퓨샷 프롬프트

LangChain으로 LLM 애플리케이션 개발하기

Jonathan Bennion

AI Engineer & LangChain Contributor

표준 프롬프트 템플릿의 한계

PromptTemplate + ChatPromptTemplate
✅ 소수 예시 처리
❌ 많은 예시에 비확장적
FewShotPromptTemplate

examples = [
    {
        "question": "..."
        "answer": "..."
    },
    ...
]

예시 세트 구성

examples = [
    {
        "question": "Does Henry Campbell have any pets?",
        "answer": "Henry Campbell has a dog called Pluto."
    },
    ...
]

# Convert pandas DataFrame to list of dicts
examples = df.to_dict(orient="records")

예시 서식 지정

from langchain_core.prompts import FewShotPromptTemplate, PromptTemplate


example_prompt = PromptTemplate.from_template("Question: {question}\n{answer}")

prompt = example_prompt.invoke({"question": "What is the capital of Italy?"
                                "answer": "Rome"})
print(prompt.text)

Question: What is the capital of Italy?
Rome

FewShotPromptTemplate

prompt_template = FewShotPromptTemplate(

    examples=examples,

    example_prompt=example_prompt,

    suffix="Question: {input}",

    input_variables=["input"]

)

examples: 딕셔너리 목록
example_prompt: 서식 템플릿
suffix: 입력에 추가할 접미사
input_variables

퓨샷 프롬프트 템플릿 호출

prompt = prompt_template.invoke({"input": "What is the name of Henry Campbell's dog?"})

print(prompt.text)

Question: Does Henry Campbell have any pets?
Henry Campbell has a dog called Pluto.
...

Question: What is the name of Henry Campbell's dog?

체인과의 통합

llm = ChatOpenAI(model="gpt-4o-mini", api_key="...")


llm_chain = prompt_template | llm
response = llm_chain.invoke({"input": "What is the name of Henry Campbell's dog?"})

print(response.content)

The name of Henry Campbell's dog is Pluto.

연습해 봅시다!

LangChain으로 LLM 애플리케이션 개발하기