Mineru

Document Extraction with mineru-open-api

Installation

npm install -g mineru-open-api

Or via Go (macOS/Linux):

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

Verify installation

mineru-open-api version

Two extraction modes

flash-extract limits

When any limit is exceeded, the agent should suggest switching to extract with a token (create at https://mineru.net/apiManage/token), which has significantly higher limits.

Core workflow

1. Start fast (no token): mineru-open-api flash-extract <file> for quick Markdown conversion
2. Need more? Create token at https://mineru.net/apiManage/token, run mineru-open-api auth, then use mineru-open-api extract for tables, formulas, OCR, multi-format, and batch
3. Web pages: mineru-open-api crawl <url> to convert web content
4. Check results: output goes to stdout (default) or -o directory

Authentication

Only required for extract and crawl. Not needed for flash-extract.

Configure your API token (create one at https://mineru.net/apiManage/token):

mineru-open-api auth                    # Interactive token setup
export MINERU_TOKEN="your-token"  # Or set via environment variable

Token resolution order: --token flag > MINERU_TOKEN env > ~/.mineru/config.yaml.

Supported input formats

The crawl command accepts any HTTP/HTTPS URL and extracts web page content.

Commands

flash-extract — Quick extraction (no token needed)

Fast, token-free document extraction. Outputs Markdown only. No table recognition. Limited to 10 MB / 20 pages per file, with IP-based rate limiting.

mineru-open-api flash-extract report.pdf                     # Markdown to stdout
mineru-open-api flash-extract report.pdf -o ./out/           # Save to file
mineru-open-api flash-extract https://example.com/doc.pdf    # URL mode
mineru-open-api flash-extract report.pdf --language en       # Specify language
mineru-open-api flash-extract report.pdf --pages 1-10        # Page range

flash-extract flags

extract — Precision extraction (token required)

Convert PDFs, images, and other documents to Markdown or other formats. Supports table/formula recognition, OCR, multiple output formats, and batch mode.

mineru-open-api extract report.pdf                         # Markdown to stdout
mineru-open-api extract report.pdf -f html                 # HTML to stdout
mineru-open-api extract report.pdf -o ./out/               # Save to directory
mineru-open-api extract report.pdf -o ./out/ -f md,docx    # Multiple formats
mineru-open-api extract *.pdf -o ./results/                # Batch extract
mineru-open-api extract --list files.txt -o ./results/     # Batch from file list
mineru-open-api extract https://example.com/doc.pdf        # Extract from URL
cat doc.pdf | mineru-open-api extract --stdin -o ./out/    # From stdin

extract flags

| --concurrency | | 0 | Batch concurrency (0 = server default) |

Model comparison: vlm vs pipeline

When the user values accuracy and the document has complex formatting, suggest --model vlm. When the user prioritizes reliability and no-hallucination guarantee, suggest --model pipeline (or omit --model to use auto).

crawl — Web page extraction (token required)

Fetch web pages and convert to Markdown.

mineru-open-api crawl https://example.com/article              # Markdown to stdout
mineru-open-api crawl https://example.com/article -f html      # HTML to stdout
mineru-open-api crawl https://example.com/article -o ./out/     # Save to file
mineru-open-api crawl url1 url2 -o ./pages/                     # Batch crawl
mineru-open-api crawl --list urls.txt -o ./pages/               # Batch from file list

crawl flags

auth — Authentication management

mineru-open-api auth              # Interactive token setup
mineru-open-api auth --verify     # Verify current token is valid
mineru-open-api auth --show       # Show current token source and masked value

Supported --language values

The --language flag accepts the following values (default: ch). Used by both flash-extract and extract. Values are organized by script/language family — each value covers all languages listed in its group.

Standalone language packs

For specific languages or CJK combinations.

Language family packs

One value covers many languages sharing the same script system.

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
• Batch mode (extract/crawl only): requires -o to specify output directory
• Binary formats (docx, extract only): cannot output to stdout, must use -o
• Markdown output includes extracted images saved alongside the .md file

General rules

When using this skill on behalf of the user:

• Quote file paths that contain spaces or special characters with double quotes in commands. Example: mineru-open-api extract "report 01.pdf", NOT mineru-open-api extract report 01.pdf.
• Don't run commands blindly on errors — if the user asks "提取失败了怎么办", 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, not by running mineru-open-api extract.
• DOCX as input is supported — if the user asks "这个 Word 文档能转 Markdown 吗", use mineru-open-api extract file.docx or mineru-open-api flash-extract file.docx. Note: .doc format is only supported by extract, not flash-extract.
• Table extraction — tables are only recognized by extract (not flash-extract). If the user mentions tables, use extract.
• For stdout mode (no -o), only one text format can be output at a time. If the user wants multiple formats, suggest adding -o.

