少樣本提示（Few-shot prompting）

使用 OpenAI API 的提示工程

Fouad Trad

Machine Learning Engineer

少樣本提示（Few-shot prompting）

提供模型範例（問答配對）

少樣本提示的結構示意圖：包含範例問題與答案，最後是要模型回答的新問題。

少樣本提示（Few-shot prompting）

提供模型範例（問答配對）

示意圖：如何將少樣本提示送給 LLM。

少樣本提示（Few-shot prompting）

提供模型範例（問答配對）

示意圖：如何將少樣本提示送給 LLM 並取得回覆。

少樣本提示（Few-shot prompting）

提供模型範例（問答配對）

示意圖：如何將少樣本提示送給 LLM 並取得回覆。

範例數量：
- 0 -> zero-shot 提示
- 1 -> one-shot 提示
- 多於 1 -> few-shot 提示

Zero-shot 提示

不提供範例的提示
模型依自身知識產生回應
適合快速、簡單的任務

prompt = "What is prompt engineering?"
print(get_response(prompt))

Prompt engineering refers to designing and refining prompts or instructions given 
to a language model like ChatGPT to elicit desired responses or behaviors. It 
involves formulating specific guidelines or hints to guide the model's output 
towards a desired outcome.

One-shot 提示

僅提供 1 個範例
有助於維持一致的格式或風格

prompt =  """ 
Q: Sum the numbers 3, 5, and 6. A: 3+5+6=14
Q: Sum the numbers 2, 4, and 7. A: 
"""
print(get_response(prompt))

2+4+7=13

One-shot 提示

prompt = """
Q: Sum the numbers 3, 5, and 6. A: The sum of 3, 5, and 6 is 14
Q: Sum the numbers 2, 4, and 7. A: 
"""
print(get_response(prompt))

The sum of 2, 4, and 7 is 13

少樣本提示（Few-shot prompting）

提供多於 1 個範例
對脈絡型任務特別有力

prompt = """
Text: Today the weather is fantastic -> Classification: positive
Text: The furniture is small -> Classification: neutral
Text: I don't like your attitude -> Classification: negative

"""

少樣本提示（Few-shot prompting）

提供多於 1 個範例
對脈絡型任務特別有力

prompt = """
Text: Today the weather is fantastic -> Classification: positive
Text: The furniture is small -> Classification: neutral
Text: I don't like your attitude -> Classification: negative
Text: That shot selection was awful -> Classification: 
"""
print(get_response(prompt))

negative

使用對話模型的少樣本提示

response = client.chat.completions.create(
  model = "gpt-4o-mini",

  messages = [{"role": "user",
             "content": "Today the weather is fantastic"},

             {"role": "assistant",
             "content": "positive"},

              {"role": "user",
             "content": "I don't like your attitude"},
              {"role": "assistant",
             "content": "negative"},

              {"role": "user",
             "content": "That shot selection was awful"}
             ],
  temperature = 0
)

print(response.choices[0].message.content)

negative

注意事項

依「任務複雜度」選擇 shots 數量
- 較少 shots -> 基礎任務
- 多元 shots -> 複雜任務

一張有人自我提問的照片。

一起來練習吧！

使用 OpenAI API 的提示工程