\r \r

Summarize PDF - Quick Content Extraction\r

\r Convert PDF files to clean Markdown using MinerU Open API. No API key required.\r \r

Quick Start\r

\r

# Summarize PDF - Quick Content Extraction\r
mineru-open-api flash-extract report.pdf\r
\r
# Summarize PDF - Quick Content Extraction\r
mineru-open-api flash-extract https://cdn-mineru.openxlab.org.cn/demo/example.pdf\r
\r
# Summarize PDF - Quick Content Extraction\r
mineru-open-api flash-extract report.pdf -o ./output/\r
\r
# Summarize PDF - Quick Content Extraction\r
mineru-open-api flash-extract report.pdf --pages 1-10\r
```\r
\r
## Language Rule\r
\r
You MUST reply to the user in the SAME language they use. This is non-negotiable.\r
\r
## Capabilities\r
\r
- Extracts text, tables, and formulas from PDF\r
- Supports both local files and URLs directly\r
- Page range selection with `--pages`\r
- Language hint with `--language` (default: `ch`, use `en` for English)\r
- No API key, no signup, no authentication\r
- Max 10MB / 20 pages per document\r
\r
## When to Use\r
\r
- User asks to "read", "extract", "convert", or "parse" a PDF\r
- User shares a PDF file or PDF link and asks for its content\r
- User wants to summarize or analyze a PDF document\r
- User needs PDF content in Markdown format\r
\r
## CLI Reference\r
\r
Run `mineru-open-api flash-extract --help` for all available options.\r
\r
## Data Flow\r
\r
`flash-extract` sends the document to the MinerU API (mineru.net) for processing and returns Markdown. This is a stateless API call — no account, no persistent storage. MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU\r
\r
## Notes\r
\r
- Output is Markdown only; images/tables/formulas may be replaced with placeholders\r
- For larger files (up to 200MB/600 pages) or precision extraction with full assets, use `mineru-open-api extract` (requires auth via `mineru-open-api auth`)\r
- If the CLI cannot be installed via npm/uv/go, download it from https://mineru.net/ecosystem?tab=cli\r