Skip to content
Back to skills

Run Llama Liteparse

ASecurity

LiteParse — Rust document parser của LlamaIndex: PDF/Word/Excel/PPT/image → JSON với bounding boxes. Node.js/Python/WASM bindings. Tesseract OCR bundled, không cần cloud.

  • 10 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 9, 2026
ai-agentstypescriptpythonrustgobashnodegitapibackendperformance

Works with

  • cli
  • api

Security analysis

A92/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned September 9, 2026

npx -y skills add yanacuti1121/Yana-AI --skill run-llama--liteparse --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Run Llama Liteparse?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Run Llama  Liteparse
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/yanacuti1121-run-llama-liteparse/badge)](https://www.skillsdirectory.com/skills/yanacuti1121-run-llama-liteparse)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: run-llama--liteparse
description: "LiteParse — Rust document parser của LlamaIndex: PDF/Word/Excel/PPT/image → JSON với bounding boxes. Node.js/Python/WASM bindings. Tesseract OCR bundled, không cần cloud."
allowed-tools: Bash, Read, Write
user-invocable: true
---

LiteParse: fast local document parser viết bằng Rust — PDF + office docs + images → structured JSON với spatial bounding boxes. Zero cloud dependency.

## Install

```bash
# Node.js
npm install liteparse

# Python
pip install liteparse

# Rust
cargo add liteparse
```

## Supported Formats

```
Native:   PDF (trực tiếp, không convert)
Office:   .doc .docx .odt .ppt .pptx .odp .xls .xlsx .ods .csv .tsv
Images:   JPG PNG GIF BMP TIFF WebP SVG
          (qua ImageMagick → OCR)
```

## API

```typescript
import { parse } from 'liteparse'

// JSON với bounding boxes
const result = await parse('document.pdf', { format: 'json' })
// result.pages[0].blocks[0].bbox = { x, y, width, height }
// result.pages[0].blocks[0].text = "..."

// Plain text với layout preserved
const text = await parse('report.docx', { format: 'text' })

// Screenshot tại DPI tùy chỉnh
await parse('slide.pptx', { format: 'screenshot', dpi: 300 })
```

```python
from liteparse import parse

result = parse("document.pdf", format="json")
for page in result["pages"]:
    for block in page["blocks"]:
        print(block["text"], block["bbox"])
```

## Performance

```
Parallel OCR processing  — configurable worker threads
Selective OCR            — chỉ chạy khi cần (không phải mọi page)
Page-range targeting     — parse trang 10-20, skip phần còn lại
Default DPI: 150         — tùy chỉnh được
```

## OCR Options

```
Default: Tesseract (bundled, offline)
HTTP backends: EasyOCR, PaddleOCR (accuracy cao hơn)
Custom: implement theo API spec
```

## CLI

```bash
liteparse document.pdf --format json --pages 1-10 --output result.json
liteparse batch/ --format text --workers 4
```

## Khi nào dùng

- RAG pipeline: parse docs → chunk → embed
- Extract structured data từ PDF reports
- Convert office docs sang Markdown cho LLM context
- OCR images trong batch pipeline

## Source

https://github.com/run-llama/liteparse · Apache-2.0 · +1613⭐/week

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.