上下文缓存

第一次请求缓存创建 token 数: 1605
第一次请求缓存命中 token 数: 0
====================
第二次请求缓存创建 token 数: 0
第二次请求缓存命中 token 数: 1605

{
  "role": "system",
  "content": [
    {
      "type": "text",
      "text": "<您指定的 prompt>",
      "cache_control": {
        "type": "ephemeral"
      }
    }
  ]
}

messages = [{"role": "system","content": "你是一位语文老师，可以帮助学生理解阅读材料。"},
  {"role": "user","content": "<文章内容> 这篇文章的主旨是什么？"}]

messages = [{"role": "system","content": "你是一位语文老师，可以帮助学生理解阅读材料。"},
  {"role": "user","content": "<文章内容> 请分析这篇文章的第三段。"}]

messages=[{"role": "system","content": "You are a helpful assistant."},
  {"role": "user","content": "你是谁？"}]

messages=[{"role": "system","content": "You are a helpful assistant."},
  {"role": "user","content": "你是谁？"},
  {"role": "assistant","content": "我是通义千问，由阿里云开发。"},
  {"role": "user","content": "你能做什么？"}]

system_prompt = """你是一位经验丰富的营销专家。请按以下格式为不同产品提供详细的营销建议：

1. 目标受众: xxx

2. 主要卖点: xxx

3. 营销渠道: xxx
...
12. 长期发展策略: xxx

请确保建议具体、可操作，且与产品特性高度相关。"""

# 第一次请求的用户消息，询问关于智能手表的营销建议
messages_1=[
  {"role": "system", "content": system_prompt},
  {"role": "user", "content": "请为一款新上市的智能手表提供营销建议。"}
]

# 第二次请求的用户消息，询问关于笔记本电脑的营销建议。由于 system_prompt 相同，缓存命中的概率很高。
messages_2=[
  {"role": "system", "content": system_prompt},
  {"role": "user", "content": "请为一款新上市的笔记本电脑提供营销建议。"}
]

# 第一次请求的用户消息，询问视频内容
messages1 = [
  {"role":"system","content":[{"text": "You are a helpful assistant."}]},
  {"role": "user",
    "content": [
      {"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250328/eepdcq/phase_change_480p.mov"},
      {"text": "这个视频的内容是什么？"}
    ]
  }
]

# 第二次请求的用户消息，询问视频时间戳。由于基于同一视频提问，将 video 放在 text 之前，缓存命中的概率很高。
messages2 = [
  {"role":"system","content":[{"text": "You are a helpful assistant."}]},
  {"role": "user",
    "content": [
      {"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250328/eepdcq/phase_change_480p.mov"},
      {"text": "请描述视频中的一系列事件，并以 JSON 格式输出开始时间（start_time）、结束时间（end_time）和事件（event）。不要输出 ```json``` 代码段。"}
    ]
  }
]

{
  "id": "145584fd-3dce-4890-99dc-e3896d7f5a42",
  "created_at": 1772440976.0,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": null,
  "model": "qwen3.6-plus",
  "object": "response",
  "output": [
    {
      "id": "msg_62a4e323-d78c-46c7-8469-2ad50f8af4b1",
      "type": "reasoning",
      "content": null
    },
    {
      "id": "msg_560e34a6-1bdf-42ae-993e-590b38249146",
      "content": [
        {
          "annotations": [],
          "text": "Although both Random Forest and GBDT (Gradient Boosting Decision Tree) are ensemble algorithms based on decision trees, they have the following main differences:\n\n1.  **Different Ensemble Strategies**\n    *   **Random Forest**: Based on the **Bagging** idea. Each tree is trained independently, with no dependency between them.\n    *   **GBDT**: Based on the **Boosting** idea. The trees have a strong dependency relationship, where the next tree aims to fit the residuals (negative gradient) of the previous tree's prediction.\n\n2.  **Different Training Methods**\n    *   **Random Forest**: Supports **parallel training** because the trees are independent, which usually results in higher computational efficiency.\n    *   **GBDT**: Must be **trained serially** because the next tree depends on the output of the previous one, making it inherently difficult to parallelize (although engineering implementations like XGBoost have made parallel optimizations at the feature level).\n\n3.  **Different Optimization Objectives**\n    *   **Random Forest**: Mainly reduces **variance** by averaging multiple models to prevent overfitting and improve stability.\n    *   **GBDT**: Mainly reduces **bias** by progressively correcting errors to improve the model's fitting ability and accuracy.\n\n4.  **Sensitivity to Outliers**\n    *   **Random Forest**: Relatively robust and not sensitive to outliers.\n    *   **GBDT**: More sensitive to outliers because outliers produce large residuals, which affect the fitting direction of subsequent trees.\n\nIn summary, Random Forest excels in stability and parallel efficiency, while GBDT usually performs better in terms of accuracy but is more complex to tune and slower to train.",
          "type": "output_text"
        }
      ],
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": false,
  "temperature": null,
  "tool_choice": "auto",
  "tools": [],
  "top_p": null,
  "status": "completed",
  "usage": {
    "input_tokens": 1524,
    "input_tokens_details": {
      "cached_tokens": 1305
    },
    "output_tokens": 1534,
    "output_tokens_details": {
      "reasoning_tokens": 1187
    },
    "total_tokens": 3058
  }
}