Fast Document Extraction with mineru-open-api#

Zero-setup, instant document parsing — no login, no token, no configuration needed. Supports tables and formulas (LaTeX).

Installation#

bash

npm install -g mineru-open-api

Or via Go (macOS/Linux):

bash

go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Verify installation#

bash

mineru-open-api version

Quick start#

bash

mineru-open-api flash-extract report.pdf                     # PDF → Markdown (instant!)
mineru-open-api flash-extract report.pdf -o ./out/           # Save to file
mineru-open-api flash-extract resume.docx                    # Word → Markdown
mineru-open-api flash-extract slides.pptx                    # PowerPoint → Markdown
mineru-open-api flash-extract photo.png                      # Image → Markdown (OCR)
mineru-open-api flash-extract https://example.com/doc.pdf    # URL → Markdown

Supported input formats#

FormatSupportedPDF ( .pdf)YesImages ( .png, .jpg, .jpeg, .jp2, .webp, .gif, .bmp)YesWord ( .docx)YesPowerPoint ( .pptx)YesURLs (remote files)Yes

Command: flash-extract#

bash

mineru-open-api flash-extract <file-or-url> [flags]

Flags#

FlagShortDefaultDescription--output``-o_(stdout)Output path (file or directory)--language``chDocument language--pages(all)_Page range, e.g. 1-10``--timeout``900Timeout in seconds

Supported --language values#

Values are organized by script/language family — each value covers all languages in its group.

Standalone language packs#

ValueIncluded languages说明chChinese, English, Chinese Traditional中英文（默认值）ch_serverChinese, English, Chinese Traditional, Japanese繁体、手写体enEnglish纯英文japanChinese, English, Chinese Traditional, Japanese日文为主koreanKorean, English韩文chinese_chtChinese, English, Chinese Traditional, Japanese繁体中文为主taTamil, English泰米尔文teTelugu, English泰卢固文kaKannada卡纳达文elGreek, English希腊文thThai, English泰文

Language family packs#

ValueScript/FamilyIncluded languageslatinLatin script (拉丁语系)French, German, Afrikaans, Italian, Spanish, Bosnian, Portuguese, Czech, Welsh, Danish, Estonian, Irish, Croatian, Uzbek, Hungarian, Serbian (Latin), Indonesian, Occitan, Icelandic, Lithuanian, Maori, Malay, Dutch, Norwegian, Polish, Slovak, Slovenian, Albanian, Swedish, Swahili, Tagalog, Turkish, Latin, Azerbaijani, Kurdish, Latvian, Maltese, Pali, Romanian, Vietnamese, Finnish, Basque, Galician, Luxembourgish, Romansh, Catalan, QuechuaarabicArabic script (阿拉伯语系)Arabic, Persian, Uyghur, Urdu, Pashto, Kurdish, Sindhi, Balochi, EnglishcyrillicCyrillic script (西里尔语系)Russian, Belarusian, Ukrainian, Serbian (Cyrillic), Bulgarian, Mongolian, Abkhazian, Adyghe, Kabardian, Avar, Dargin, Ingush, Chechen, Lak, Lezgin, Tabasaran, Kazakh, Kyrgyz, Tajik, Macedonian, Tatar, Chuvash, Bashkir, Malian, Moldovan, Udmurt, Komi, Ossetian, Buryat, Kalmyk, Tuvan, Sakha, Karakalpak, Englisheast_slavicEast Slavic (东斯拉夫语系)Russian, Belarusian, Ukrainian, EnglishdevanagariDevanagari script (天城文语系)Hindi, Marathi, Nepali, Bihari, Maithili, Angika, Bhojpuri, Magahi, Santali, Newari, Konkani, Sanskrit, Haryanvi, English

Examples#

bash

mineru-open-api flash-extract report.pdf
mineru-open-api flash-extract report.pdf -o ./out/
mineru-open-api flash-extract report.pdf --language en
mineru-open-api flash-extract report.pdf --language latin
mineru-open-api flash-extract report.pdf --pages "1-5"
mineru-open-api flash-extract contract.docx -o ./out/
mineru-open-api flash-extract presentation.pptx -o ./out/
mineru-open-api flash-extract scan.jpg --language ch

Output behavior#

• No -o flag: result goes to stdout; status/progress messages go to stderr
• With -o flag: result saved to file/directory; progress messages on stderr
• Markdown output includes extracted images saved alongside the .md file
• Tables are converted to Markdown tables
• Formulas are converted to LaTeX format (inline $...$ and block $$...$$)

Agent guidelines#

When using this skill on behalf of the user:

• Always use flash-extract for any input — whether it's a local file or a URL (e.g. https://cdn-mineru.openxlab.org.cn/demo/example.pdf). Do NOT assume a URL means "web page". flash-extract handles URLs to document files directly.
• Quote file paths that contain spaces or special characters with double quotes. Example: mineru-open-api flash-extract "report 01.pdf".
• Don't run commands blindly on errors — explain the exit code and troubleshooting steps instead of re-running the command.
• Installation questions ("mineru 怎么安装") should be answered with the install instructions above.

Default output directory#

When the user does NOT specify -o, generate a default output directory:

text

~/MinerU-Skill/<name>_<hash>/

• <name>: derived from the source, then sanitized (replace spaces and shell-unsafe characters with _, collapse consecutive _).

  • For URLs: last path segment (e.g. https://arxiv.org/pdf/2509.22186 → 2509.22186)
  • For local files: filename without extension (e.g. report.pdf → report)

• <hash>: first 6 characters of MD5 hash of the full original source.

bash

echo -n "source" | md5sum | cut -c1-6   # Linux
echo -n "source" | md5 | cut -c1-6      # macOS

When the user specifies -o: use the user's path as-is.

Skill upgrade = CLI upgrade#

When the user asks to upgrade this skill, re-install the CLI first:

bash

npm install -g mineru-open-api@latest

Exit codes#

CodeMeaningRecovery0Success—1General API or unknown errorCheck network; retry; use --verbose2Invalid parameters / usage errorCheck command syntax and flag values4File too large or page limit exceededTry a smaller file or fewer pages5Extraction failedDocument may be corrupted or unsupported6TimeoutIncrease with --timeout

Troubleshooting#

• Timeout on large files: Increase with --timeout 1600
• Extraction quality is poor: Try specifying --language to match the document language
• HTTP 429: Rate limit hit. Wait a few minutes and retry.