#1515th of 50 in Data and scraping for AIFor data and documents, documents and ocr
liteparse
Local PDF and Office document parser with bounding boxes and Markdown output
- Stars
- 13k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Rust
4,415 on 21 Apr 202613,034 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
LlamaIndex is hiring: 4 open roles
Overview
LiteParse extracts spatially laid-out text from PDFs using PDFium, at roughly 2-5 ms per page, and converts DOCX, XLSX, PPTX and images through LibreOffice or Rust image crates. It outputs Markdown, JSON with bounding boxes, or plain text, and can run Tesseract or an HTTP OCR server on pages that need it. A Rust core ships with a `lit` CLI plus Node.js, Python and WASM bindings.
Who it is for: Developers feeding PDFs and Office files into RAG pipelines or LLM agents
Strengths
- No ML model or GPU required; ~2-5 ms per page text extraction via PDFium
- Bindings for Rust, Node.js, Python and browser WASM, with one `lit` CLI
- Pluggable OCR: bundled Tesseract or any server following its OCR HTTP API spec
- Worker pool mode gives parallel parsing and hard per-parse timeouts
Weaknesses
- Markdown is heuristic and rule-based; complex layouts may render imperfectly
- Charts score near zero in its own ParseBench results
- Math is not output as LaTeX; olmOCR-bench math categories score 0%
- Office formats depend on LibreOffice for conversion
What it needs
- no GPU
- Docker
- Needs LibreOffice (for DOCX/XLSX/PPTX), Optional HTTP OCR server (EasyOCR, PaddleOCR, RapidOCR)
- Models: Tesseract OCR (bundled), PaddleOCR PP-OCRv5 via HTTP, EasyOCR via HTTP
Quick answers
Is liteparse open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run liteparse with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does liteparse need a GPU?
No, it runs without one.
Also in Data and scraping for AI
See all 50| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 90 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 88 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |