← Discover
Discover · GitHub · Liteparse↑ +929 today

Quickly parse your documents with Rust

Liteparse (run-llama); is an open source document parser written in Rust to parse documents quickly and efficiently. It facilitates AI and RAG processes by making complex document structures processable.

Updates

  • September 16, 2026: Stars 12,311 → 12,314, latest release node-v2.14.6 (September 15, 2026).
  • September 15, 2026: Stars 12,269 → 12,311, latest release docker-v2.14.5 (September 15, 2026).
  • September 8, 2026: Stars 12,220 → 12,269, latest release node-v2.14.4 (September 7, 2026).
  • September 2, 2026: Stars 12,210 → 12,220, latest release node-v2.14.3 (September 1, 2026).

What you get

  • Provides fast and efficient document parsing.
  • It makes complex structures machinable.
  • Fully compatible with AI and RAG pipelines.

Installation

Using pip (PyPI)
pip install liteparse

How to install, how to use?

🤖 Paste this into your AI agent (Claude Code · Codex · Antigravity)

Install the LiteParse PDF parsing tool with 'pip install liteparse', then extract the text of a PDF with the command 'lit parse document.pdf' or save as structured JSON with bounding boxes with 'lit parse document.pdf --format json -o output.json'.

Related dictionary terms

OutputPipelineRAGPDFOpen SourceRust
Who it is forDevelopers who process documents/data
DifficultyMedium developer tool
What offersFast document parsing
FeeFree · open source (Apache-2.0)
LicenseApache-2.0 · ayrıntı aşağıda
License: Apache-2.0 · you can use it freely, modify it, make commercial use (also includes patent protection).

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-05-30: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. This page was machine-translated from the Turkish original · the Turkish version prevails.