知識問答生成器

將此提示複製到我們的開發者控制台中，親自試試看！

角色	內容
User	生成各種主題的知識問答題，並提供提示幫助用戶找到正確答案。從多樣化的類別中選擇，創建測試用戶知識或推理能力的問題。提供一系列逐漸具體的提示，引導用戶找到解答。確保問題具有挑戰性，且提示提供足夠的信息來幫助用戶，但不要過於輕易地透露答案。

範例輸出

類別：地理

問題：
世界上唯一一個同時與法國和西班牙接壤的國家是哪個？

提示 1：這個國家位於法國和西班牙之間的比利牛斯山脈中。
提示 2：它以令人驚嘆的山景、滑雪勝地和免稅購物而聞名。
提示 3：該國的首都名稱中包含國家本身的名稱。

答案：安道爾

類別：科學

問題：
植物通過什麼過程將陽光、水和二氧化碳轉化為能量和氧氣？

提示 1：這個過程對地球上的生命至關重要，因為它提供了食物和氧氣。
提示 2：它主要發生在植物的葉子中。
提示 3：這個過程涉及葉綠素，一種吸收陽光的綠色色素。

答案：光合作用

類別：文學

問題：
誰寫了1813年首次出版的經典小說《傲慢與偏見》？

提示 1：這位作者是一位生活在1775年至1817年的英國女性。
提示 2：她以機智、富有洞察力地描繪英國社會和禮儀而聞名。
提示 3：她的其他著名作品包括《理智與情感》和《艾瑪》。

答案：簡·奧斯汀

類別：歷史

問題：
分隔東西德的柏林牆在哪一年開始被拆除？

提示 1：這一事件發生在20世紀末。
提示 2：它標誌著冷戰結束的重要時刻。
提示 3：這一年常與歐洲「共產主義倒台」這一說法聯繫在一起。

答案：1989年

API 請求

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=0.5,
  messages=[
    {
    "role": "user",
    "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
)
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=0.5,
  messages=[
    {
    "role": "user",
    "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
)
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: 0.5,
  messages: [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
});
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=0.5,
messages=[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
}
]
}
]
)
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: 0.5,
  messages: [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
});
console.log(msg);

from anthropic import AnthropicVertex

client = AnthropicVertex()

message = client.messages.create(
    model="claude-3-7-sonnet-v1@20250219",
    max_tokens=2000,
    temperature=0.5,
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
                }
            ]
        }
    ]
)
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: 0.5,
  messages: [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Generate trivia questions on various topics and provide hints to help users arrive at the correct answer. Select from a diverse set of categories and create questions that test the user's knowledge or reasoning skills. Offer a series of increasingly specific hints to guide users towards the solution. Ensure that the questions are challenging and that the hints provide enough information to help the user without giving away the answer too easily."
        }
      ]
    }
  ]
});
console.log(msg);

資源

​範例輸出

​API 請求

範例輸出

API 請求