리소스
- Overview
- 빠른 시작
- Claude 3 모델 카드
- Claude 3.7 시스템 카드
- 시스템 상태
- Anthropic 코스
- 프롬프트 라이브러리
- 프롬프트 라이브러리
- 우주의 키스트로크
- 기업 선견자
- 웹사이트 마법사
- 엑셀 수식 전문가
- Google 앱스 스크립트 작성자
- Python 버그 버스터
- 시간 여행 컨설턴트
- 스토리텔링 조력자
- 출처 인용하기
- SQL 마법사
- 꿈 해석가
- 말장난꾼
- 요리 크리에이터
- 혼성어 시인
- 유머러스한 도우미 할(Hal)
- LaTeX 전문가
- 감정 색상화
- Git 마스터하기
- 비유의 달인
- 윤리적 딜레마 내비게이터
- 회의 기록자
- 관용구 해설가
- 코드 컨설턴트
- 함수 제작기
- 신조어 창작자
- CSV 변환기
- 이모지 인코더
- 문장 개선기
- 관점 분석기
- 퀴즈 생성기
- 마음챙김 멘토
- 초등학교 2학년 수준 단순화기
- VR 피트니스 혁신가
- PII 정화기
- 메모 마에스트로
- 커리어 코치
- 채점 전문가
- 혀 꼬부리기
- 면접 질문 작성기
- 문법 지니
- 수수께끼를 내겠습니다
- 코드 명확화 도구
- 외계 인류학자
- 데이터 정리기
- 브랜드 빌더
- 효율성 추정기
- 리뷰 분류기
- 방향 디코더
- 동기부여 뮤즈
- 이메일 추출기
- 마스터 중재자
- 수업 계획 작성기
- 소크라테스식 현자
- 두운법 연금술사
- 미래적 패션 어드바이저
- 다국어 초능력
- 제품 이름 짓기 전문가
- 철학적 사색
- 스프레드시트 마법사
- 공상과학 시나리오 시뮬레이터
- 적응형 에디터
- 바벨의 방송
- 트윗 톤 감지기
- 공항 코드 분석기
프롬프트 라이브러리
출처 인용하기
문서 내용에 관한 질문에 대한 답변을 관련 인용과 함께 얻으세요.
프롬프트 기반 접근 방식 대신 API에 내장된 인용 기능을 사용하는 것이 좋습니다. API 인용 기능을 사용하면 인용 품질이 향상되고, 반환된 모든 인용이 유효하며, 필요한 출력 토큰 수가 잠재적으로 감소할 수 있습니다.
이 프롬프트를 개발자 콘솔에 복사하여 직접 시도해보세요!
내용 | |
---|---|
System | 당신은 전문 연구 보조원입니다. 다음은 질문에 답할 문서입니다: 먼저, 질문에 답하는 데 가장 관련성이 높은 문서의 인용문을 찾아 번호 순서대로 출력하세요. 인용문은 비교적 짧아야 합니다. 관련 인용문이 없으면 대신 “관련 인용문 없음”이라고 작성하세요. 그런 다음 “답변:“으로 시작하여 질문에 답하세요. 답변에 인용된 내용을 그대로 포함하거나 참조하지 마세요. 답변할 때 “인용문 [1]에 따르면”이라고 말하지 마세요. 대신 관련 문장 끝에 대괄호 안의 번호를 추가하여 답변의 각 섹션과 관련된 인용문을 참조하세요. 따라서 전체 응답 형식은 인용문: [1] “Company X는 2021년에 1,200만 달러의 수익을 보고했습니다.” [2] “수익의 거의 90%가 위젯 판매에서 발생했으며, 가젯 판매가 나머지 10%를 차지했습니다.” 답변: Company X는 1,200만 달러를 벌었습니다. [1] 그 중 거의 90%가 위젯 판매에서 발생했습니다. [2] 문서로 질문에 답할 수 없는 경우 그렇게 말하세요. |
User | Matterport는 잘 하고 있나요? |
예시 출력
인용문:
[1] “우리는 최근 급속한 성장을 경험했습니다. 우리의 구독자는 2018년 12월 31일부터 2022년 12월 31일까지 약 49배 증가했습니다. 우리의 수익은 2022년 12월 31일에 끝난 해에 약 22% 증가한 1억 3,610만 달러로, 2021년 12월 31일에 끝난 해의 약 1억 1,120만 달러에서 증가했습니다.”
[2] “우리의 총 이익은 2022년 12월 31일에 끝난 해에 810만 달러 또는 14% 감소하여 5,180만 달러가 되었으며, 이는 2021년 12월 31일에 끝난 해의 6,000만 달러에서 감소한 것으로, 주로 2022 회계연도의 글로벌 공급망 제약으로 인한 특정 혼란 및 추가 비용에 기인합니다.”
[3] “2022년 12월 31일에 끝난 3개월 동안의 순 달러 확장률 103%는 우리 플랫폼의 고착성과 성장 잠재력을 보여줍니다.”
답변:
Matterport는 최근 몇 년간 구독자와 수익 측면에서 급속한 성장을 경험했습니다. [1] 그러나 공급망 문제로 인해 2022년에는 총 이익이 감소했습니다. [2] 순 달러 확장률은 강력한 구독자 유지율과 지속적인 성장 가능성을 나타냅니다. [3] 전반적으로, 총 이익의 감소에도 불구하고 Matterport의 구독자 및 수익 성장과 플랫폼의 고착성은 회사가 비교적 잘 하고 있음을 시사합니다.
