{"_id":"@chenchaolong/plugin-mineru-chaolong","_rev":"3-c278d54f7325560809f69c7c21859907","name":"@chenchaolong/plugin-mineru-chaolong","dist-tags":{"latest":"1.0.14"},"versions":{"1.0.12":{"name":"@chenchaolong/plugin-mineru-chaolong","version":"1.0.12","license":"AGPL-3.0","_id":"@chenchaolong/plugin-mineru-chaolong@1.0.12","maintainers":[{"name":"chenchaolong","email":"646520399@qq.com"}],"homepage":"https://github.com/xpert-ai/xpert-plugins#readme","bugs":{"url":"https://github.com/xpert-ai/xpert-plugins/issues"},"dist":{"shasum":"831a5e114aa2107d0a639391fbd7376cd6c61514","tarball":"https://registry.npmjs.org/@chenchaolong/plugin-mineru-chaolong/-/plugin-mineru-chaolong-1.0.12.tgz","fileCount":20,"integrity":"sha512-W1vNFByWPn4TDWwGObRnDSPUXbrcsbF9DheMXIgMc2SsxH2jB3/XhJsy74oAPsxhoehddMkMIkWZ4iJnAB1+Xg==","signatures":[{"sig":"MEUCIQCT4eUbOpS2NZNVnYiJN8Z0N/enmEmGAP1SGwKYmIEp0QIgCY2sZmA9dc09jy81FXHQzK5m3HDmNN5io4hwEDILhH0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":39258},"main":"./dist/index.js","type":"module","types":"./dist/index.d.ts","module":"./dist/index.js","exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js","default":"./dist/index.js"},"./package.json":"./package.json"},"gitHead":"9ab4d51696e5c20120afa568617ddd004b36d4dc","_npmUser":{"name":"chenchaolong","email":"646520399@qq.com"},"repository":{"url":"git+https://github.com/xpert-ai/xpert-plugins.git","type":"git"},"_npmVersion":"10.8.2","description":"## 简介","directories":{},"_nodeVersion":"20.19.5","dependencies":{"jszip":"^3.10.1","tslib":"^2.3.0"},"_hasShrinkwrap":false,"peerDependencies":{"zod":"3.25.67","chalk":"4.1.2","@nestjs/common":"^11.1.6","@nestjs/config":"^4.0.2","@langchain/core":"0.3.72","@langchain/langgraph":"0.4.7","@xpert-ai/plugin-sdk":"^3.6.2"},"_npmOperationalInternal":{"tmp":"tmp/plugin-mineru-chaolong_1.0.12_1766379170289_0.5360498463024463","host":"s3://npm-registry-packages-npm-production"}},"1.0.13":{"name":"@chenchaolong/plugin-mineru-chaolong","version":"1.0.13","license":"AGPL-3.0","_id":"@chenchaolong/plugin-mineru-chaolong@1.0.13","maintainers":[{"name":"chenchaolong","email":"646520399@qq.com"}],"homepage":"https://github.com/xpert-ai/xpert-plugins#readme","bugs":{"url":"https://github.com/xpert-ai/xpert-plugins/issues"},"dist":{"shasum":"c43680106444a312464c1eb179ecd632874347e8","tarball":"https://registry.npmjs.org/@chenchaolong/plugin-mineru-chaolong/-/plugin-mineru-chaolong-1.0.13.tgz","fileCount":20,"integrity":"sha512-WzO03I0KSxF6jem28FHmSTYtS1seR4RzGpID7LLP+BOFMki0346QSPYgC/3sQ4Y73OmSNZ20X8Doe/Z0S9LbUg==","signatures":[{"sig":"MEUCIQDsc7TsB1cHKPIYOg9Ou7WfiBfYymeZo7Lju9lQSzTfggIgSoYjKYpi70jIkNW+3m2/lKanMwM/vuw22A4UzSrz2Gc