One-shot prompting: will it be enough?
As you saw, there's room for improvement in your initial prompt. Try adding an example, Love these! = 5, and including = after each review to see if you can get more consistent formatting and more accurate numbers.
This exercise is part of the course
Working with DeepSeek in Python
Exercise instructions
- Add the example
Love these! = 5to the start of the prompt, and add=after each review in the prompt to indicate how the result should be formatted.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
client = OpenAI(api_key="", base_url="https://api.together.xyz/v1")
# Add the example to the prompt
prompt = """Classify sentiment as 1-5 (negative to positive). Return no explanations:
1. ____
2. Unbelievably good! ____
3. Shoes fell apart on the second use. ____
4. The shoes look nice, but they aren't very comfortable. ____
5. Can't wait to show them off! ____"""
response = client.chat.completions.create(model="deepseek-ai/DeepSeek-V3", messages=[{"role": "user", "content": prompt}], max_tokens=150)
print(response.choices[0].message.content)