# Marker — Convert PDF to Markdown for AI Tools

> High-accuracy PDF to Markdown converter optimized for AI pipelines. Marker handles tables, equations, code blocks, and multi-column layouts with deep learning OCR.

## Install

Save as a script file and run:

## Quick Use

```bash
pip install marker-pdf
```

```bash
# Convert a single PDF
marker_single input.pdf output_dir/

# Convert a directory of PDFs
marker output_dir/ --workers 4
```

```python
from marker.converters.pdf import PdfConverter
from marker.models import create_model_dict

models = create_model_dict()
converter = PdfConverter(artifact_dict=models)
rendered = converter("paper.pdf")
print(rendered.markdown)
```

## What is Marker?

Marker is a deep learning PDF-to-Markdown converter designed for AI pipelines. It accurately extracts text, tables, equations, code blocks, and images from PDFs — including scanned documents. Unlike rule-based tools, Marker uses trained models for layout detection, OCR, table recognition, and equation conversion, achieving significantly higher accuracy on complex academic and technical documents.

**Answer-Ready**: Marker converts PDFs to clean Markdown using deep learning. Handles tables, equations, code blocks, multi-column layouts, and scanned documents. 10x faster than similar tools, 90%+ accuracy on academic papers. Used in RAG pipelines for document ingestion. 19k+ GitHub stars.

**Best for**: AI teams building RAG pipelines or processing technical PDFs. **Works with**: Any LLM framework, LangChain, LlamaIndex. **Setup time**: Under 3 minutes.

## Core Features

### 1. High-Accuracy Extraction

| Element | Accuracy |
|---------|----------|
| Body text | 95%+ |
| Tables | 90%+ |
| Equations (LaTeX) | 85%+ |
| Code blocks | 90%+ |
| Multi-column | 90%+ |

### 2. Batch Processing

```bash
# Process 1000 PDFs with 8 workers
marker input_dir/ --workers 8 --output_format markdown
```

### 3. Multiple Output Formats

```bash
# Markdown (default)
marker_single paper.pdf out/ --output_format markdown

# JSON (structured)
marker_single paper.pdf out/ --output_format json

# HTML
marker_single paper.pdf out/ --output_format html
```

### 4. Language Support

Supports 50+ languages with automatic detection. Works especially well on English, Chinese, Japanese, Korean, and European languages.

### 5. GPU Acceleration

```bash
# Auto-detects CUDA/MPS
# CPU fallback available but slower
TORCH_DEVICE=cuda marker_single paper.pdf out/
```

## Marker vs Alternatives

| Feature | Marker | PyMuPDF | Zerox | Docling |
|---------|--------|---------|-------|---------|
| Tables | Deep learning | Rule-based | Vision LLM | Deep learning |
| Equations | LaTeX output | Text only | Depends on LLM | Limited |
| Scanned PDFs | Built-in OCR | No | Yes (via LLM) | Yes |
| Speed | Fast (GPU) | Very fast | Slow (API calls) | Moderate |
| Cost | Free (local) | Free | API costs | Free |
| Accuracy | Very high | Moderate | High | High |

## FAQ

**Q: How does it compare to Zerox?**
A: Marker runs locally with no API costs and is much faster for batch processing. Zerox uses vision LLMs (GPT-4o) which cost per page but can handle edge cases better.

**Q: Does it work on scanned PDFs?**
A: Yes, includes built-in OCR using deep learning models.

**Q: What hardware do I need?**
A: GPU recommended for speed (NVIDIA CUDA or Apple MPS). CPU works but is 5-10x slower.

## Source & Thanks

> Created by [VikParuchuri](https://github.com/VikParuchuri). Licensed under GPL-3.0.
>
> [VikParuchuri/marker](https://github.com/VikParuchuri/marker) — 19k+ stars

<!-- ZH -->

## 快速使用

```bash
pip install marker-pdf
marker_single input.pdf output_dir/
```

一行命令将 PDF 转为高质量 Markdown。

## 什么是 Marker？

Marker 是基于深度学习的 PDF 转 Markdown 工具，精确提取表格、公式、代码块和多栏版式，支持扫描件 OCR。

**一句话总结**：深度学习 PDF 转 Markdown，精确处理表格/公式/代码/多栏，支持 50+ 语言和扫描件，比同类快 10x，19k+ stars。

**适合人群**：构建 RAG 管线或处理技术文档的 AI 团队。

## 核心功能

### 1. 高精度提取
表格 90%+，公式转 LaTeX，代码块识别。

### 2. 批量处理
多进程并行，支持 GPU 加速。

### 3. 多语言
50+ 语言自动检测，中文表现优秀。

## 常见问题

**Q: 和 Zerox 比？**
A: Marker 本地运行无 API 费用，批量处理快得多。Zerox 用视觉模型按页收费。

**Q: 支持扫描件？**
A: 支持，内置深度学习 OCR。

## 来源与致谢

> [VikParuchuri/marker](https://github.com/VikParuchuri/marker) — 19k+ stars, GPL-3.0

---
Source: https://tokrepo.com/en/workflows/cfafd4e4-d57d-481d-a44c-10f1c8a66cb0
Author: Script Depot