{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "huatuo-encyclopedia-qa",
  "name": "huatuo_encyclopedia_qa",
  "summary": {
    "zh": "许可证声明：宽松（Apache-2.0）；本站处理：只链接原出处。许可证宽松，但有来源风险：内容抓取自网站，原站条款未说明；只链接原出处。",
    "en": "License: permissive (Apache-2.0); Mdexa hosting: link-only. License is permissive, but source risk: content scraped from websites whose terms are not stated; link only."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine",
    "pharmacy-drugs"
  ],
  "content_types": [
    "qa-dialogue"
  ],
  "content_description": {
    "en": "Encyclopedia QA corpus",
    "zh": "百科问答语料"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "364,420条问答",
    "measures": [
      {
        "value": 364420,
        "unit": "qa-pairs",
        "qualifier": "exact"
      }
    ]
  },
  "publisher": "FreedomIntelligence",
  "year": {
    "value": null,
    "raw": "未标明（参考 Huatuo-26M 论文，2023）"
  },
  "expert_review": {
    "en": "Not stated",
    "zh": "未说明"
  },
  "license": {
    "legacy_status": "distributable",
    "spdx": "Apache-2.0",
    "commercial_use": "yes",
    "derivatives": "yes",
    "redistribution": "yes",
    "rationale": {
      "en": "Dataset card states Apache-2.0",
      "zh": "数据集卡为 Apache-2.0"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Hugging Face dataset card metadata: Apache-2.0",
          "zh": "Hugging Face 数据集卡元数据：Apache-2.0"
        },
        "excerpt": "license: apache-2.0",
        "spdx": "Apache-2.0",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "permissive",
  "hosting": "link-only",
  "hosting_reason": {
    "zh": "许可证宽松，但有来源风险：内容抓取自网站，原站条款未说明；只链接原出处。",
    "en": "License is permissive, but source risk: content scraped from websites whose terms are not stated; link only."
  },
  "signoff": null,
  "risk_flags": [
    "scraped"
  ],
  "provenance": {
    "source_description": {
      "en": "Extracted from 8,699 Chinese Wikipedia disease entries, 2,736 drug entries and 226,432 articles from the Qianwen Health website",
      "zh": "中文维基百科疾病词条8,699条、药品词条2,736条、千问健康网站文章226,432篇抽取"
    },
    "upstream": [
      {
        "slug": null,
        "name": "Chinese Wikipedia",
        "relation": "based-on"
      },
      {
        "slug": null,
        "name": "千问健康 (website articles)",
        "relation": "based-on"
      }
    ]
  },
  "known_issues": [
    {
      "en": "Includes articles scraped from the Qianwen Health website; original site copyright not stated",
      "zh": "其中含千问健康网站爬取文章，原站版权未说明"
    },
    {
      "en": "Wikipedia content is usually under CC BY-SA; the card does not say",
      "zh": "维基百科内容通常适用 CC BY-SA，卡片未说明"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "task_format",
      "value": "open-qa",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "en": "QA pairs.",
        "zh": "问答对"
      }
    },
    {
      "facet": "specialty",
      "value": "multi-specialty",
      "basis": "inferred",
      "inferred_from": "card-content-description",
      "note": {
        "zh": "综合医学百科问答，未限定专科",
        "en": "综合医学百科问答; not limited to a specialty"
      }
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 2 (0 stated by the authors with excerpts, 2 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 2 个（作者声明 0 个，附逐字摘录；据内容推断 2 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.",
        "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: multi-specialty(inferred).",
        "zh": "新增专科标签：multi-specialty(inferred)。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "FreedomIntelligence/huatuo_encyclopedia_qa",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/FreedomIntelligence/huatuo_encyclopedia_qa",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [
      {
        "name": ".gitattributes",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa/resolve/2989899dd5bed83cf9bd17cf9fff9889705436e2/.gitattributes",
        "size_bytes": 2322,
        "checksum": null,
        "format": "gitattributes"
      },
      {
        "name": "README.md",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa/resolve/2989899dd5bed83cf9bd17cf9fff9889705436e2/README.md",
        "size_bytes": 1317,
        "checksum": null,
        "format": "md"
      },
      {
        "name": "my_dataset.py",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa/resolve/2989899dd5bed83cf9bd17cf9fff9889705436e2/my_dataset.py",
        "size_bytes": 2069,
        "checksum": null,
        "format": "py"
      },
      {
        "name": "test_datasets.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa/resolve/2989899dd5bed83cf9bd17cf9fff9889705436e2/test_datasets.jsonl",
        "size_bytes": 1713540,
        "checksum": null,
        "format": "jsonl"
      },
      {
        "name": "train_datasets.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa/resolve/2989899dd5bed83cf9bd17cf9fff9889705436e2/train_datasets.jsonl",
        "size_bytes": 604103775,
        "checksum": {
          "algorithm": "sha256",
          "value": "d89c034a924b63c66f94e3a920b9872ed1a609d66d8ad79d8f747374521e9285"
        },
        "format": "jsonl"
      },
      {
        "name": "validation_datasets.jsonl",
        "url": "https://huggingface.co/datasets/FreedomIntelligence/huatuo_encyclopedia_qa/resolve/2989899dd5bed83cf9bd17cf9fff9889705436e2/validation_datasets.jsonl",
        "size_bytes": 1688211,
        "checksum": null,
        "format": "jsonl"
      }
    ],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download FreedomIntelligence/huatuo_encyclopedia_qa --repo-type dataset",
        "evidence": {
          "excerpt": "You can use the hf download command from the terminal to directly download files from the Hub.",
          "doc": "hf-download",
          "url": "https://huggingface.co/docs/huggingface_hub/guides/download",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": "2989899dd5bed83cf9bd17cf9fff9889705436e2",
      "last_modified": "2023-05-17T03:20:55.000Z"
    },
    "license_note": {
      "license_status": "permissive",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": []
  },
  "_links": {
    "text": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：ChatMed_Consult_Dataset (https://mdexa.com/zh/datasets/chatmed-consult-dataset/)；Chinese-medical-dialogue-data（Toyhom） (https://mdexa.com/zh/datasets/chinese-medical-dialogue-data/)；cMedQA2 (https://mdexa.com/zh/datasets/cmedqa2/)。",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/zh/agents.md",
    "faq": "https://mdexa.com/zh/developers/faq/",
    "similar": [
      {
        "name": "ChatMed_Consult_Dataset",
        "url": "https://mdexa.com/zh/datasets/chatmed-consult-dataset/",
        "json": "https://mdexa.com/zh/datasets/chatmed-consult-dataset.json"
      },
      {
        "name": "Chinese-medical-dialogue-data（Toyhom）",
        "url": "https://mdexa.com/zh/datasets/chinese-medical-dialogue-data/",
        "json": "https://mdexa.com/zh/datasets/chinese-medical-dialogue-data.json"
      },
      {
        "name": "cMedQA2",
        "url": "https://mdexa.com/zh/datasets/cmedqa2/",
        "json": "https://mdexa.com/zh/datasets/cmedqa2.json"
      }
    ]
  }
}