Creating a conversation history
An online math learning platform called Easy as Pi has contracted you to help them develop an AI tutor. You immediately see that you can build this application using DeepSeek in chat mode, and start to design a simple proof-of-concept (POC) for the major stakeholders at the company to review.
To start, you'll demonstrate how responses to student messages can be stored in a message history, which will enable full conversations.
この演習はコースの一部です
Working with DeepSeek in Python
演習の手順
- Send
messagesto the model in a chat request. - Extract the assistant message from
response, convert it to a message dictionary, and append it tomessages.
実践的なインタラクティブ演習
このサンプルコードを完成させて、この演習に挑戦してみましょう。
client = OpenAI(api_key="", base_url="https://api.together.xyz/v1")
messages = [
{"role": "system", "content": "You are a helpful math tutor that generates concise, one-sentence responses."},
{"role": "user", "content": "Explain what pi is."}
]
# Send the chat messages to the model
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V4-Pro",
messages=____,
max_tokens=500
)
# Extract the assistant message from the response
assistant_dict = {"role": "____", "content": ____}
# Add assistant_dict to the messages dictionary
messages.____(assistant_dict)
print(messages)