Parse multi-format RAG inputs with OmniParse
Run OmniParse locally or as an API service to turn documents, images, audio, video, and web pages into structured Markdown-ready inputs for agent and RAG workflows.
Prerequisites
Linux, Python 3.10, Conda or virtualenv, Docker optional, GPU recommended for heavier parsing workloads
Installation
Use the upstream install or setup path that matches your environment:
- git clone https://github.com/adithya-s-k/omniparse
- conda create -n omniparse-venv python=3.10
- conda activate omniparse-venv
- pip install -e .
Requirements and caveats from upstream:
- ✅ Easily deployable using Docker and Skypilot \
- To use OmniParse with Docker, execute the following commands:
Basic usage or getting-started notes:
[!IMPORTANT]
The server only works on Linux-based systems. This is due to certain dependencies and system-specific configurations that are not compatible with Windows or macOS.
cd omniparse
Extracted from upstream docs: https://raw.githubusercontent.com/adithya-s-k/omniparse/HEAD/README.md