资源
- Overview
- 快速入门
- Claude 3 模型卡
- Claude 3.7 系统卡
- 系统状态
- Anthropic 课程
- 提示词库
- 提示词库
- 宇宙键盘
- 企业预见者
- 网站向导
- Excel公式专家
- Google Apps 脚本编写者
- Python 错误修复器
- 时间旅行顾问
- 讲故事助手
- 引用你的来源
- SQL 魔法师
- 解梦师
- 双关语大师
- 烹饪创作者
- 混合词诗人
- 幽默助手哈尔
- LaTeX 指南
- 情绪色彩转换器
- Git 精通
- 比喻大师
- 伦理困境导航器
- 会议记录员
- 成语解析器
- 代码顾问
- 函数制造者
- 新词创造者
- CSV 转换器
- 表情符号编码器
- 文章润色师
- 观点权衡者
- 琐事生成器
- 正念导师
- 二年级简化器
- VR健身创新者
- PII 净化器
- 备忘录大师
- 职业教练
- 评分大师
- 绕口令
- 面试问题设计师
- 语法精灵
- 猜谜语
- 代码解释器
- 外星人类学家
- 数据整理器
- 品牌构建者
- 效率估算器
- 评论分类器
- 方向解码器
- 激励缪斯
- 电子邮件提取器
- 专业审核员
- 课程计划制定者
- 苏格拉底式智者
- 头韵炼金术师
- 未来主义时尚顾问
- 多语言超能力
- 产品命名专家
- 哲学沉思
- 电子表格魔术师
- 科幻场景模拟器
- 自适应编辑器
- 巴别塔的广播
- 推文语调检测器
- 机场代码分析器
提示词库
引用你的来源
获取关于文档内容的问题答案,并提供支持回答的相关引用。
我们建议使用API中内置的引用功能,而不是基于提示的方法。使用API引用功能将提高引用质量,确保所有返回的引用都是有效的,并可能减少所需的输出标记数量。
将此提示复制到我们的开发者控制台中,亲自尝试!
内容 | |
---|---|
System | 你是一位专家研究助手。这里有一份文档,你将回答关于它的问题: 首先,找出文档中与回答问题最相关的引用,然后按编号顺序打印出来。引用应该相对简短。 如果没有相关引用,请写”没有相关引用”。 然后,回答问题,以”回答:“开头。不要在答案中逐字包含或引用引用内容。回答时不要说”根据引用[1]“。相反,仅通过在相关句子末尾添加方括号编号来引用与答案每个部分相关的引用。 因此,你的整体回答格式应该看起来像 引用: [1] “X公司在2021年报告收入为1200万美元。” [2] “近90%的收入来自小部件销售,而小工具销售占剩余的10%。” 回答: X公司赚了1200万美元。[1] 其中近90%来自小部件销售。[2] 如果文档无法回答该问题,请说明。 |
User | Matterport的发展情况如何? |
示例输出
引用:
[1] “我们最近经历了快速增长。从2018年12月31日到2022年12月31日,我们的订阅用户增长了约49倍。我们的收入在截至2022年12月31日的年度增加了约22%,达到1.361亿美元,而截至2021年12月31日的年度约为1.112亿美元。“
[2] “我们的毛利润从2021年12月31日止年度的6000万美元减少了810万美元或14%,至2022年12月31日止年度的5180万美元,主要归因于2022财年全球供应链限制导致的某些破坏性和增量成本。“
[3] “我们截至2022年12月31日的三个月期间的净美元扩展率为103%,这证明了我们平台的粘性和增长潜力。”
回答:
Matterport在近年来经历了快速的订阅用户和收入增长。[1] 然而,由于供应链问题,他们2022年的毛利润下降了。[2] 他们的净美元扩展率表明订阅用户保留率强劲,并有持续增长的潜力。[3] 总体而言,尽管毛利润有所下降,但Matterport的订阅用户和收入增长,以及其平台的粘性,表明公司发展相对良好。
API请求
import anthropic
client = anthropic.Anthropic( # 默认为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( # 默认为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", // 默认为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
# 有关身份验证选项,请参阅https://docs.anthropic.com/claude/reference/claude-on-amazon-bedrock
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";
// 有关身份验证选项,请参阅https://docs.anthropic.com/claude/reference/claude-on-amazon-bedrock
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';
// 从`CLOUD_ML_REGION`和`ANTHROPIC_VERTEX_PROJECT_ID`环境变量中读取。
// 此外,还通过标准的`google-auth-library`流程。
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);