adithya-s-k/omniparse

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

51
/ 100
Established

This project helps data professionals and AI engineers prepare diverse data for use with AI applications. It takes various unstructured inputs like documents, images, videos, audio, and web pages, and converts them into structured, high-quality text, such as markdown. The output is specifically optimized for tasks like RAG or fine-tuning large language models.

6,805 stars.

Use this if you need to standardize and optimize messy, multi-format data from sources like PDFs, scanned documents, images, or web pages, to feed into your generative AI systems.

Not ideal if you're looking for a simple data extraction tool for basic CSVs or structured databases, or if you primarily work on macOS or Windows for deployment.

data-preparation AI-engineering document-processing multimedia-analysis information-extraction
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

6,805

Forks

538

Language

Python

License

GPL-3.0

Category

scraper

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/perception/adithya-s-k/omniparse"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.