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":39258},"main":"./dist/index.js","type":"module","types":"./dist/index.d.ts","module":"./dist/index.js","exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js","default":"./dist/index.js"},"./package.json":"./package.json"},"gitHead":"9ab4d51696e5c20120afa568617ddd004b36d4dc","_npmUser":{"name":"chenchaolong","email":"646520399@qq.com"},"repository":{"url":"git+https://github.com/xpert-ai/xpert-plugins.git","type":"git"},"_npmVersion":"10.8.2","description":"## 简介","directories":{},"_nodeVersion":"20.19.5","dependencies":{"jszip":"^3.10.1","tslib":"^2.3.0"},"_hasShrinkwrap":false,"peerDependencies":{"zod":"3.25.67","chalk":"4.1.2","@nestjs/common":"^11.1.6","@nestjs/config":"^4.0.2","@langchain/core":"0.3.72","@langchain/langgraph":"0.4.7","@xpert-ai/plugin-sdk":"^3.6.2"},"_npmOperationalInternal":{"tmp":"tmp/plugin-mineru-chaolong_1.0.13_1766379413077_0.12041251857850477","host":"s3://npm-registry-packages-npm-production"}},"1.0.14":{"name":"@chenchaolong/plugin-mineru-chaolong","version":"1.0.14","license":"AGPL-3.0","repository":{"type":"git","url":"git+https://github.com/xpert-ai/xpert-plugins.git"},"bugs":{"url":"https://github.com/xpert-ai/xpert-plugins/issues"},"type":"module","main":"./dist/index.js","module":"./dist/index.js","types":"./dist/index.d.ts","exports":{"./package.json":"./package.json",".":{"types":"./dist/index.d.ts","import":"./dist/index.js","default":"./dist/index.js"}},"dependencies":{"jszip":"^3.10.1","tslib":"^2.3.0"},"peerDependencies":{"@langchain/core":"0.3.72","@langchain/langgraph":"0.4.7","@nestjs/common":"^11.1.6","@nestjs/config":"^4.0.2","@xpert-ai/plugin-sdk":"^3.6.2","chalk":"4.1.2","zod":"3.25.67"},"_id":"@chenchaolong/plugin-mineru-chaolong@1.0.14","gitHead":"9ab4d51696e5c20120afa568617ddd004b36d4dc","description":"## 简介","homepage":"https://github.com/xpert-ai/xpert-plugins#readme","_nodeVersion":"20.19.5","_npmVersion":"10.8.2","dist":{"integrity":"sha512-Vw/SJr8vJYbRxeS1JZyQkz3I8r5M2s8av6ES5bWh+OEZP9iA7as7Y/qEsWmsgbX6S2ujj7f5wpeFqPuK4hCtWQ==","shasum":"eaca2a20bb0b38870d7d84d6edcc5e266252913e","tarball":"https://registry.npmjs.org/@chenchaolong/plugin-mineru-chaolong/-/plugin-mineru-chaolong-1.0.14.tgz","fileCount":20,"unpackedSize":42575,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIQCruLUKiJareD4jW1hGZ5mUVWaIyBAWnS09jEHFc/hGRgIgI+lhLBNfMY/3sd+ZWhurkgPlFyJ9Q4oIEiirZGFZ2yU="}]},"_npmUser":{"name":"chenchaolong","email":"646520399@qq.com"},"directories":{},"maintainers":[{"name":"chenchaolong","email":"646520399@qq.