{
  "id": "conv_20251010_213857_814",
  "title": "rag全称是什么",
  "created_at": "2025-10-10T21:38:57.814950",
  "updated_at": "2025-10-10T22:03:34.424046",
  "messages": [
    {
      "role": "user",
      "content": "rag全称是什么",
      "timestamp": "2025-10-10T21:39:05.734088"
    },
    {
      "role": "assistant",
      "content": "RAG 的全称是 **Retrieval-Augmented Generation**，中文常译为“检索增强生成”。\n\n它是一种结合信息检索（Retrieval）与文本生成（Generation）的技术，广泛应用于大语言模型（LLM）系统中，尤其是在需要引用外部知识库或实时数据的场景下。RAG 的核心思想是：在生成答案前，先从外部文档或数据库中检索相关信息，再将这些信息作为上下文输入给语言模型，从而生成更准确、更可靠的回答。",
      "timestamp": "2025-10-10T21:39:08.143795"
    }
  ],
  "metadata": {
    "project_path": "/Users/jojo/Desktop/agents/正在修复中/agent_kimi_源码备份_标记有bug版本/project",
    "thinking_mode": true,
    "total_messages": 2,
    "total_tools": 0,
    "status": "active"
  },
  "token_statistics": {
    "total_input_tokens": 8821,
    "total_output_tokens": 163,
    "updated_at": "2025-10-10T22:03:34.424077"
  }
}