skills.rest
Ritabrata-Chakraborty
Ritabrata-ChakrabortyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

liteparse

Extract spatial text and bounding boxes from local documents with OCR.

Updated Jun 6, 2026
Search Tags:#text extraction#OCR#document parsing#local processing#layout-aware
One-click install
npx skills add https://github.com/Ritabrata-Chakraborty/Claude-Setup --skill liteparse-ritabrata-chakraborty
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: liteparse
Source: https://github.com/Ritabrata-Chakraborty/Claude-Setup/tree/main/skills/liteparse
Command: npx skills add https://github.com/Ritabrata-Chakraborty/Claude-Setup --skill liteparse-ritabrata-chakraborty

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 parsing various document formats, providing spatial text extraction with bounding boxes, OCR capabilities, and local processing without cloud dependencies.

Core Features & Use Cases

  • Local Parsing: Process documents locally without relying on cloud APIs.
  • Spatial Text Extraction: Extract text with bounding boxes for layout-aware applications.
  • OCR: Perform OCR on scanned PDFs and images using bundled Tesseract.
  • Use Case: Ideal for extracting text from PDFs, DOCX files, and images, or for OCR tasks where local processing and spatial information are required.

Quick Start

To extract text from a PDF, use the LiteParse skill with the command: lit parse paper.pdf

Frequently Asked Questions about liteparse

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

FAQPage Schema
How do I extract text from a PDF with bounding boxes locally?▼

Local document parsing with spatial text and bounding boxes extracts layout-aware text from PDFs using Python and Rust. You can parse documents locally by running the command `lit parse paper.pdf` without relying on cloud APIs.

Can I perform OCR on scanned documents without cloud dependencies?▼

Yes, you can perform local OCR on scanned PDFs and images without cloud dependencies. The parsing process utilizes bundled Tesseract to extract text from images entirely on your local machine, ensuring data privacy and fast processing.

Do I need LibreOffice and ImageMagick installed to parse DOCX files?▼

Yes, parsing DOCX files and performing OCR requires liteparse, LibreOffice, and ImageMagick. These dependencies are necessary for the local processing engine to handle various document formats and extract spatial text effectively.

What is the best way to get layout-aware text extraction from images?▼

The best way to get layout-aware text extraction from images is using local document parsing with spatial text and bounding boxes. This approach uses bundled Tesseract for OCR, providing fast parsing and spatial information for layout-aware applications without cloud APIs.

Does this local document parsing approach work for fast processing workflows?▼

Yes, local document parsing is ideal for fast processing workflows requiring spatial information and OCR. By using Python and Rust without cloud dependencies, it provides efficient text extraction from PDFs, DOCX files, and images directly on your machine.

Related Skills

Explore More Software Engineering Skills→
galeepgaleep

liteparse

Extract text and metadata from PDFs, DOCX, and images with spatial bounding boxes.

Community
Advanced
tassiovaletassiovale
13

liteparse

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

Community
Intermediate
Quill-AgentQuill-Agent
3

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced
a2ajinkyaa2ajinkya
1

liteparse-ingest

Convert PDFs, Office files, and images into structured JSON via LiteParse.

Community
Intermediate