data/engineering/liteparse

Parse unstructured documents into clean text and structured JSON.

1|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/2nth-ai/skills --skill data-engineering-liteparse
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: data/engineering/liteparse
Source: https://github.com/2nth-ai/skills/tree/main/data/engineering
Command: npx skills add https://github.com/2nth-ai/skills --skill data-engineering-liteparse

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @llamaindex/liteparse, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of parsing unstructured documents such as PDFs, Word, PowerPoint, Excel, and images, converting them into structured data for use in RAG pipelines, data analytics, or AI training without reliance on cloud-based solutions.

Core Features & Use Cases

  • Local Document Parsing: Parses a wide variety of document formats locally on the user's system, supporting both plain text extraction and JSON formatting with bounding boxes.
  • No Cloud Dependencies: Eliminates the need for cloud-based services, making it ideal for environments where cloud services are not allowed or when handling sensitive data.
  • Document Processing Options: Offers multiple modes of document processing, including text extraction, OCR (Optical Character Recognition), and screenshot generation for multimodal content.

Quick Start

Run the command 'lit parse input.pdf --format json -o output.json' to parse 'input.pdf' into structured JSON.

Frequently Asked Questions about data/engineering/liteparse

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

FAQPage Schema
How do I parse PDFs locally into structured JSON for RAG ingestion?

You parse PDFs locally into structured JSON by running a command like 'lit parse input.pdf --format json -o output.json', extracting clean text and bounding boxes without relying on cloud services. This local-first approach ensures data privacy during RAG ingestion.

Can I extract text from unstructured documents without cloud dependencies?

Yes, you can extract text from unstructured documents without cloud dependencies. This Skill processes various formats entirely on-premises, making it ideal for environments where cloud services are restricted or sensitive data must remain localized.

Does local document parsing support OCR and screenshot generation for images?

Yes, local document parsing supports OCR and screenshot generation for images. It offers multiple processing modes including plain text extraction, Optical Character Recognition, and screenshot generation for handling multimodal content.

What is the best way to convert Word and Excel files into clean text for AI training?

The best way to convert Word and Excel files into clean text for AI training is using a local-first parser. It streamlines converting unstructured formats like Word, PowerPoint, and Excel into structured data securely on your system.

When should I not use a cloud-based document parsing solution?

You should not use a cloud-based document parsing solution when handling sensitive data or operating in environments where cloud services are not allowed. In these cases, a local-first parsing approach ensures localized and secure data processing.