Tech Forum staff

SoMark

SoMark is a document-parsing company headquartered in Shanghai. It builds models and APIs that turn PDFs and document images into structured data for AI applications. This article is contributed by the SoMark team.

1 article

Analysis

SoMark Releases Code and Weights for OXR, a 1.3B Document Parser Built for Self-Hosted RAG and Agent Pipelines

SoMark released the code and weights for OXR, a 1.3B document parsing model for self-hosted RAG and agent pipelines, with Markdown and JSON output.

SoMark / October 21, 2026