// Document parsing & crawling
run-llama/liteparse
A fast, helpful, and open-source document parser
Official · LlamaIndexApache-2.0Active
01Overview
run-llama/liteparse is an official LlamaIndex repository in our “Document parsing & crawling” category, written mainly in Rust and licensed under Apache-2.0. As of 2026-10-23 it has 12,901 stars and 888 forks, ranking #14 of 20 tracked Document parsing & crawling repos and #538 of all 1046 repos we track. It was created on 2026-02-09 (about 0.7 years ago); the latest commit is from 2026-10-22, so it is actively updated. The latest release is node-v2.17.0 (2026-10-23), with 20 releases in the last 30 days.
GitHub topics:document-ocrdocument-processingocrocr-recognitionpdfpdf-parsertext-extraction
02Recent releases
-
run-llama/liteparse node-v2.17.0 Minor
chore(deps): bump lopdf from 0.38.0 to 0.42.0 by @dependabot[bot] in https://github.com/run-llama/liteparse/pull/515
-
run-llama/liteparse python-v2.17.0 Minor
chore(deps): bump lopdf from 0.38.0 to 0.42.0 by @dependabot[bot] in https://github.com/run-llama/liteparse/pull/515
-
run-llama/liteparse wasm-v2.17.0 Minor
chore(deps): bump lopdf from 0.38.0 to 0.42.0 by @dependabot[bot] in https://github.com/run-llama/liteparse/pull/515
-
run-llama/liteparse crates-v2.17.0 Minor
chore(deps): bump lopdf from 0.38.0 to 0.42.0 by @dependabot[bot] in https://github.com/run-llama/liteparse/pull/515
-
run-llama/liteparse docker-v2.16.0 Minor
Docker images published to GHCR:
03Related repos (shared GitHub topics)
- opendataloader-project/opendataloader-pdf ★ 29.9k · ocr, ocr-recognition, pdf, pdf-parserPDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
- opendatalab/MinerU ★ 82.3k · ocr, pdf, pdf-parserTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
- bytedance/Dolphin ★ 9,065 · ocr, pdf, pdf-parserThe official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
- Unstructured-IO/unstructured ★ 15.6k · ocr, pdfConvert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models…
04More from LlamaIndex
Vendor page →- llama_index ★ 52.6k · Agent frameworks
- rags ★ 6,546 · RAG & knowledge bases
- llama_cloud_services ★ 4,270 · RAG & knowledge bases
05Same category
All repos →
firecrawl/firecrawl Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. Document parsing & crawling★ 194k 
microsoft/markitdown Python tool for converting files and office documents to Markdown. Document parsing & crawling · official★ 192k 
PaddlePaddle/PaddleOCR Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. Document parsing & crawling · official★ 91.5k 
D4Vinci/Scrapling ️ A Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily… Document parsing & crawling★ 89.2k 
unclecode/crawl4ai Open-source web crawler and scraper for LLMs and AI agents: any website into clean, LLM-ready Markdown. Run it yourself, or use Crawl4AI Cloud with one key. Join our Discord htt… Document parsing & crawling★ 86.1k FAQ
What licence does liteparse use?
Apache-2.0, as shown on GitHub. Check the LICENSE file in run-llama/liteparse before commercial use.
Is liteparse still maintained?
The last commit was on 2026-10-22 (1 days before 2026-10-23) and the latest release is node-v2.17.0 from 2026-10-23.
How popular is liteparse among Document parsing & crawling projects?
#14 of 20 by stars (12,901). The most-starred in this category is firecrawl/firecrawl (194k).