OmniParse: open-source tool turns 20+ file formats into LLM-ready structured data
tom_doerr · x · 2026-09-10
OmniParse, an open-source project (7.8k GitHub stars), ingests unstructured data — documents, tables, images, video, audio, and web pages (20 file types) — and converts it into high-quality structured Markdown or JSON optimized for LLM applications.
Key features:
- Runs fully locally, no external APIs
- Fits on a single T4 GPU
- Table extraction, image extraction/captioning, audio/video transcription, web crawling
- Deployable via Docker/Skypilot, Colab-friendly, with a Gradio UI
It targets data preparation pipelines for RAG, fine-tuning, and other GenAI workflows.
More from coding & agent
- How to run a hackathon entirely with ChatGPT Sites, all from your phone — gabrielchua · 2026-09-10
- 34-day agent run processed 21.5B input tokens for $200 with 98% cache hits — nodo48 · 2026-09-10
- Engineer stops reading AI-written code, shares 4 ways to keep judgment sharp — every · 2026-09-10
- Memory Doesn't Equal Expertise: Builders Ask Where Domain-Specific Agents Get Their Knowledge — sartomiki · 2026-09-10
- Google Simplifies Gemini API Skills, Boosting Correct API Code Generation to 87% — patloeber · 2026-09-10
- Do Persistent AI 'Teammates' Actually Work? Users Question Grok Bot's Real-World Value — No-Advantage8770 · 2026-09-10