenAI API
Personalized Language Tutor
WORKING WITH THE OPENAI API
Let's practice!
WORKING WITH THE OPENAI API
