为什么"Mondays"对话会出现在我的摘要中?

我的摘要中出现了“Mondays”对话:

我在日志中看到了这个——它似乎是为了帮助模型解释格式?但不应该显示给用户。

在更改两项内容后,此行为开始出现:

  1. 从 sonnet 3.5 切换到 haiku 3.5
  2. 使用 AiSummary.destroy_all删除了 ai_summaries 表中现有的摘要。也许这还不够?

切换到 Claude Haiku 3.5 后,每个摘要都是这样的吗?

1 个赞

不,大约一半——大约 10 个摘要中有 5 个生成了。我尝试切换回 sonnet 以查看这是否能解决问题,但遇到了速率限制,因此这可能需要一段时间才能确定。

您能否检查一下发生这种情况的某个主题的整个API请求和响应,并与我分享?它将在 ai_api_audit_logs 表中。

2 个赞

目前还不。但我之前看过,发现该主题的回复是一个有效的摘要,没有提到星期一。回复后是否有任何方式会混淆?如果没什么想到的,我将在几天内给你一个更明确的例子。

1 个赞

我们对 ai_api_audit_logs 的日志记录是有保证的,任何成功的响应都会记录在那里,您应该能看到完整的提示。您能否运行数据浏览器并查看表的内容?

1 个赞

我遇到了 Anthropic 的速率限制问题,至少在使用 haiku 时是这样。我可以尝试修复速率限制,但最好是失败而不是显示错误。

/logs:

Job exception: {"type":"error","error":{"type":"rate_limit_error","message":"Number of request tokens has exceeded your per-minute rate limit (https://docs.anthropic.com/en/api/rate-limits); see the response headers for current usage. Please reduce the prompt length or the maximum tokens requested, or try again later. You may also contact sales at https://www.anthropic.com/contact-sales to discuss your options for a rate limit increase."}}

来自 ai_api_audit_logs 的请求。我已编辑掉真实的用户内容:

{
  "model": "claude-3-haiku-20240307",
  "max_tokens": 3000,
  "messages": [
    {
      "role": "user",
      "content": "Here are the posts inside <input></input> XML tags:\n\n<input>1) user1 said: I love Mondays 2) user2 said: I hate Mondays</input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language."
    },
    {
      "role": "assistant",
      "content": "Two users are sharing their feelings toward Mondays. [user1](/t/-/11772/1) hates them, while [user2](/t/-/11772/2) loves them."
    },
    {
      "role": "user",
      "content": "he discussion title is: [redacted].\n\nHere are the posts, inside <input>[redacted]</input> XML tags:\n\n<input></input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language."
    }
  ],
  "system": "You are an advanced summarization bot that generates concise, coherent summaries of provided text.\n\n- Only include the summary, without any additional commentary.\n- You understand and generate Discourse forum Markdown; including links, _italics_, **bold**.\n- Maintain the original language of the text being summarized.\n- Aim for summaries to be 400 words or less.\n- Each post is formatted as \"<POST_NUMBER>) <USERNAME> <MESSAGE>\"\n- Cite specific noteworthy posts using the format [NAME](/t/-/11772/POST_NUMBER)\n  - Example: link to the 3rd post by sam: [sam](/t/-/11772/3)\n  - Example: link to the 6th post by jane: [agreed with](/t/-/11772/6)\n  - Example: link to the 13th post by joe: [#13](/t/-/11772/13)\n- When formatting usernames either use @USERNMAE OR [USERNAME](/t/-/11772/POST_NUMBER)"
}

来自 ai_api_audit_logs 的响应:

{
  "id": "msg_01QPVSmg93tu21WtPUvoNZ33",
  "type": "message",
  "role": "assistant",
  "model": "claude-3-haiku-20240307",
  "content": [
    {
      "type": "text",
      "text": "Summary:\n\nTwo users are sharing their feelings toward Mondays. [user1](/t/-/11772/1) loves them, while [user2](/t/-/11772/2) hates them."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 7298,
    "output_tokens": 49
  }
}

点击“Summarize”按钮会显示:

这意味着当您达到速率限制时,他们会返回 200 响应而不是 429。

这将是他们 API 的一个错误。您可以在那里提交错误报告吗?

1 个赞

他们想要包含标头的网络流量。我不知道如何通过点击“摘要”按钮或触发 sidekiq 作业来从浏览器中获取它。

我们不会记录该信息,您需要从服务器重现 cURL 请求并将其转发。

1 个赞

您也可以提供 msg_01QPVSmg93tu21WtPUvoNZ33 给他们,他们可以直接在日志中查找。

3 个赞

Sam @markschmucker 提供的请求 ID 有来自 Anthropic 的任何消息吗?

如果您仍然受到速率限制,也许可以尝试将回填批次大小减半。

1 个赞

他们没有典型的支持工单系统——而是你与机器人对话。我向机器人报告了问题,包括 @sam 提供的消息 ID。机器人相信了,并承诺将其转交给人工处理,并在有新状态时给我发邮件。还没有收到邮件。

3 个赞

今天我收到一条来自 Anthropic 的聊天消息,只是问我是否还在发生。它还在发生。没有进一步的反馈。令人沮丧的经历。

来自 Anthropic 的回复:

你好,

很遗憾,我目前无法重现此错误。

此致,
Ryan

我不知道该如何进一步推进此事。我可以自己创建一个 cURL 测试,但我怀疑这并不能准确地复制 Discourse 的操作。

Discourse 会执行与 cURL 相同的 HTTP 调用,因此可以 100% 精确地重现。

话虽如此,众所周知,Anthropic 在满足日益增长的需求方面遇到了困难,因此,通过 AWS 或 Google Cloud 使用 Claude,或者尝试 Gemini 或其他 LLM API 可能更容易。