제로샷 및 퓨샷 프롬프트 작성

제로샷 및 퓨샷 프롬프팅 입문

제로샷 이해하기

제로샷 활용: 분류하기

def call_llm_api(prompt):
    # In a real scenario, this would call an LLM API.
    # For this example, we simulate a response.
    if "sentiment" in prompt.lower():
        return "Sentiment: Positive"
    return "LLM Response: Could not process."

# Our zero-shot prompt
zero_shot_prompt = "Classify the sentiment of 'The movie was fantastic!'"

print(f"Prompt: {zero_shot_prompt}")
print(f"LLM Output: {call_llm_api(zero_shot_prompt)}")

제로샷: 정보 추출하기

def call_llm_api(prompt):
    if "name and age" in prompt.lower():
        return "Name: Alice, Age: 30"
    return "LLM Response: Information not found."

# Another zero-shot prompt example
zero_shot_prompt = "Extract the name and age from 'My name is Alice and I am 30 years old.'"

print(f"Prompt: {zero_shot_prompt}")
print(f"LLM Output: {call_llm_api(zero_shot_prompt)}")

제로샷의 한계

퓨샷 프롬프팅 소개

퓨샷 활용: 다시 작성하기

def call_llm_api(prompt):
    if "active voice" in prompt.lower() and "ball was thrown" in prompt.lower():
        return "Output: The boy threw the ball."
    return "LLM Response: Could not rephrase."

# Our few-shot prompt with one example
few_shot_prompt = """Rephrase into active voice:
Input: The mouse was chased by the cat.
Output: The cat chased the mouse.

Rephrase into active voice:
Input: The ball was thrown by the boy."""

print(f"Prompt: {few_shot_prompt}")
print(f"LLM Output: {call_llm_api(few_shot_prompt)}")

퓨샷: 코드 생성

def call_llm_api(prompt):
    if "function to add" in prompt.lower():
        return "def add(a, b):\n    return a + b"
    return "LLM Response: Code not generated."

# Few-shot prompt for code generation
few_shot_prompt = """Generate a Python function:
Example 1:
Input: Function to multiply two numbers.
Output:
def multiply(a, b):
    return a * b

Example 2:
Input: Function to add two numbers."""

print(f"Prompt: {few_shot_prompt}")
print(f"LLM Output:\n{call_llm_api(few_shot_prompt)}")

적절한 기법 선택하기

제로샷/퓨샷 점검

복습: 프롬프트의 힘