Creating an AI chatbot
To complete your POC, you'll integrate your message history with a for
loop, so you can send repeated prompts to the model, storing each response in the message history in series.
This exercise is part of the course
Working with the OpenAI API
Exercise instructions
- Loop over the user messages (
user_msgs
). - Create a dictionary for the user message in each iteration, and append it to
messages
. - Send
messages
to the model in a chat request. - Append the assistant message dictionary to
messages
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
client = OpenAI(api_key="")
messages = [{"role": "system", "content": "You are a helpful math tutor that speaks concisely."}]
user_msgs = ["Explain what pi is.", "Summarize this in two bullet points."]
# Loop over the user questions
for q in ____:
print("User: ", q)
# Create a dictionary for the user message from q and append to messages
user_dict = {"role": ____, "content": ____}
messages.append(____)
# Create the API request
response = client.chat.completions.create(
model="gpt-4o-mini",
____,
max_completion_tokens=100
)
# Append the assistant's message to messages
assistant_dict = {"role": "assistant", "content": response.choices[0].message.content}
messages.append(____)
print("Assistant: ", response.choices[0].message.content, "\n")