API 요청
import anthropic
client = anthropic.Anthropic( # defaults to os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-opus-4-20250514",
max_tokens=2000,
temperature=0,
system='You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write "No relevant quotes" instead. \n \nThen, answer the question, starting with "Answer:". Do not include or reference quoted content verbatim in the answer. Don\'t say "According to Quote [1]" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what\'s shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] "Company X reported revenue of \$12 million in 2021." \n[2] "Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%." \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.',
messages=[
{
"role": "user",
"content": [{"type": "text", "text": "Is Matterport doing well?"}],
}
],
)
print(message.content)
import anthropic
client = anthropic.Anthropic( # defaults to os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-opus-4-20250514",
max_tokens=2000,
temperature=0,
system='You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write "No relevant quotes" instead. \n \nThen, answer the question, starting with "Answer:". Do not include or reference quoted content verbatim in the answer. Don\'t say "According to Quote [1]" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what\'s shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] "Company X reported revenue of \$12 million in 2021." \n[2] "Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%." \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.',
messages=[
{
"role": "user",
"content": [{"type": "text", "text": "Is Matterport doing well?"}],
}
],
)
print(message.content)
import Anthropic from "@anthropic-ai/sdk";
const anthropic = new Anthropic({
apiKey: "my_api_key", // defaults to process.env["ANTHROPIC_API_KEY"]
});
const msg = await anthropic.messages.create({
model: "claude-opus-4-20250514",
max_tokens: 2000,
temperature: 0,
system: "You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write \"No relevant quotes\" instead. \n \nThen, answer the question, starting with \"Answer:\". Do not include or reference quoted content verbatim in the answer. Don't say \"According to Quote [1]\" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what's shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] \"Company X reported revenue of \$12 million in 2021.\" \n[2] \"Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%.\" \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.",
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Is Matterport doing well?"
}
]
}
]
});
console.log(msg);
from anthropic import AnthropicBedrock
# See https://docs.anthropic.com/claude/reference/claude-on-amazon-bedrock
# for authentication options
client = AnthropicBedrock()
message = client.messages.create(
model="anthropic.claude-opus-4-20250514-v1:0",
max_tokens=2000,
temperature=0,
system="You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write \"No relevant quotes\" instead. \n \nThen, answer the question, starting with \"Answer:\". Do not include or reference quoted content verbatim in the answer. Don't say \"According to Quote [1]\" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what's shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] \"Company X reported revenue of \$12 million in 2021.\" \n[2] \"Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%.\" \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Is Matterport doing well?"
}
]
}
]
)
print(message.content)
import AnthropicBedrock from "@anthropic-ai/bedrock-sdk";
// See https://docs.anthropic.com/claude/reference/claude-on-amazon-bedrock
// for authentication options
const client = new AnthropicBedrock();
const msg = await client.messages.create({
model: "anthropic.claude-opus-4-20250514-v1:0",
max_tokens: 2000,
temperature: 0,
system: "You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write \"No relevant quotes\" instead. \n \nThen, answer the question, starting with \"Answer:\". Do not include or reference quoted content verbatim in the answer. Don't say \"According to Quote [1]\" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what's shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] \"Company X reported revenue of \$12 million in 2021.\" \n[2] \"Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%.\" \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.",
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Is Matterport doing well?"
}
]
}
]
});
console.log(msg);
from anthropic import AnthropicVertex
client = AnthropicVertex()
message = client.messages.create(
model="claude-3-7-sonnet-v1@20250219",
max_tokens=2000,
temperature=0,
system="You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write \"No relevant quotes\" instead. \n \nThen, answer the question, starting with \"Answer:\". Do not include or reference quoted content verbatim in the answer. Don't say \"According to Quote [1]\" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what's shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] \"Company X reported revenue of \$12 million in 2021.\" \n[2] \"Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%.\" \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.",
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Is Matterport doing well?"
}
]
}
]
)
print(message.content)
import { AnthropicVertex } from '@anthropic-ai/vertex-sdk';
// Reads from the `CLOUD_ML_REGION` & `ANTHROPIC_VERTEX_PROJECT_ID` environment variables.
// Additionally goes through the standard `google-auth-library` flow.
const client = new AnthropicVertex();
const msg = await client.messages.create({
model: "claude-3-7-sonnet-v1@20250219",
max_tokens: 2000,
temperature: 0,
system: "You are an expert research assistant. Here is a document you will answer questions about: \n<doc> \n[Full text of [Matterport SEC filing 10-K 2023](https://investors.matterport.com/node/9501/html), not pasted here for brevity] \n</doc> \n \nFirst, find the quotes from the document that are most relevant to answering the question, and then print them in numbered order. Quotes should be relatively short. \n \nIf there are no relevant quotes, write \"No relevant quotes\" instead. \n \nThen, answer the question, starting with \"Answer:\". Do not include or reference quoted content verbatim in the answer. Don't say \"According to Quote [1]\" when answering. Instead make references to quotes relevant to each section of the answer solely by adding their bracketed numbers at the end of relevant sentences. \n \nThus, the format of your overall response should look like what's shown between the <example></example> tags. Make sure to follow the formatting and spacing exactly. \n<example> \nQuotes: \n[1] \"Company X reported revenue of \$12 million in 2021.\" \n[2] \"Almost 90% of revenue came from widget sales, with gadget sales making up the remaining 10%.\" \n \nAnswer: \nCompany X earned \$12 million. [1] Almost 90% of it was from widget sales. [2] \n</example> \n \nIf the question cannot be answered by the document, say so.",
messages: [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Is Matterport doing well?"
}
]
}
]
});
console.log(msg);