# Document parsing

Capability · https://godooo.ai/en/capability/document-parsing

> Document parsing: 17 AI tools in this graph can do it, including RAGFlow, MinerU, PaddleOCR, MarkItDown and PDF Skill.

Turn PDFs, scans and office files into clean text, tables and structured data.

- **Takes in:** Document, Image
- **Gives out:** Text, Data

## Tools that do it

| Tool | Type | How well | Pricing | Open source | How you run it |
| --- | --- | --- | --- | --- | --- |
| [RAGFlow](https://godooo.ai/en/product/ragflow) | Product | main job* | Open source, free | Yes | Self-host, API, Web |
| [MinerU](https://godooo.ai/en/framework/mineru) | Framework | main job* |  | Yes | Terminal, Runs offline, API, Self-host |
| [PaddleOCR](https://godooo.ai/en/framework/paddleocr) | Framework | main job* |  | Yes | Self-host, Runs offline, Terminal, API |
| [MarkItDown](https://godooo.ai/en/framework/markitdown) | Framework | main job* |  | Yes | Terminal, Runs offline, Self-host |
| [PDF Skill](https://godooo.ai/en/skill/pdf) | Skill | main job* |  |  | API |
| [Docling](https://godooo.ai/en/framework/docling) | Framework | main job* |  | Yes | Self-host, Runs offline, Terminal, API |
| [Marker](https://godooo.ai/en/framework/marker) | Framework | main job* |  | Yes | Self-host, Runs offline, Terminal, API |
| [Unstructured](https://godooo.ai/en/framework/unstructured) | Framework | main job* |  | Yes | Self-host, API, Terminal |
| [Surya](https://godooo.ai/en/framework/surya) | Framework | main job* |  | Yes | Self-host, Runs offline, API |
| [LlamaIndex](https://godooo.ai/en/framework/llamaindex) | Framework | supported* |  | Yes | API, Self-host, Runs offline |
| [Firecrawl](https://godooo.ai/en/product/firecrawl) | Product | supported* | Open source, free | Yes | API, Self-host, Terminal |
| [Firecrawl MCP Server](https://godooo.ai/en/mcp/firecrawl) | MCP server | supported* |  | Yes | API, Self-host, Terminal |
| [PrivateGPT](https://godooo.ai/en/framework/privategpt) | Framework | supported* |  | Yes | Self-host, API, Runs offline |
| [FastGPT](https://godooo.ai/en/product/fastgpt) | Product | supported* | Open source, free | Yes | Web, Self-host, API |
| [kotaemon](https://godooo.ai/en/product/kotaemon) | Product | supported* | Open source, free | Yes | Web, Self-host, Runs offline |
| [QAnything](https://godooo.ai/en/product/qanything) | Product | supported* | Open source, free | Yes | Self-host, Runs offline, API |
| [Jina Reader](https://godooo.ai/en/product/jina-reader) | Product | supported* | Open source, free | Yes | API, Self-host |

\* proposed by a machine, awaiting calibration

## Related

- **Needed to:** [Build an AI customer support bot](https://godooo.ai/en/goal/customer-support-bot), [Q&A over your documents](https://godooo.ai/en/goal/document-qa-system), [Translate documents](https://godooo.ai/en/goal/translate-documents), [Collect data from the web](https://godooo.ai/en/goal/scrape-web-data)

## Questions

### What is Document parsing?

Turn PDFs, scans and office files into clean text, tables and structured data. Document parsing: 17 AI tools in this graph can do it, including RAGFlow, MinerU, PaddleOCR, MarkItDown and PDF Skill.

### Which tools are built for “Document parsing”?

RAGFlow, MinerU, PaddleOCR, MarkItDown, PDF Skill, Docling, Marker and Unstructured.

### Are there free tools for “Document parsing”?

RAGFlow, MinerU, PaddleOCR, MarkItDown, Docling, Marker, Unstructured and Surya.

### Which open-source tools can do “Document parsing”?

RAGFlow, MinerU, PaddleOCR, MarkItDown, Docling, Marker, Unstructured and Surya.

### Which tools for “Document parsing” run offline?

MinerU, PaddleOCR, MarkItDown, Docling, Marker, Surya, LlamaIndex and PrivateGPT.

---

Last updated 2026-09-24 · Markdown version of https://godooo.ai/en/capability/document-parsing. Every page on this site has one: add .md to its address.