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/plugin-mineru-chaolong_1.0.14_1766379897342_0.7153981009731503"},"_hasShrinkwrap":false}},"time":{"created":"2025-12-22T04:52:50.229Z","modified":"2025-12-22T05:04:57.684Z","1.0.12":"2025-12-22T04:52:50.441Z","1.0.13":"2025-12-22T04:56:53.226Z","1.0.14":"2025-12-22T05:04:57.503Z"},"bugs":{"url":"https://github.com/xpert-ai/xpert-plugins/issues"},"license":"AGPL-3.0","homepage":"https://github.com/xpert-ai/xpert-plugins#readme","repository":{"type":"git","url":"git+https://github.com/xpert-ai/xpert-plugins.git"},"description":"## 简介","maintainers":[{"name":"chenchaolong","email":"646520399@qq.com"}],"readme":"# MinerU Plugin\n\n## 简介\n\nMinerU 是一个将文件转换为机器可读格式（如 markdown、JSON）的工具，可以方便地提取为任意格式。\n\nMinerU 是一个文档解析器，可以解析复杂的文档数据，适用于任何下游 LLM 用例（RAG、智能体等）。\n\n[GitHub - opendatalab/MinerU](https://github.com/opendatalab/MinerU)\n\n## 主要特性\n\n- 移除页眉、页脚、脚注、页码等，确保语义连贯性\n- 以人类可读的顺序输出文本，适用于单列、多列和复杂布局\n- 保留原始文档的结构，包括标题、段落、列表等\n- 提取图片、图片描述、表格、表格标题和脚注\n- 自动识别并将文档中的公式转换为 LaTeX 格式\n- 自动识别并将文档中的表格转换为 HTML 格式\n- 自动检测扫描 PDF 和乱码 PDF 并启用 OCR 功能\n- OCR 支持检测和识别 84 种语言\n- 支持多种输出格式，如多模态和 NLP Markdown、按阅读顺序排序的 JSON，以及丰富的中间格式\n- 支持多种可视化结果，包括布局可视化和跨度可视化，用于高效确认输出质量\n- 支持在纯 CPU 环境中运行，也支持 GPU(CUDA)/NPU(CANN)/MPS 加速\n- 兼容 Windows、Linux 和 Mac 平台\n\n## 支持的输入文件类型\n\n**PDF, DOC, DOCX, PPT, PPTX, PNG, JPG, JPEG**\n\n## 使用方法\n\n### 配置步骤\n\n1. 配置 MinerU 插件参数：\n   - Base URL: MinerU API 服务的基础 URL（例如：`https://mineru.net`）\n   - Token: [从 MinerU 获取您的 API token](https://mineru.net/apiManage/token)\n\n2. 保存配置\n\n### 输入参数\n\n| 参数 | 类型 | 必填 | 示例 | 描述 |\n| :--- | :--- | :--- | :--- | :--- |\n| enable_formula | bool | 否 | true | 是否启用公式识别，默认为 true |\n| enable_table | bool | 否 | true | 是否启用表格识别，默认为 true |\n| language | string | 否 | ch | 指定文档语言，默认为 ch，可以设置为 auto，当为 auto 时，模型将自动识别文档语言，其他可选值列表请参见：[PaddleOCR](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5) |\n| enable_ocr | bool | 否 | false | 是否启动 OCR 功能，默认为 false |\n| extra_formats | [string] | 否 | [\"docx\",\"html\"] | Markdown 和 json 是默认的导出格式，无需设置。此参数仅支持 docx、html、latex 三种格式中的一种或多种 |\n| model_version | string | 否 | pipeline | MinerU 模型版本；选项：pipeline 或 vlm，默认为 pipeline |\n\n### 输出\n\n插件为每个处理的文件提供以下输出：\n\n- **text**: 解析后的 Markdown 文本\n- **files**: 额外导出格式的文件（html、docx、latex）和提取的图片\n- **json**: 解析后的内容列表\n\n### 支持的导出格式\n\n默认情况下，插件会输出 Markdown 和 JSON 格式。通过 `extra_formats` 参数，还可以获取以下额外格式：\n\n- **HTML**: 格式化的 HTML 文档\n- **DOCX**: Microsoft Word 文档格式\n- **LaTeX**: LaTeX 源代码格式\n\n这些额外格式的文件将存储在输出的 `files` 中。\n\n## 技术细节\n\n### API 端点\n\n插件使用 MinerU 官方 API，主要端点包括：\n\n- `POST /api/v4/file-urls/batch`: 创建解析任务\n- `GET /api/v4/extract-results/batch/{batch_id}`: 获取解析结果\n\n### 处理流程\n\n1. 上传文件到 MinerU API 获取的上传 URL\n2. 创建解析任务\n3. 轮询获取解析结果\n4. 下载并解压 ZIP 文件\n5. 提取 Markdown、图片、JSON 等格式的内容\n6. 替换 Markdown 中的图片路径为可访问的 URL\n\n## 许可证\n\n请参考项目根目录的 LICENSE 文件。\n","readmeFilename":"README.md"}