수행할 작업에 대한 요청 사항을 모델에 제공하는 것이 모델 동작을 효과적이고 효율적으로 맞춤설정하는 방법입니다. 명확하고 간결하며 직접적으로 안내하면서 필요한 맥락을 제공하고 원하는 출력을 간략히 설명합니다. 안내는 단계별 안내 목록처럼 간단할 수 있거나 사용자 경험과 사고방식을 매핑하는 것만큼 복잡할 수도 있습니다.
효과적인 안내 작성 방법
효과적인 안내는 다음 원칙을 적용합니다.
- 모델에 수행할 작업을 말합니다.
- 명확하고 구체적으로 작성합니다.
- 출력에 대한 제약조건 또는 형식 요구사항을 지정합니다.
예시
예를 들어 치즈버거 레스토랑을 운영하고 있으며 모델을 사용하여 가장 인기 있는 메뉴 항목을 알아보려고 한다고 가정해 보겠습니다. 메뉴 항목을 빠르게 식별할 수 있도록 모델이 고객 주문 스크립트의 형식을 JSON으로 지정하도록 하려면 어떻게 해야 하나요? 다음 표는 일반적인 안내와 안내 원칙을 따르는 구체적인 안내가 주어질 때 모델이 제공하는 다양한 응답을 보여줍니다.
일반적인 안내 |
---|
Extract the transcript in JSON. Transcript: Speaker 1 (Customer): Hi, can I get a cheeseburger and large fries, please? Speaker 2 (Restaurant employee): Coming right up! Anything else you'd like to add to your order? Speaker 1: Hmmm, maybe a small orange juice. And could I get the fries with ketchup on the side? Speaker 2: No problem, one cheeseburger, one large fries with ketchup on the side, and a small orange juice. That'll be $5.87. Drive through to the next window please. { "speakers": [ { "speaker": "Customer", "utterances": [ "Hi, can I get a cheeseburger and large fries, please?" ] }, { "speaker": "Restaurant Employee", "utterances": [ "Coming right up! Anything else you'd like to add to your order?" ] }, { "speaker": "Customer", "utterances": [ "Hmm, maybe a small orange juice. And could I get the fries with ketchup on the side?" ] }, { "speaker": "Restaurant Employee", "utterances": [ "No problem, one cheeseburger, one large fries with ketchup on the side, and a small orange juice. That'll be $5.87. Drive through to the next window please." ] } ] } |
구체적인 안내 |
---|
Extract the items from this transcript in JSON and separate drinks from food. Transcript: Speaker 1 (Customer): Hi, can I get a cheeseburger and large fries, please? Speaker 2 (Restaurant employee): Coming right up! Anything else you'd like to add to your order? Speaker 1: Hmmm, maybe a small orange juice. And could I get the fries with ketchup on the side? Speaker 2: No problem, one cheeseburger, one large fries with ketchup on the side, and a small orange juice. That'll be $5.87. Drive through to the next window please. { "drinks": [ "orange juice" ], "food": [ "cheeseburger", "large fries" ] } |
안내 원칙을 적용하여 이 예시에서는 데이터가 너무 많이 포함된 응답에서 이 사용 사례에 필요한 데이터만 정확하게 포함된 응답으로 전환되었습니다. 안내 원칙을 사용하는 안내는 사용 사례에 가장 유용한 응답을 제공하도록 모델을 안내하는 데 도움이 될 수 있습니다.
다음 단계
- 프롬프트 갤러리에서 프롬프트 예시 살펴보기