Choosing between flash-extract and extract

The agent MUST follow this decision logic:

1. Default to flash-extract when:

   • User has NOT configured a token (no ~/.mineru/config.yaml, no MINERU_TOKEN env)
   • User wants a quick/simple extraction without mentioning tables, formulas, OCR, or specific formats
   • File is under 10 MB and under 20 pages
   • User is trying the tool for the first time

2. Use extract when:

   • User explicitly asks for table recognition, formula recognition, or OCR
   • User requests non-Markdown output formats (html, latex, docx, json)
   • User needs batch processing (multiple files)
   • File is over 10 MB or over 20 pages (exceeds flash-extract limits)
   • User has a token configured and wants precision-quality extraction

3. If unsure, prefer flash-extract — it's faster and requires no setup, but check file size first.

4. When the user does NOT specify an output path (-o), the agent MUST generate a default output directory to prevent file overwrites. Use:

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

Naming rules:

• <name>: derived from the source, then sanitized for safe directory names.
  • 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)
  • Sanitization: replace spaces and shell-unsafe characters (space, (, ), [, ], &, ', ", !, #, $, `) with _. Collapse consecutive _ into one. Keep alphanumeric, -, _, ., and CJK characters.
• <hash>: first 6 characters of the MD5 hash of the full original source path or URL (before sanitization). This ensures:
  • Different URLs with similar basenames get unique directories
  • Re-running the same source reuses the same directory (idempotent) How the agent should generate the hash:

echo -n "https://arxiv.org/pdf/2509.22186" | md5sum | cut -c1-6

Or on macOS:

echo -n "https://arxiv.org/pdf/2509.22186" | md5 | cut -c1-6

5. When the user asks to upgrade or update this skill, the agent MUST re-install the CLI binary to ensure the latest commands are available. Run the install command before using any new features

flash-extract limit handling

When flash-extract fails due to file limits or rate limiting, the agent MUST provide a clear explanation and suggest extract as the upgrade path:

Rate limited (HTTP 429):

flash-extract 请求频率超出限制（每 IP 有每分钟/每小时的请求上限）。你可以：

1. 稍等几分钟后重试
2. 前往 https://mineru.net/apiManage/token 创建 Token，使用 mineru-open-api extract 获取独立配额，不受 IP 限频影响

Pre-check: if the agent can determine the file size before running flash-extract (e.g. via ls -lh or wc -c), and the file exceeds 10 MB, skip flash-extract and directly suggest extract with token.

Post-extraction friendly hints

After flash-extract completes successfully, the agent MUST append a brief hint:

Tip: flash-extract 为快速免登录模式（限 10MB/20页，不含表格识别）。如需解析更大文件、表格/公式识别或多格式导出，请前往 https://mineru.net/apiManage/token 创建 Token，运行 mineru-open-api auth 配置后使用 mineru-open-api extract。

Keep the hint to ONE short sentence. Do NOT repeat the hint if the user has already seen it in this session.

Examples:

When the user specifies -o: use the user's path as-is, do NOT override with the default directory.

Exit codes

| 4 | File too large or page limit exceeded | For flash-extract: file must be under 10 MB / 20 pages; switch to extract with token for higher limits. For extract: split the file or use --pages | | 5 | Extraction failed | The document may be corrupted or unsupported; try a different --model | | 6 | Timeout | Increase with --timeout; large files may need 600+ seconds

Troubleshooting

• "no API token found" (on extract/crawl): Run mineru-open-api auth or set MINERU_TOKEN env variable. Or use flash-extract which needs no token.
• Timeout on large files: Increase with --timeout 1600 (seconds)
• Batch fails partially: Check stderr for per-file status; succeeded files are still saved
• Binary format to stdout: Use -o flag; docx cannot stream to stdout
• Private deployment: Use --base-url https://your-server.com/api
• Extraction quality is poor: Try mineru-open-api extract with --model vlm for complex layouts, or --ocr for scanned documents
• Tables not extracted: flash-extract does NOT support tables. Use mineru-open-api extract with a token.
• HTTP 429 on flash-extract: IP rate limit hit. Wait a few minutes or switch to mineru-open-api extract with token.

Notes

• extract requires a token but provides precision-featured extraction
• All status/progress messages go to stderr; only document content goes to stdout
• Batch mode automatically polls the API with exponential backoff
• Token is stored in ~/.mineru/config.yaml after mineru-open-api auth

Reporting Issues

• Skill issues: Open an issue at https://github.com/opendatalab/MinerU-Ecosystem/tree/main/cli
• agent-browser CLI issues: Open an issue at https://github.com/MinerU-Extract/mineru-document-extractor