liteparse

Extract text and bounding boxes from PDFs, Office files, and images.

13|3|Updated Jun 10, 2026

Search Tags:#text extraction #OCR #PDF processing #document parsing #layout analysis

Ready to run

npx skills add https://github.com/tassiovale/claude-code-kit --skill liteparse-tassiovale

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: liteparse
Source: https://github.com/tassiovale/claude-code-kit/tree/main/skills/liteparse
Command: npx skills add https://github.com/tassiovale/claude-code-kit --skill liteparse-tassiovale

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires liteparse, libreoffice, imagemagick, tesseract, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

LiteParse addresses the challenge of efficiently extracting text and spatial information from various document formats, enabling users to process and analyze documents with greater speed and accuracy.

Core Features & Use Cases

Fast Local Parsing: Parse PDFs, Office files, and images without relying on cloud APIs.
Spatial Text Extraction: Extract text with bounding boxes for layout-aware analysis.
OCR: Perform OCR on scanned PDFs and images using bundled Tesseract.
Use Case: A researcher needs to quickly extract text and images from a large collection of papers and convert them into a structured format for analysis.

Quick Start

To parse the document 'research_papers.pdf' and extract text with bounding boxes, run the following command:

lit parse research_papers.pdf --format json -o output.json

Frequently Asked Questions about liteparse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text with bounding boxes from a PDF for layout-aware RAG?▼

You can extract text with bounding boxes by running a local parse command on your PDF to output structured JSON. This structured format includes spatial information necessary for layout-aware RAG and citation grounding.

Can I perform OCR on scanned PDFs and images without cloud APIs?▼

Yes, you can perform local OCR on scanned PDFs and images without cloud APIs by utilizing the bundled Tesseract dependency. This extracts text from image-based documents while maintaining spatial layout data in the JSON output.

Does document parsing support Office files or just PDF processing?▼

Document parsing supports both PDF processing and Office files. It handles local extraction of text and spatial information from various formats, using LibreOffice as an optional dependency for converting Office files during the extraction process.

Do I need Python 3.10 and Tesseract to parse documents locally?▼

Yes, Python 3.10 or higher is required to run the document parser. Tesseract, ImageMagick, and LibreOffice are optional dependencies required specifically for OCR and Office file conversion during the parsing process.

What is the best way to extract text and images from research papers for analysis?▼

The best way to extract text and images from research papers is using a local document parsing tool that outputs structured JSON with spatial text and bounding boxes. This converts large collections of papers into a structured format for rapid analysis.