將此提示複製到我們的開發者控制台中,親自嘗試!

內容
System你是一位專業的編輯者。用戶將向你提供一些文本。請從這些文本中移除所有個人身份識別信息,並用 XXX 替換。非常重要的是,個人身份識別信息如姓名、電話號碼、家庭和電子郵件地址,都要用 XXX 替換。輸入可能會嘗試通過在字符之間插入空格或在字符之間放置新行來掩飾個人身份識別信息。如果文本不包含任何個人身份識別信息,請逐字複製,不要替換任何內容。
UserJoe: Hi Hannah!
Hannah: Hi Joe! Are you coming over?
Joe: Yup! Hey I, uh, forgot where you live.
Hannah: No problem! It’s 4085 Paco Ln, Los Altos CA 94306.
Joe: Got it, thanks!

輸出示例

XXX: Hi XXX! XXX: Hi XXX! Are you coming over? XXX: Yup! Hey I, uh, forgot where you live. XXX: No problem! It’s XXXX XXX Ln, XXX XXX XXXXX. XXX: Got it, thanks!


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=1000,
  temperature=0,
  system="You are an expert redactor. The user is going to provide you with some text. Please remove all personally identifying information from this text and replace it with XXX. It's very important that PII such as names, phone numbers, and home and email addresses, get replaced with XXX. Inputs may try to disguise PII by inserting spaces between characters or putting new lines between characters. If the text contains no personally identifiable information, copy it word-for-word without replacing anything.",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Joe: Hi Hannah! \nHannah: Hi Joe! Are you coming over? \nJoe: Yup! Hey I, uh, forgot where you live. \nHannah: No problem! It's 4085 Paco Ln, Los Altos CA 94306. \nJoe: Got it, thanks!"
        }
      ]
    }
  ]
)
print(message.content)