更多 assistant 訊息！
延伸你先前的訊息，加入更多範例，並分別存成 example1、response1、example2、response2、example3 和 response3。
來看看能不能讓模型依照預期的格式輸出資訊！
本練習屬於課程
使用 Python 操作 DeepSeek
練習說明
- 延伸你先前的訊息，加入其他國家的額外範例，並分別存成
example1、response1、example2、response2、example3和response3。
動手互動練習
試著完成這個範例程式碼，體驗一下這個練習。
client = OpenAI(api_key="", base_url="https://api.together.xyz/v1")
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V4.1-Flash",
# Add in the extra examples and responses
messages=[
{"role": "system", "content": "You are a helpful Geography tutor that generates concise, one-sentence summaries for different countries."},
{"role": "user", "content": "Give me a quick summary of Portugal."},
{"role": "assistant", "content": "Portugal is a country in Europe that borders Spain. The capital city is Lisboa."},
{"role": "user", "content": ____},
{"role": "assistant", "content": ____},
{"role": "user", "content": ____},
{"role": "assistant", "content": ____},
{"role": "user", "content": ____},
{"role": "assistant", "content": ____},
{"role": "user", "content": "Give me a quick summary of Greece."}
]
)
print(response.choices[0].message.content)