OpenSource-Hub
L

liteparse

SHA-256
11.8k stars·Developer Tools·SHA-256 checksum verified

A fast, open-source document parser that extracts text, markdown, and structured JSON from PDFs with optional OCR support, running entirely locally with zero cloud dependencies.

Smart Download

Download Download Version

vpython-v2.10.0 · 9.1 MB

Fast, local PDF parser with markdown/JSON output and OCR — a lighter alternative to cloud-based document parsers.

Core Features

  • Fast PDF text extraction with bounding boxes
  • Markdown/JSON/Text output with heading/table/list reconstruction
  • Built-in Tesseract OCR or custom HTTP OCR servers
  • Input support: PDF, DOCX, XLSX, PPTX, images
  • Multi-language bindings: Rust, Node.js, Python, WASM, cross-platform

What It Can't Do

  • Markdown reconstruction quality drops for complex documents (dense tables, multi‑column, scanned PDFs). OCR requires Tesseract or a custom HTTP server. WASM build does not include the CLI.

Use Cases

  • Batch extract PDF content as structured data for RAG pipelines
  • Preprocess documents for LLMs by generating clean Markdown

Detailed Introduction

LiteParse is a standalone OSS PDF parsing tool focused on speed and lightness. It provides high-quality spatial text parsing with bounding boxes, markdown reconstruction (headings, tables, lists), and OCR integration via Tesseract or custom HTTP servers. Unlike cloud-heavy solutions like LlamaParse, LiteParse runs 100% locally on your machine, making it ideal for offline or privacy-sensitive pipelines. It supports multiple output formats (Markdown, JSON, Text), screenshot generation, complexity detection, and multiple language bindings (Rust, Node.js, Python, WASM). Compared to tools like pdfplumber, LiteParse offers richer output with built-in markdown and OCR, broader format support (DOCX, XLSX, PPTX, images), and cross-platform compatibility (Linux, macOS, Windows). It is licensed under Apache-2.0 and has earned over 11,800 stars on GitHub.

Tags

pdfdocument-parserocrmarkdownrustwasmllm

Getting Started

1

Download installer

Click the button above to download the installer for your system

2

Install the software

Double-click the downloaded installer and follow the prompts

3

Install globally via npm: npm i -g @llamaindex/liteparse

4

Install via pip: pip install liteparse

5

Parse a PDF: lit parse document.pdf --format markdown -o output.md

Install Guide
  1. Install globally via npm: npm i -g @llamaindex/liteparse
  2. Install via pip: pip install liteparse
  3. Parse a PDF: lit parse document.pdf --format markdown -o output.md
File Integrity

SHA-256 checksum verified

Checksum extracted from GitHub official Release page

SHA256 Checksum

883462e89c4b24d9c92cf04eb67ed867563968c4c92559aa04540f034b11d8bf

This checksum is extracted from the GitHub Release page. Verify file integrity after download.

All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.

Open Source Transparency

View GitHub Source
Environment Guide

Uninstall Info

Node: npm uninstall -g @llamaindex/liteparse; Python: pip uninstall liteparse; Rust: cargo uninstall liteparse.

No Extra Dependencies

Ready to use after download. No additional runtime required.

Project Info
LicenseApache-2.0
Last Updated2026-07-29T09:21:49Z
GitHub RepositoryOfficial Website

Similar Projects